# Account Balance API Source: https://docs.siray.ai/api-reference/account-balance openapi-spec/account-balance.json GET /v1/account/balance Retrieve the identity and balance summary (balance, coupon, available, and frozen amounts) of the account that owns the API key. ## Overview Use this endpoint to inspect the account behind your API key: its identity (email, user ID, name) and a balance summary in US dollars. > [!TIP] > > Use `available_balance` to decide whether to issue new requests. It already accounts for amounts reserved by in-flight generation requests (`frozen_balance`), so no manual subtraction is needed. ## Endpoint * `GET https://api.siray.ai/v1/account/balance` **Headers** * `Authorization: Bearer ` ## Response structure ```json theme={null} { "request_uuid": "f1c2...", "code": 200, "message": "OK", "data": { "user_id": "user-3f8a2c1d", "user_name": "alice", "email": "alice@example.com", "balance": 123.45, "coupon_balance": 1.25, "available_balance": 121.10, "frozen_balance": 3.60 } } ``` ### Fields * `request_uuid`: Identifier of this API call, useful for support and log correlation. * `code` / `message`: Service-level indicators for the request outcome (`200` / `OK` on success). * `data.user_id`: ID of the account that owns the API key. * `data.user_name`: Name of that account. * `data.email`: Email of that account. * `data.balance`: Account balance in USD. * `data.coupon_balance`: Remaining coupon balance in USD (expired coupons excluded). * `data.available_balance`: Balance you can actually spend, in USD: `available_balance = balance + coupon_balance − frozen_balance`. * `data.frozen_balance`: Total amount currently reserved by in-flight requests, in USD. It is `0` when no amount is frozen. All amounts are in **USD, rounded to two decimal places**. ## Usage example ```bash theme={null} curl -X GET "https://api.siray.ai/v1/account/balance" \ -H "Authorization: Bearer ${SIRAY_API_TOKEN}" ``` > `frozen_balance` is reserved by in-flight generation requests and is released automatically once they settle or expire; `available_balance` recovers accordingly without any action on your side. ## Errors The endpoint returns the standard response envelope. Non-`200` `code` values indicate failure and come with a `message` and no `data`. | HTTP status | `code` | Typical cause | | - | - | - | | 401 | 401 | Missing or malformed `Authorization` header; unknown API key. | | 403 | 403 | API key is disabled or expired, or the account is forbidden. | | 500 | 500 | Upstream (billing) validation failure; retry later. | # Error Codes Source: https://docs.siray.ai/api-reference/fail-code Machine-readable failure codes returned in the fail_code field when a request or generation task fails. ## Overview When a generation task fails (`status` is `FAILURE`) or a submit/query request is rejected, the response may include a `fail_code` field. Use this code for programmatic handling; `fail_reason` provides the human-readable message. Names that include `` are templates. The actual code substitutes the parameter name, for example `MissingParameter.Prompt`. ## Codes | fail\_code | HTTP | Description | | - | - | - | | `MissingParameter` | 400 | Missing a required parameter | | `MissingParameter.` | 400 | Missing the specified parameter | | `InvalidParameter` | 400 | Invalid request parameter; also commonly returned when content moderation rejects the request | | `InvalidParameter.` | 400 | Invalid value for the specified parameter | | `InvalidImageURL.EmptyURL` | 400 | Image URL is empty | | `InvalidImageURL.InvalidFormat` | 400 | Image URL, Base64 data, or format could not be parsed | | `InputImageSensitiveContentDetected` | 400 | Input image contains sensitive content | | `InputImageSensitiveContentDetected.PolicyViolation` | 400 | Input image may involve copyright restrictions | | `InputImageSensitiveContentDetected.PrivacyInformation` | 400 | Input image may contain a real person | | `OutputImageSensitiveContentDetected` | 400 | Output image contains sensitive content | | `OutputImageSensitiveContentDetected.DeepFake` | 400 | Output image may contain a forged ID or credential | | `OutputVideoSensitiveContentDetected` | 400 | Output video contains sensitive content | | `OutofContextError` | 400 | Image and text tokens exceed the context length limit | | `AuthenticationError` | 401 | API key or AK/SK is missing, invalid, or expired | | `AccessDenied` | 403 | No permission to access the target resource | | `OperationDenied.ServiceNotOpen` | 403 | Model service is not enabled | | `AccountOverdueError` | 403 | Account has an overdue balance | | `InsufficientBalance` | 403 | Insufficient balance | | `EmailNotVerified` | 403 | Email is not verified | | `KeyDenied` | 403 | API key is disabled | | `InvalidEndpointOrModel.NotFound` | 404 | Model or endpoint does not exist or is not accessible | | `ModelNotOpen` | 404 | Account has not enabled this model | | `UnsupportedModel` | 404 | Model does not support the requested feature | | `ServerOverloaded` | 429 | Service is overloaded | | `InternalServiceError` | 500 | Internal service error | | `TaskSubmitFailed` | Other non-200 | Submission failed but the upstream code could not be parsed | | `MissingParameter.Prompt` | 400 | Prompt is missing or empty | | `MissingParameter.Model` | 400 | Model name is empty | | `InvalidParameter.Prompt` | 400 | Prompt type could not be parsed | | `InvalidParameter.Model` | 400 | Model type could not be parsed | | `InvalidParameter.Request` | 400 | JSON / request structure / multipart parsing failed | | `InvalidParameter.TaskTypeConstraint` | 400 | Parameter is incompatible with the task type | | `InvalidParameter.TaskTypeMismatch` | 400 | Specified task type does not match the detected result | | `InvalidEndpoint.ClosedEndpoint` | 400 | Endpoint is closed or unavailable | | `InvalidArgumentError` | 400 | Invalid protocol parameter | | `InvalidArgumentError.UnknownRole` | 400 | Unsupported role | | `InvalidArgumentError.InvalidImageDetail` | 400 | Image detail only supports auto/high/low | | `InvalidArgumentError.InvalidPixelLimit` | 400 | Invalid custom image pixel upper/lower bound | | `SensitiveContentDetected` | 400 | Input text may contain sensitive information | | `InputTextSensitiveContentDetected` | 400 | Input text triggered content safety filtering | | `ContentPolicyViolation` | 400 | Blocked by local content safety policy | | `InvalidAccountStatus` | 401 | Account status is abnormal | # Introduction Source: https://docs.siray.ai/api-reference/introduction Siray uses a unified API key structure, simplifying integration and allowing access to all models from a single credential. ## Authentication The Siray API uses API keys in the `request headers` to authenticate requests. ```json theme={null} Authorization: Bearer ``` > **[Get API Key](https://console.siray.ai/keys)** # Claude Fable 5.1 Source: https://docs.siray.ai/api-reference/model-api/claude-fable-5.1 openapi-spec/claude-fable-5.1.json POST /v1/chat/completions # claude-haiku-4-5-20251001 Source: https://docs.siray.ai/api-reference/model-api/claude-haiku-4-5-20251001 openapi-spec/claude-haiku-4-5-20251001.json POST /v1/chat/completions # Claude Haiku 4.5 Source: https://docs.siray.ai/api-reference/model-api/claude-haiku-4.5 openapi-spec/claude-haiku-4.5.json POST /v1/chat/completions # Claude Haiku 5.5 Source: https://docs.siray.ai/api-reference/model-api/claude-haiku-5.5 openapi-spec/claude-haiku-5.5.json POST /v1/chat/completions # Claude Opus 4.6 Source: https://docs.siray.ai/api-reference/model-api/claude-opus-4.6 openapi-spec/claude-opus-4.6.json POST /v1/chat/completions # Claude Opus 5.5 Source: https://docs.siray.ai/api-reference/model-api/claude-opus-5.5 openapi-spec/claude-opus-5.5.json POST /v1/chat/completions # claude-sonnet-4-5-20250929 Source: https://docs.siray.ai/api-reference/model-api/claude-sonnet-4-5-20250929 openapi-spec/claude-sonnet-4-5-20250929.json POST /v1/chat/completions # Claude Sonnet 4.5 Source: https://docs.siray.ai/api-reference/model-api/claude-sonnet-4.5 openapi-spec/claude-sonnet-4.5.json POST /v1/chat/completions # Claude Sonnet 4.6 Source: https://docs.siray.ai/api-reference/model-api/claude-sonnet-4.6 openapi-spec/claude-sonnet-4.6.json POST /v1/chat/completions # Claude Sonnet 5.5 Source: https://docs.siray.ai/api-reference/model-api/claude-sonnet-5.5 openapi-spec/claude-sonnet-5.5.json POST /v1/chat/completions # DeepSeek V4 Flash Source: https://docs.siray.ai/api-reference/model-api/deepseek-v4-flash openapi-spec/deepseek-v4-flash.json POST /v1/chat/completions # DeepSeek V4 Pro Source: https://docs.siray.ai/api-reference/model-api/deepseek-v4-pro openapi-spec/deepseek-v4-pro.json POST /v1/chat/completions # DeepSeek V4.1 Flash 1017 Source: https://docs.siray.ai/api-reference/model-api/deepseek-v4.1-flash openapi-spec/deepseek-v4.1-flash.json POST /v1/chat/completions # Embedding Model Example Source: https://docs.siray.ai/api-reference/model-api/example-usage-genai-embedding Examples for python ```python python theme={null} from google import genai from google.genai import types client = genai.Client( api_key='sk-xxxx', http_options=types.HttpOptions( base_url='https://api.siray.ai', ), ) result = client.models.embed_content( model="google/gemini-embedding-001", contents=[ "How do I get a driver's license/learner's permit?", "How long is my driver's license valid for?", "Driver's knowledge test study guide", ], config=types.EmbedContentConfig(task_type="SEMANTIC_SIMILARITY") ) print(result) ``` # Image Generation Example Source: https://docs.siray.ai/api-reference/model-api/example-usage-image Examples for python, nodejs and http. ```python python theme={null} # install using pip # pip install siray from siray import Siray client = Siray() # load a local file and get a ready-to-use data URI local_image = client.load_from_local("path/to/image.jpg") status = client.image.run( model="black-forest-labs/flux-1.1-pro-ultra-i2i", prompt="A futuristic city skyline at dusk", image=local_image, poll_interval=2.0, # optional, defaults to 2 seconds ) print(f"Final status: {status.status}") if status.is_completed(): print(status.outputs) ``` ```javascript nodejs theme={null} // install using npm // npm install siray import { Siray } from 'siray'; const client = new Siray({ apiKey: 'your-api-key-here', }); // turn a local file into a base64 data URL you can pass as the `image` field const initImage = await client.loadFromLocal('path/to/image.jpg'); const status = await client.image.run( { model: 'black-forest-labs/flux-kontext-i2i-pro', prompt: 'A cinematic portrait photo of a cyberpunk samurai', image: initImage, }, { pollIntervalMs: 3000, timeoutMs: 3 * 60 * 1000, } ); if (status.isCompleted()) { console.log('Generated image:', status.result); } else if (status.isFailed()) { console.log('Error:', status.fail_reason); } else { console.log('Final status:', status.status); } ``` ```bash http theme={null} # Submit Task BASE64_DATA=$(base64 image.jpg | tr -d '\n') DATA_URL="data:image/jpeg;base64,$BASE64_DATA" curl -X POST https://api.siray.ai/v1/images/generations/async \ -H "Content-Type: application/json" \ -H "Authorization: Bearer ${SIRAY_API_TOKEN}" \ -d "{\"prompt\": \"\", \"image\": \"$DATA_URL\", \"model\": \"black-forest-labs/flux-kontext-i2i-pro\"}" # Query Result curl -X GET "https://api.siray.ai/v1/images/generations/async/${task_id}" \ -H "Authorization: Bearer ${SIRAY_API_TOKEN}" ``` # Flux 1.1 Pro i2i Source: https://docs.siray.ai/api-reference/model-api/flux-1.1-pro-i2i openapi-spec/flux-1.1-pro-i2i.json POST /v1/images/generations/async # Flux 1.1 Pro t2i Source: https://docs.siray.ai/api-reference/model-api/flux-1.1-pro-t2i openapi-spec/flux-1.1-pro-t2i.json POST /v1/images/generations/async # Flux 1.1 Pro Ultra i2i Source: https://docs.siray.ai/api-reference/model-api/flux-1.1-pro-ultra-i2i openapi-spec/flux-1.1-pro-ultra-i2i.json POST /v1/images/generations/async # Flux 1.1 Pro Ultra t2i Source: https://docs.siray.ai/api-reference/model-api/flux-1.1-pro-ultra-t2i openapi-spec/flux-1.1-pro-ultra-t2i.json POST /v1/images/generations/async # Flux 3 i2v Source: https://docs.siray.ai/api-reference/model-api/flux-3-i2v openapi-spec/flux-3-i2v.json POST /v1/video/generations # Flux 3 t2v Source: https://docs.siray.ai/api-reference/model-api/flux-3-t2v openapi-spec/flux-3-t2v.json POST /v1/video/generations # Flux 3 v2v Source: https://docs.siray.ai/api-reference/model-api/flux-3-v2v openapi-spec/flux-3-v2v.json POST /v1/video/generations # Flux Kontext i2i Max Source: https://docs.siray.ai/api-reference/model-api/flux-kontext-i2i-max openapi-spec/flux-kontext-i2i-max.json POST /v1/images/generations/async # Flux Kontext i2i Pro Source: https://docs.siray.ai/api-reference/model-api/flux-kontext-i2i-pro openapi-spec/flux-kontext-i2i-pro.json POST /v1/images/generations/async # Flux Kontext t2i Max Source: https://docs.siray.ai/api-reference/model-api/flux-kontext-t2i-max openapi-spec/flux-kontext-t2i-max.json POST /v1/images/generations/async # Flux Kontext t2i Pro Source: https://docs.siray.ai/api-reference/model-api/flux-kontext-t2i-pro openapi-spec/flux-kontext-t2i-pro.json POST /v1/images/generations/async # Gemini 2.5 Flash Source: https://docs.siray.ai/api-reference/model-api/gemini-2.5-flash openapi-spec/gemini-2.5-flash.json POST /v1/chat/completions # Gemini 2.5 Pro Source: https://docs.siray.ai/api-reference/model-api/gemini-2.5-pro openapi-spec/gemini-2.5-pro.json POST /v1/chat/completions # Gemini 3 Flash Preview Source: https://docs.siray.ai/api-reference/model-api/gemini-3-flash-preview openapi-spec/gemini-3-flash-preview.json POST /v1/chat/completions # Gemini 3.1 Pro Preview Source: https://docs.siray.ai/api-reference/model-api/gemini-3.1-pro-preview openapi-spec/gemini-3.1-pro-preview.json POST /v1/chat/completions # GLM 4.6V Flash Source: https://docs.siray.ai/api-reference/model-api/glm-4.6v-flash openapi-spec/glm-4.6v-flash.json POST /v1/chat/completions # GLM 4.7 Source: https://docs.siray.ai/api-reference/model-api/glm-4.7 openapi-spec/glm-4.7.json POST /v1/chat/completions # GLM 5 Source: https://docs.siray.ai/api-reference/model-api/glm-5 openapi-spec/glm-5.json POST /v1/chat/completions # GLM 5.2 Source: https://docs.siray.ai/api-reference/model-api/glm-5.2 openapi-spec/glm-5.2.json POST /v1/chat/completions # Google Omni 1.1 Flash i2v Source: https://docs.siray.ai/api-reference/model-api/google-omni-1.1-flash-i2v openapi-spec/google-omni-1.1-flash-i2v.json POST /v1/video/generations # Google Omni 1.1 Flash ref2v Source: https://docs.siray.ai/api-reference/model-api/google-omni-1.1-flash-ref2v openapi-spec/google-omni-1.1-flash-ref2v.json POST /v1/video/generations # Google Omni 1.1 Flash t2v Source: https://docs.siray.ai/api-reference/model-api/google-omni-1.1-flash-t2v openapi-spec/google-omni-1.1-flash-t2v.json POST /v1/video/generations # GPT 4.1 Source: https://docs.siray.ai/api-reference/model-api/gpt-4.1 openapi-spec/gpt-4.1.json POST /v1/chat/completions # GPT 4.1 Mini Source: https://docs.siray.ai/api-reference/model-api/gpt-4.1-mini openapi-spec/gpt-4.1-mini.json POST /v1/chat/completions # GPT 4o Source: https://docs.siray.ai/api-reference/model-api/gpt-4o openapi-spec/gpt-4o.json POST /v1/chat/completions # GPT 4o mini Source: https://docs.siray.ai/api-reference/model-api/gpt-4o-mini openapi-spec/gpt-4o-mini.json POST /v1/chat/completions # GPT 5 Nano Source: https://docs.siray.ai/api-reference/model-api/gpt-5-nano openapi-spec/gpt-5-nano.json POST /v1/chat/completions # GPT 5.2 Source: https://docs.siray.ai/api-reference/model-api/gpt-5.2 openapi-spec/gpt-5.2.json POST /v1/chat/completions # GPT 5.4 Source: https://docs.siray.ai/api-reference/model-api/gpt-5.4 openapi-spec/gpt-5.4.json POST /v1/chat/completions # GPT 5.4 Mini Source: https://docs.siray.ai/api-reference/model-api/gpt-5.4-mini openapi-spec/gpt-5.4-mini.json POST /v1/chat/completions # GPT 5.5 Source: https://docs.siray.ai/api-reference/model-api/gpt-5.5 openapi-spec/gpt-5.5.json POST /v1/chat/completions # GPT 6 Astra Source: https://docs.siray.ai/api-reference/model-api/gpt-6-astra openapi-spec/gpt-6-astra.json POST /v1/chat/completions # GPT 6 Luna Source: https://docs.siray.ai/api-reference/model-api/gpt-6-luna openapi-spec/gpt-6-luna.json POST /v1/chat/completions # GPT 6.1 Sol Source: https://docs.siray.ai/api-reference/model-api/gpt-6.1-sol openapi-spec/gpt-6.1-sol.json POST /v1/chat/completions # GPT Image 2 Edit Source: https://docs.siray.ai/api-reference/model-api/gpt-image-2-edit openapi-spec/gpt-image-2-edit.json POST /v1/images/generations/async # GPT Image 2 t2i Source: https://docs.siray.ai/api-reference/model-api/gpt-image-2-t2i openapi-spec/gpt-image-2-t2i.json POST /v1/images/generations/async # GPT Image 2.5 Flare Edit Source: https://docs.siray.ai/api-reference/model-api/gpt-image-2.5-flare-edit openapi-spec/gpt-image-2.5-flare-edit.json POST /v1/images/generations/async # GPT Image 2.5 Flare t2i Source: https://docs.siray.ai/api-reference/model-api/gpt-image-2.5-flare-t2i openapi-spec/gpt-image-2.5-flare-t2i.json POST /v1/images/generations/async # GPT Image 2.5 Sunburst Edit Source: https://docs.siray.ai/api-reference/model-api/gpt-image-2.5-sunburst-edit openapi-spec/gpt-image-2.5-sunburst-edit.json POST /v1/images/generations/async # GPT Image 2.5 Sunburst t2i Source: https://docs.siray.ai/api-reference/model-api/gpt-image-2.5-sunburst-t2i openapi-spec/gpt-image-2.5-sunburst-t2i.json POST /v1/images/generations/async # GPT oss 20b Source: https://docs.siray.ai/api-reference/model-api/gpt-oss-20b openapi-spec/gpt-oss-20b.json POST /v1/chat/completions # Grok 4.1 Fast Non Reasoning Source: https://docs.siray.ai/api-reference/model-api/grok-4.1-fast-non-reasoning openapi-spec/grok-4.1-fast-non-reasoning.json POST /v1/chat/completions # Grok 4.1 Fast Reasoning Source: https://docs.siray.ai/api-reference/model-api/grok-4.1-fast-reasoning openapi-spec/grok-4.1-fast-reasoning.json POST /v1/chat/completions # Grok Imagine Image i2i Source: https://docs.siray.ai/api-reference/model-api/grok-imagine-image-i2i openapi-spec/grok-imagine-image-i2i.json POST /v1/images/generations/async # Grok Imagine Image t2i Source: https://docs.siray.ai/api-reference/model-api/grok-imagine-image-t2i openapi-spec/grok-imagine-image-t2i.json POST /v1/images/generations/async # Grok Imagine Video Extension Source: https://docs.siray.ai/api-reference/model-api/grok-imagine-video-extension openapi-spec/grok-imagine-video-extension.json POST /v1/video/generations # Grok Imagine Video i2v Source: https://docs.siray.ai/api-reference/model-api/grok-imagine-video-i2v openapi-spec/grok-imagine-video-i2v.json POST /v1/video/generations # Grok Imagine Video t2v Source: https://docs.siray.ai/api-reference/model-api/grok-imagine-video-t2v openapi-spec/grok-imagine-video-t2v.json POST /v1/video/generations # Hunyuan Image 3 Instruct i2i Source: https://docs.siray.ai/api-reference/model-api/hunyuan-image-3-instruct-i2i openapi-spec/hunyuan-image-3-instruct-i2i.json POST /v1/images/generations/async # Hunyuan Image 3 Instruct t2i Source: https://docs.siray.ai/api-reference/model-api/hunyuan-image-3-instruct-t2i openapi-spec/hunyuan-image-3-instruct-t2i.json POST /v1/images/generations/async # Hunyuan3d V2.5 Rapid image-to-3d Source: https://docs.siray.ai/api-reference/model-api/hunyuan3d-v2.5-rapid-image-to-3d openapi-spec/hunyuan3d-v2.5-rapid-image-to-3d.json POST /v1/3d/generations # Hunyuan3d V2.5 Rapid text-to-3d Source: https://docs.siray.ai/api-reference/model-api/hunyuan3d-v2.5-rapid-text-to-3d openapi-spec/hunyuan3d-v2.5-rapid-text-to-3d.json POST /v1/3d/generations # Kimi K3 Source: https://docs.siray.ai/api-reference/model-api/kimi-k3 openapi-spec/kimi-k3.json POST /v1/chat/completions # Kling 2.6 Motion Control Source: https://docs.siray.ai/api-reference/model-api/kling-2.6-motion-control openapi-spec/kling-2.6-motion-control.json POST /v1/video/generations # Kling 2.6 Pro i2v Source: https://docs.siray.ai/api-reference/model-api/kling-2.6-pro-i2v openapi-spec/kling-2.6-pro-i2v.json POST /v1/video/generations # Kling 2.6 Pro Motion Control Source: https://docs.siray.ai/api-reference/model-api/kling-2.6-pro-motion-control openapi-spec/kling-2.6-pro-motion-control.json POST /v1/video/generations # Kling 2.6 Pro t2v Source: https://docs.siray.ai/api-reference/model-api/kling-2.6-pro-t2v openapi-spec/kling-2.6-pro-t2v.json POST /v1/video/generations # Kling 3 Motion Control Source: https://docs.siray.ai/api-reference/model-api/kling-3-motion-control openapi-spec/kling-3-motion-control.json POST /v1/video/generations # Kling 3.0 i2v Source: https://docs.siray.ai/api-reference/model-api/kling-3.0-i2v openapi-spec/kling-3.0-i2v.json POST /v1/video/generations # Kling 3.0 t2v Source: https://docs.siray.ai/api-reference/model-api/kling-3.0-t2v openapi-spec/kling-3.0-t2v.json POST /v1/video/generations # LTX 2.3 22B i2v Source: https://docs.siray.ai/api-reference/model-api/ltx-2.3-22b-i2v openapi-spec/ltx-2.3-22b-i2v.json POST /v1/video/generations # LTX 2.3 22B t2v Source: https://docs.siray.ai/api-reference/model-api/ltx-2.3-22b-t2v openapi-spec/ltx-2.3-22b-t2v.json POST /v1/video/generations # Midjourney Niji 6 t2i Source: https://docs.siray.ai/api-reference/model-api/midjourney-niji-6-t2i openapi-spec/midjourney-niji-6-t2i.json POST /v1/images/generations/async # Midjourney Niji 7 t2i Source: https://docs.siray.ai/api-reference/model-api/midjourney-niji-7-t2i openapi-spec/midjourney-niji-7-t2i.json POST /v1/images/generations/async # Midjourney V6 t2i Source: https://docs.siray.ai/api-reference/model-api/midjourney-v6-t2i openapi-spec/midjourney-v6-t2i.json POST /v1/images/generations/async # Midjourney V6.1 t2i Source: https://docs.siray.ai/api-reference/model-api/midjourney-v6.1-t2i openapi-spec/midjourney-v6.1-t2i.json POST /v1/images/generations/async # Midjourney V7 t2i Source: https://docs.siray.ai/api-reference/model-api/midjourney-v7-t2i openapi-spec/midjourney-v7-t2i.json POST /v1/images/generations/async # Midjourney V8.2 t2i Source: https://docs.siray.ai/api-reference/model-api/midjourney-v8.2-t2i openapi-spec/midjourney-v8.2-t2i.json POST /v1/images/generations/async # MiMo V2 Flash Source: https://docs.siray.ai/api-reference/model-api/mimo-v2-flash openapi-spec/mimo-v2-flash.json POST /v1/chat/completions # MiniMax H3 i2v Source: https://docs.siray.ai/api-reference/model-api/minimax-h3-i2v openapi-spec/minimax-h3-i2v.json POST /v1/video/generations # MiniMax H3 i2v Spicy Source: https://docs.siray.ai/api-reference/model-api/minimax-h3-i2v-spicy openapi-spec/minimax-h3-i2v-spicy.json POST /v1/video/generations # MiniMax H3 ref2v Source: https://docs.siray.ai/api-reference/model-api/minimax-h3-ref2v openapi-spec/minimax-h3-ref2v.json POST /v1/video/generations # MiniMax H3 ref2v Spicy Source: https://docs.siray.ai/api-reference/model-api/minimax-h3-ref2v-spicy openapi-spec/minimax-h3-ref2v-spicy.json POST /v1/video/generations # MiniMax H3 t2v Source: https://docs.siray.ai/api-reference/model-api/minimax-h3-t2v openapi-spec/minimax-h3-t2v.json POST /v1/video/generations # MiniMax H3 t2v Spicy Source: https://docs.siray.ai/api-reference/model-api/minimax-h3-t2v-spicy openapi-spec/minimax-h3-t2v-spicy.json POST /v1/video/generations # Nano Banana 2 i2i Source: https://docs.siray.ai/api-reference/model-api/nano-banana-2-i2i openapi-spec/nano-banana-2-i2i.json POST /v1/images/generations/async # Nano Banana 2 Lite Edit Source: https://docs.siray.ai/api-reference/model-api/nano-banana-2-lite-edit openapi-spec/nano-banana-2-lite-edit.json POST /v1/images/generations/async # Nano Banana 2 Lite t2i Source: https://docs.siray.ai/api-reference/model-api/nano-banana-2-lite-t2i openapi-spec/nano-banana-2-lite-t2i.json POST /v1/images/generations/async # Nano Banana 2 t2i Source: https://docs.siray.ai/api-reference/model-api/nano-banana-2-t2i openapi-spec/nano-banana-2-t2i.json POST /v1/images/generations/async # Nano Banana 2.1 i2i Source: https://docs.siray.ai/api-reference/model-api/nano-banana-2.1-i2i openapi-spec/nano-banana-2.1-i2i.json POST /v1/images/generations/async # Nano Banana 2.1 t2i Source: https://docs.siray.ai/api-reference/model-api/nano-banana-2.1-t2i openapi-spec/nano-banana-2.1-t2i.json POST /v1/images/generations/async # Nano Banana i2i Source: https://docs.siray.ai/api-reference/model-api/nano-banana-i2i openapi-spec/nano-banana-i2i.json POST /v1/images/generations/async # Nano Banana Pro i2i Source: https://docs.siray.ai/api-reference/model-api/nano-banana-pro-i2i openapi-spec/nano-banana-pro-i2i.json POST /v1/images/generations/async # Nano Banana Pro t2i Source: https://docs.siray.ai/api-reference/model-api/nano-banana-pro-t2i openapi-spec/nano-banana-pro-t2i.json POST /v1/images/generations/async # Nano Banana t2i Source: https://docs.siray.ai/api-reference/model-api/nano-banana-t2i openapi-spec/nano-banana-t2i.json POST /v1/images/generations/async # PixVerse C1 i2v Source: https://docs.siray.ai/api-reference/model-api/pixverse-c1-i2v openapi-spec/pixverse-c1-i2v.json POST /v1/video/generations # PixVerse C1 t2v Source: https://docs.siray.ai/api-reference/model-api/pixverse-c1-t2v openapi-spec/pixverse-c1-t2v.json POST /v1/video/generations # PixVerse V5.6 i2v Source: https://docs.siray.ai/api-reference/model-api/pixverse-v5.6-i2v openapi-spec/pixverse-v5.6-i2v.json POST /v1/video/generations # PixVerse V5.6 t2v Source: https://docs.siray.ai/api-reference/model-api/pixverse-v5.6-t2v openapi-spec/pixverse-v5.6-t2v.json POST /v1/video/generations # PixVerse V6 i2v Source: https://docs.siray.ai/api-reference/model-api/pixverse-v6-i2v openapi-spec/pixverse-v6-i2v.json POST /v1/video/generations # PixVerse V6 t2v Source: https://docs.siray.ai/api-reference/model-api/pixverse-v6-t2v openapi-spec/pixverse-v6-t2v.json POST /v1/video/generations # Qwen Image 3 Edit Source: https://docs.siray.ai/api-reference/model-api/qwen-image-3-edit openapi-spec/qwen-image-3-edit.json POST /v1/images/generations/async # Qwen Image 3 Edit Spicy Source: https://docs.siray.ai/api-reference/model-api/qwen-image-3-edit-spicy openapi-spec/qwen-image-3-edit-spicy.json POST /v1/images/generations/async # Qwen Image 3 Pro Edit Spicy Source: https://docs.siray.ai/api-reference/model-api/qwen-image-3-pro-edit-spicy openapi-spec/qwen-image-3-pro-edit-spicy.json POST /v1/images/generations/async # Qwen Image 3 Pro t2i Spicy Source: https://docs.siray.ai/api-reference/model-api/qwen-image-3-pro-t2i-spicy openapi-spec/qwen-image-3-pro-t2i-spicy.json POST /v1/images/generations/async # Qwen Image 3 t2i Source: https://docs.siray.ai/api-reference/model-api/qwen-image-3-t2i openapi-spec/qwen-image-3-t2i.json POST /v1/images/generations/async # Qwen Image 3 t2i Spicy Source: https://docs.siray.ai/api-reference/model-api/qwen-image-3-t2i-spicy openapi-spec/qwen-image-3-t2i-spicy.json POST /v1/images/generations/async # Qwen3 Coder 480B A35B Instruct Source: https://docs.siray.ai/api-reference/model-api/qwen3-coder-480b-a35b-instruct openapi-spec/qwen3-coder-480b-a35b-instruct.json POST /v1/chat/completions # Seed 1.6 Source: https://docs.siray.ai/api-reference/model-api/seed-1.6 openapi-spec/seed-1.6.json POST /v1/chat/completions # Seedance 1.0 Lite i2v Source: https://docs.siray.ai/api-reference/model-api/seedance-1.0-lite-i2v openapi-spec/seedance-1.0-lite-i2v.json POST /v1/video/generations # Seedance 1.0 Lite t2v Source: https://docs.siray.ai/api-reference/model-api/seedance-1.0-lite-t2v openapi-spec/seedance-1.0-lite-t2v.json POST /v1/video/generations # Seedance 1.0 Pro Fast t2v Source: https://docs.siray.ai/api-reference/model-api/seedance-1.0-pro-fast-t2v openapi-spec/seedance-1.0-pro-fast-t2v.json POST /v1/video/generations # Seedance 1.0 Pro i2v Source: https://docs.siray.ai/api-reference/model-api/seedance-1.0-pro-i2v openapi-spec/seedance-1.0-pro-i2v.json POST /v1/video/generations # Seedance 1.0 Pro t2v Source: https://docs.siray.ai/api-reference/model-api/seedance-1.0-pro-t2v openapi-spec/seedance-1.0-pro-t2v.json POST /v1/video/generations # Seedance 1.5 Pro i2v Source: https://docs.siray.ai/api-reference/model-api/seedance-1.5-pro-i2v openapi-spec/seedance-1.5-pro-i2v.json POST /v1/video/generations # Seedance 1.5 Pro se2v Source: https://docs.siray.ai/api-reference/model-api/seedance-1.5-pro-se2v openapi-spec/seedance-1.5-pro-se2v.json POST /v1/video/generations # Seedance 1.5 Pro t2v Source: https://docs.siray.ai/api-reference/model-api/seedance-1.5-pro-t2v openapi-spec/seedance-1.5-pro-t2v.json POST /v1/video/generations # Seedance 2.0 Fast i2v Source: https://docs.siray.ai/api-reference/model-api/seedance-2.0-fast-i2v openapi-spec/seedance-2.0-fast-i2v.json POST /v1/video/generations # Seedance 2.0 Fast t2v Source: https://docs.siray.ai/api-reference/model-api/seedance-2.0-fast-t2v openapi-spec/seedance-2.0-fast-t2v.json POST /v1/video/generations # Seedance 2.0 i2v Source: https://docs.siray.ai/api-reference/model-api/seedance-2.0-i2v openapi-spec/seedance-2.0-i2v.json POST /v1/video/generations # Seedance 2.0 i2v Spicy Source: https://docs.siray.ai/api-reference/model-api/seedance-2.0-i2v-spicy openapi-spec/seedance-2.0-i2v-spicy.json POST /v1/video/generations # Seedance 2.0 ref2v Spicy Source: https://docs.siray.ai/api-reference/model-api/seedance-2.0-ref2v-spicy openapi-spec/seedance-2.0-ref2v-spicy.json POST /v1/video/generations # Seedance 2.0 t2v Source: https://docs.siray.ai/api-reference/model-api/seedance-2.0-t2v openapi-spec/seedance-2.0-t2v.json POST /v1/video/generations # Seedance 2.0 t2v Spicy Source: https://docs.siray.ai/api-reference/model-api/seedance-2.0-t2v-spicy openapi-spec/seedance-2.0-t2v-spicy.json POST /v1/video/generations # Seedance 2.5 i2v Source: https://docs.siray.ai/api-reference/model-api/seedance-2.5-i2v openapi-spec/seedance-2.5-i2v.json POST /v1/video/generations # Seedance 2.5 i2v Spicy Source: https://docs.siray.ai/api-reference/model-api/seedance-2.5-i2v-spicy openapi-spec/seedance-2.5-i2v-spicy.json POST /v1/video/generations # Seedance 2.5 ref2v Source: https://docs.siray.ai/api-reference/model-api/seedance-2.5-ref2v openapi-spec/seedance-2.5-ref2v.json POST /v1/video/generations # Seedance 2.5 ref2v Spicy Source: https://docs.siray.ai/api-reference/model-api/seedance-2.5-ref2v-spicy openapi-spec/seedance-2.5-ref2v-spicy.json POST /v1/video/generations # Seedance 2.5 t2v Source: https://docs.siray.ai/api-reference/model-api/seedance-2.5-t2v openapi-spec/seedance-2.5-t2v.json POST /v1/video/generations # Seedance 2.5 t2v Spicy Source: https://docs.siray.ai/api-reference/model-api/seedance-2.5-t2v-spicy openapi-spec/seedance-2.5-t2v-spicy.json POST /v1/video/generations # Seedream 4.0 i2i Source: https://docs.siray.ai/api-reference/model-api/seedream-4.0-i2i openapi-spec/seedream-4.0-i2i.json POST /v1/images/generations/async # Seedream 4.0 ref2i Source: https://docs.siray.ai/api-reference/model-api/seedream-4.0-ref2i openapi-spec/seedream-4.0-ref2i.json POST /v1/images/generations/async # Seedream 4.0 t2i Source: https://docs.siray.ai/api-reference/model-api/seedream-4.0-t2i openapi-spec/seedream-4.0-t2i.json POST /v1/images/generations/async # Seedream 4.5 i2i Source: https://docs.siray.ai/api-reference/model-api/seedream-4.5-i2i openapi-spec/seedream-4.5-i2i.json POST /v1/images/generations/async # Seedream 4.5 i2i Spicy Source: https://docs.siray.ai/api-reference/model-api/seedream-4.5-i2i-spicy openapi-spec/seedream-4.5-i2i-spicy.json POST /v1/images/generations/async # Seedream 4.5 ref2i Source: https://docs.siray.ai/api-reference/model-api/seedream-4.5-ref2i openapi-spec/seedream-4.5-ref2i.json POST /v1/images/generations/async # Seedream 4.5 ref2i Spicy Source: https://docs.siray.ai/api-reference/model-api/seedream-4.5-ref2i-spicy openapi-spec/seedream-4.5-ref2i-spicy.json POST /v1/images/generations/async # Seedream 4.5 t2i Source: https://docs.siray.ai/api-reference/model-api/seedream-4.5-t2i openapi-spec/seedream-4.5-t2i.json POST /v1/images/generations/async # Seedream 4.5 t2i Spicy Source: https://docs.siray.ai/api-reference/model-api/seedream-4.5-t2i-spicy openapi-spec/seedream-4.5-t2i-spicy.json POST /v1/images/generations/async # Seedream 5.0 Pro i2i Spicy Source: https://docs.siray.ai/api-reference/model-api/seedream-5.0-pro-i2i-spicy openapi-spec/seedream-5.0-pro-i2i-spicy.json POST /v1/images/generations/async # Seedream 5.0 Pro t2i Spicy Source: https://docs.siray.ai/api-reference/model-api/seedream-5.0-pro-t2i-spicy openapi-spec/seedream-5.0-pro-t2i-spicy.json POST /v1/images/generations/async # Tripo3D V2.5 image-to-3d Source: https://docs.siray.ai/api-reference/model-api/tripo3d-v2.5-image-to-3d openapi-spec/tripo3d-v2.5-image-to-3d.json POST /v1/3d/generations # Veo 3.1 i2v Source: https://docs.siray.ai/api-reference/model-api/veo-3.1-i2v openapi-spec/veo-3.1-i2v.json POST /v1/video/generations # Veo 3.1 t2v Source: https://docs.siray.ai/api-reference/model-api/veo-3.1-t2v openapi-spec/veo-3.1-t2v.json POST /v1/video/generations # Vidu Q2-pro-fast i2v Source: https://docs.siray.ai/api-reference/model-api/vidu-q2-pro-fast-i2v openapi-spec/vidu-q2-pro-fast-i2v.json POST /v1/video/generations # Vidu Q2-pro i2v Source: https://docs.siray.ai/api-reference/model-api/vidu-q2-pro-i2v openapi-spec/vidu-q2-pro-i2v.json POST /v1/video/generations # Vidu Q2-pro se2v Source: https://docs.siray.ai/api-reference/model-api/vidu-q2-pro-se2v openapi-spec/vidu-q2-pro-se2v.json POST /v1/video/generations # Vidu Q2 t2v Source: https://docs.siray.ai/api-reference/model-api/vidu-q2-t2v openapi-spec/vidu-q2-t2v.json POST /v1/video/generations # Vidu Q3-pro i2v Source: https://docs.siray.ai/api-reference/model-api/vidu-q3-pro-i2v openapi-spec/vidu-q3-pro-i2v.json POST /v1/video/generations # Vidu Q3-pro t2v Source: https://docs.siray.ai/api-reference/model-api/vidu-q3-pro-t2v openapi-spec/vidu-q3-pro-t2v.json POST /v1/video/generations # Vidu Q4 i2v Source: https://docs.siray.ai/api-reference/model-api/vidu-q4-i2v openapi-spec/vidu-q4-i2v.json POST /v1/video/generations # Vidu Q4 ref2v Source: https://docs.siray.ai/api-reference/model-api/vidu-q4-ref2v openapi-spec/vidu-q4-ref2v.json POST /v1/video/generations # Wan 2.6 i2v Source: https://docs.siray.ai/api-reference/model-api/wan-2.6-i2v openapi-spec/wan-2.6-i2v.json POST /v1/video/generations # Wan 2.6 t2v Source: https://docs.siray.ai/api-reference/model-api/wan-2.6-t2v openapi-spec/wan-2.6-t2v.json POST /v1/video/generations # Wan 2.7 i2v Spicy Source: https://docs.siray.ai/api-reference/model-api/wan-2.7-i2v-spicy openapi-spec/wan-2.7-i2v-spicy.json POST /v1/video/generations # Wan 2.7 i2v Uncensored Source: https://docs.siray.ai/api-reference/model-api/wan-2.7-i2v-uncensored openapi-spec/wan-2.7-i2v-uncensored.json POST /v1/video/generations # Wan 2.7 Image i2i Spicy Source: https://docs.siray.ai/api-reference/model-api/wan-2.7-image-i2i-spicy openapi-spec/wan-2.7-image-i2i-spicy.json POST /v1/images/generations/async # Wan 2.7 Image Pro i2i Spicy Source: https://docs.siray.ai/api-reference/model-api/wan-2.7-image-pro-i2i-spicy openapi-spec/wan-2.7-image-pro-i2i-spicy.json POST /v1/images/generations/async # Wan 2.7 Image Pro t2i Spicy Source: https://docs.siray.ai/api-reference/model-api/wan-2.7-image-pro-t2i-spicy openapi-spec/wan-2.7-image-pro-t2i-spicy.json POST /v1/images/generations/async # Wan 2.7 Image t2i Spicy Source: https://docs.siray.ai/api-reference/model-api/wan-2.7-image-t2i-spicy openapi-spec/wan-2.7-image-t2i-spicy.json POST /v1/images/generations/async # Wan 2.7 ref2v Uncensored Source: https://docs.siray.ai/api-reference/model-api/wan-2.7-ref2v-uncensored openapi-spec/wan-2.7-ref2v-uncensored.json POST /v1/video/generations # Wan 2.7 t2v Uncensored Source: https://docs.siray.ai/api-reference/model-api/wan-2.7-t2v-uncensored openapi-spec/wan-2.7-t2v-uncensored.json POST /v1/video/generations # Wan 3.0 i2v Source: https://docs.siray.ai/api-reference/model-api/wan-3.0-i2v openapi-spec/wan-3.0-i2v.json POST /v1/video/generations # Wan 3.0 i2v Prime Spicy Source: https://docs.siray.ai/api-reference/model-api/wan-3.0-i2v-prime-spicy openapi-spec/wan-3.0-i2v-prime-spicy.json POST /v1/video/generations # Wan 3.0 i2v Spicy Source: https://docs.siray.ai/api-reference/model-api/wan-3.0-i2v-spicy openapi-spec/wan-3.0-i2v-spicy.json POST /v1/video/generations # Wan 3.0 ref2v Source: https://docs.siray.ai/api-reference/model-api/wan-3.0-ref2v openapi-spec/wan-3.0-ref2v.json POST /v1/video/generations # Wan 3.0 ref2v Prime Spicy Source: https://docs.siray.ai/api-reference/model-api/wan-3.0-ref2v-prime-spicy openapi-spec/wan-3.0-ref2v-prime-spicy.json POST /v1/video/generations # Wan 3.0 ref2v Spicy Source: https://docs.siray.ai/api-reference/model-api/wan-3.0-ref2v-spicy openapi-spec/wan-3.0-ref2v-spicy.json POST /v1/video/generations # Wan 3.0 t2v Source: https://docs.siray.ai/api-reference/model-api/wan-3.0-t2v openapi-spec/wan-3.0-t2v.json POST /v1/video/generations # Wan 3.0 t2v Prime Spicy Source: https://docs.siray.ai/api-reference/model-api/wan-3.0-t2v-prime-spicy openapi-spec/wan-3.0-t2v-prime-spicy.json POST /v1/video/generations # Wan 3.0 t2v Spicy Source: https://docs.siray.ai/api-reference/model-api/wan-3.0-t2v-spicy openapi-spec/wan-3.0-t2v-spicy.json POST /v1/video/generations # Z-Image Spicy Pro t2i Source: https://docs.siray.ai/api-reference/model-api/z-image-spicy-pro-t2i openapi-spec/z-image-spicy-pro-t2i.json POST /v1/images/generations/async # Z-Image Turbo t2i Source: https://docs.siray.ai/api-reference/model-api/z-image-turbo-t2i openapi-spec/z-image-turbo-t2i.json POST /v1/images/generations/async # Models API Source: https://docs.siray.ai/api-reference/models openapi-spec/models.json GET /v1/models List available models, inspect supported endpoint types, and track model lifecycle metadata. ## Overview Use the Models API to discover which models are available to you. Each model includes the endpoint families it supports and lifecycle metadata you can use to migrate away from deprecated or retired models. > [!TIP] > > Use `supported_endpoint_types` to choose the correct generation endpoint instead of relying only on model naming conventions. ## Endpoints * `GET https://api.siray.ai/v1/models` * `GET https://api.siray.ai/v1/models/{model}` **Headers** * `Authorization: Bearer ` **Path parameters** | Name | Description | | - | - | | `model` | Model ID to retrieve, such as `openai/gpt-4o` or `gpt-4o`. | ## List response structure ```json theme={null} { "success": true, "object": "list", "data": [ { "id": "openai/gpt-4o", "object": "model", "created": 1626777600, "owned_by": "openai", "supported_endpoint_types": [ "openai" ], "status": "active" }, { "id": "openai/gpt-4", "object": "model", "created": 1626777600, "owned_by": "openai", "supported_endpoint_types": [ "openai" ], "status": "deprecated", "deprecated_at": 1710000000, "replaced_by": "openai/gpt-4.1" } ] } ``` ## Retrieve response structure ```json theme={null} { "id": "openai/gpt-4o", "object": "model", "created": 1626777600, "owned_by": "openai", "supported_endpoint_types": [ "openai" ], "status": "active" } ``` ### Fields * `id`: Model identifier used in request payloads. * `object`: Always `model` for each model item. * `created`: Unix timestamp attached to the model metadata. * `owned_by`: Owner derived from `id`. If the ID contains `/`, this is the part before the first `/`; otherwise it is the full model ID. * `supported_endpoint_types`: Endpoint families supported by the model. Empty array means the API could not determine a supported endpoint type. * `status`: Lifecycle state of the model. Values are listed below. * `deprecated_at`: Unix timestamp when the model was deprecated. Omitted when empty. * `retired_at`: Unix timestamp when the model was retired. Omitted when empty. * `replaced_by`: Replacement model ID. Omitted when empty. ### Supported endpoint types | Type | Use case | | - | - | | `openai` | OpenAI-compatible chat completions. | | `openai-response` | OpenAI-compatible Responses API. | | `anthropic` | Anthropic-compatible messages endpoint. | | `gemini` | Gemini-compatible content generation. | | `jina-rerank` | Rerank requests. | | `embeddings` | Embedding generation. | | `image-generation` | Text-to-image or image-to-image generation. | | `video-generation` | Video, text-to-video, image-to-video, or video-to-video generation. | | `3d-generation` | Text-to-3D or image-to-3D generation. | | `openai-video` | OpenAI-compatible video endpoint. | ### Lifecycle status values | Status | Meaning | | - | - | | `active` | Model is currently available for normal use. | | `deprecated` | Model still works, but you should migrate to `replaced_by` when provided. | | `retired` | Model is no longer intended for use. Migrate before sending production traffic. | ## Usage examples List all models available to the token: ```bash theme={null} curl -X GET "https://api.siray.ai/v1/models" \ -H "Authorization: Bearer ${SIRAY_API_TOKEN}" ``` Retrieve one model: ```bash theme={null} curl -X GET "https://api.siray.ai/v1/models/openai/gpt-4o" \ -H "Authorization: Bearer ${SIRAY_API_TOKEN}" ``` > For provider-qualified IDs that contain `/`, URL-encode the slash if your HTTP client does not preserve it in path parameters. # 3D Model Task Status API Source: https://docs.siray.ai/api-reference/task-status-3d openapi-spec/task-status.json GET /v1/3d/generations/{task_id} Monitor asynchronous 3D model generation tasks and download the produced 3D assets. ## Overview All image-to-3D or text-to-3D submissions return a `task_id`. Use the 3D task status endpoint to poll the job until it finishes. The payload mirrors the async submission response and includes downloadable asset URLs when the task succeeds. > [!TIP] > > Poll every 5–10 seconds to balance freshness with API usage efficiency. 3D model generation typically takes longer than image or video tasks. ## Endpoint * `GET https://api.siray.ai/v1/3d/generations/{task_id}` **Headers** * `Authorization: Bearer ` **Path parameters** | Name | Description | | - | - | | `task_id` | ID returned when the 3D generation task was created. | ## Response structure ```json theme={null} { "code": "success", "message": "", "data": { "task_id": "3d_69196fafcc9c8190acccf32e9b560c3f0da8a6d1948cfaa5", "status": "SUCCESS", "progress": "100%", "outputs": [ "https://api.siray.ai/redirect/example-output" ], "start_time": 1763274702, "finish_time": 1763274838, "submit_time": 1763274672, "fail_code": "", "fail_reason": "" } } ``` ### Fields * `code` / `message`: Service-level indicators for the polling request. * `data.task_id`: Echo of the 3D task identifier. * `data.status`: Lifecycle state — values listed below. * `data.progress`: Human-readable progress string. * `data.outputs`: URLs pointing to the generated 3D model assets (present when `status` is `SUCCESS`). * `data.fail_code`: Machine-readable failure code when `status` is `FAILURE`. See [fail\_code](/api-reference/fail-code). * `data.fail_reason`: Explains why processing stopped when `status` is `FAILURE`. * `data.submit_time`, `data.start_time`, `data.finish_time`: Unix timestamps that help track total latency. ### Status values | Status | Meaning | | - | - | | `NOT_START` | Task accepted but preprocessing has not started yet. | | `SUBMITTED` | Request stored and waiting to enter the queue. | | `QUEUED` | Task is scheduled and waiting for compute resources. | | `IN_PROGRESS` | Generation is currently running. | | `SUCCESS` | Outputs are ready; download the 3D model via the provided URLs. | | `FAILURE` | Irrecoverable error; inspect `fail_code` and `fail_reason` for remediation steps. | ## Usage example ```bash theme={null} curl -X GET "https://api.siray.ai/v1/3d/generations/${TASK_ID}" \ -H "Authorization: Bearer ${SIRAY_API_TOKEN}" ``` > When `status` reaches `SUCCESS`, download the 3D model from the URLs in `outputs`. If the task fails, retry after resolving the underlying issue noted in `fail_code` / `fail_reason`. # Image Task Status API Source: https://docs.siray.ai/api-reference/task-status-image openapi-spec/task-status.json GET /v1/images/generations/async/{task_id} Check asynchronous t2i/i2i generation tasks and retrieve the generated image URLs. ## Overview When you submit an image generation task (text-to-image or image-to-image) you receive a `task_id`. Use this endpoint to poll the execution lifecycle until the task either completes successfully or fails. > [!TIP] > > Query every 3–5 seconds to maintain responsiveness without exceeding rate limits. ## Endpoint * `GET https://api.siray.ai/v1/images/generations/async/{task_id}` **Headers** * `Authorization: Bearer ` **Path parameters** | Name | Description | | - | - | | `task_id` | ID returned in the async submission response. | ## Response structure ```json theme={null} { "code": "success", "message": "", "data": { "task_id": "image_a8813a4b4c9", "status": "SUCCESS", "progress": "100%", "outputs": [ "https://api.siray.ai/redirect/example-output" ], "start_time": 1763274702, "finish_time": 1763274838, "submit_time": 1763274672, "fail_code": "", "fail_reason": "" } } ``` ### Fields * `code` / `message`: Service-level indicators for the request outcome. * `data.task_id`: Echoes the submitted task identifier. * `data.status`: Current lifecycle state — see the table below. * `data.progress`: Human-readable percentage for UI display. * `data.outputs`: Array of public URLs that host the generated image assets (present when `status` is `SUCCESS`). * `data.fail_code`: Machine-readable failure code when `status` is `FAILURE`. See [fail\_code](/api-reference/fail-code). * `data.fail_reason`: Populated if generation fails. * `data.submit_time`, `data.start_time`, `data.finish_time`: Unix timestamps for auditing latency. ### Status values | Status | Meaning | | - | - | | `NOT_START` | Task accepted but preprocessing has not started yet. | | `SUBMITTED` | Request stored and waiting to enter the queue. | | `QUEUED` | Task is scheduled and waiting for compute resources. | | `IN_PROGRESS` | Generation is currently running. | | `SUCCESS` | Outputs are ready; download them via the URLs in `outputs`. | | `FAILURE` | Irrecoverable error; inspect `fail_code` and `fail_reason` for remediation steps. | ## Usage example ```bash theme={null} curl -X GET "https://api.siray.ai/v1/images/generations/async/${TASK_ID}" \ -H "Authorization: Bearer ${SIRAY_API_TOKEN}" ``` > Once `status` becomes `SUCCESS`, fetch the image(s) via the URLs in `outputs`. If the task fails, retry only after resolving the reported `fail_code` / `fail_reason`. # Video Task Status API Source: https://docs.siray.ai/api-reference/task-status-video openapi-spec/task-status.json GET /v1/video/generations/{task_id} Monitor asynchronous t2v/i2v generation tasks and download the produced video assets. ## Overview All text-to-video or image-to-video submissions return a `task_id`. Use the video task status endpoint to poll the job until it finishes. The payload mirrors the async submission response and includes downloadable asset URLs when the task succeeds. > [!TIP] > > Poll every 3–5 seconds to balance freshness with API usage efficiency. ## Endpoint * `GET https://api.siray.ai/v1/video/generations/{task_id}` **Headers** * `Authorization: Bearer ` **Path parameters** | Name | Description | | - | - | | `task_id` | ID returned when the video task was created. | ## Response structure ```json theme={null} { "code": "success", "message": "", "data": { "task_id": "video_69196fafcc9c8190acccf32e9b560c3f0da8a6d1948cfaa5", "status": "SUCCESS", "progress": "100%", "outputs": [ "https://api.siray.ai/redirect/example-output" ], "start_time": 1763274702, "finish_time": 1763274838, "submit_time": 1763274672, "fail_code": "", "fail_reason": "" } } ``` ### Fields * `code` / `message`: Service-level indicators for the polling request. * `data.task_id`: Echo of the video task identifier. * `data.status`: Lifecycle state — values listed below. * `data.progress`: Human-readable progress string. * `data.outputs`: URLs pointing to the generated video assets (present when `status` is `SUCCESS`). * `data.fail_code`: Machine-readable failure code when `status` is `FAILURE`. See [fail\_code](/api-reference/fail-code). * `data.fail_reason`: Explains why processing stopped when `status` is `FAILURE`. * `data.submit_time`, `data.start_time`, `data.finish_time`: Unix timestamps that help track total latency. ### Status values | Status | Meaning | | - | - | | `NOT_START` | Task accepted but preprocessing has not started yet. | | `SUBMITTED` | Request stored and waiting to enter the queue. | | `QUEUED` | Task is scheduled and waiting for compute resources. | | `IN_PROGRESS` | Generation is currently running. | | `SUCCESS` | Outputs are ready; download the video via the provided URLs. | | `FAILURE` | Irrecoverable error; inspect `fail_code` and `fail_reason` for remediation steps. | ## Usage example ```bash theme={null} curl -X GET "https://api.siray.ai/v1/video/generations/${TASK_ID}" \ -H "Authorization: Bearer ${SIRAY_API_TOKEN}" ``` > When `status` reaches `SUCCESS`, stream or download the video from the URLs in `outputs`. If the task fails, retry after resolving the underlying issue noted in `fail_code` / `fail_reason`. # September 5, 2025 Product Updates Source: https://docs.siray.ai/changelog/05-09-25 #### New Features ##### 🚀AI Model Endpoints * Added Model Endpoints module, providing a unified API access method. * Released 10 new models for text, image, and code generation tasks. * Each model supports flexible parameters, rate limits, and access control. * Developers can now call models with a single line of code, seamlessly integrated into their applications. * Always connected to the latest AI models, ensuring cutting-edge performance. # Introduction Source: https://docs.siray.ai/index Siray empower users to unleash stronger AI productivity at a significantly lower cost. ## Siray: The Unified AI Infrastructure for Enterprise Growth * **One-Click Access to the World's Most Comprehensive Model Library** * Integrates 300+ AI models covering the full spectrum of capabilities including language (LLMs), T2I, TTS, T2V and more. * A single API interface allows access to all models, completely eliminating the complexity and inefficiency of scattered, multi-source integration. * **Enterprise-Grade Smart Routing · 99.9% Availability** * Integrates 20+ model providers with 30+ global acceleration nodes. * The intelligent path optimization algorithm automatically matches the optimal route, ensuring every call is high-speed, stable, and delivers seamless, undetectable latency. * **Full-Chain Compliance · Trusted Security** * Fully compliant with strict security standards, rigorously vetting every model provider and data transfer process. * Provides enterprises with traceable security assurance for API usage, ensuring safety and trust. * **Scaled Discount Supply · Cost Savings Up to 70%** * Multi-vendor aggregation and dynamic routing mechanisms automatically match the lowest calling cost path. * Single call costs can be reduced by **up to 70%**—delivering cost reduction without sacrificing quality. * **FDE (Forward Deployed Engineer) Expert Escort · Accelate Project Launch** * Provides N:1 technical support to quickly diagnose and solve problems. * On average, Siray help you shortens time-to-market by 20%, accelerating the rapid iteration, scaled deployment, and commercialization of AI projects. > **[Quickstart](/quickstart)** > > Set up your account and get started. > **[Model APIs](/model-apis/api-integration)** > > Start your project with AI APIs. # Qwen Image 3 Edit Source: https://docs.siray.ai/model-apis/alibaba/qwen-image-3-edit Qwen Image 3 Edit Spicy by Alibaba Cloud is a Spicy image editing model for prompt-guided retouching and compositing. It supports mature, boundary-pushing content with polished results. ### Model Use Cases Use Qwen Image 3 Pro Edit Spicy by Alibaba Cloud for prompt-guided image editing, retouching, compositing, and mature or boundary-pushing creative concepts. > **[Try Qwen Image 3 Edit on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with precise natural-language instructions. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Prompt Control:** Applies targeted edits while following subject, composition, and style requirements. * **Professional Quality:** Targets polished outputs for demanding design, marketing, and production workflows. * **Creative Iteration:** Enables rapid variations for campaigns, concepts, and visual development workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/qwen-image-3-edit)** # Qwen Image 3 Edit Spicy Source: https://docs.siray.ai/model-apis/alibaba/qwen-image-3-edit-spicy Qwen Image 3 Edit Spicy by Alibaba Cloud is a Spicy image editing model for prompt-guided retouching and compositing. It supports mature, boundary-pushing content with polished results. ### Model Use Cases Use Qwen Image 3 Pro Edit Spicy by Alibaba Cloud for prompt-guided image editing, retouching, compositing, and mature or boundary-pushing creative concepts. > **[Try Qwen Image 3 Edit Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with precise natural-language instructions. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Prompt Control:** Applies targeted edits while following subject, composition, and style requirements. * **Professional Quality:** Targets polished outputs for demanding design, marketing, and production workflows. * **Creative Iteration:** Enables rapid variations for campaigns, concepts, and visual development workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/qwen-image-3-edit-spicy)** # Qwen Image 3 Pro Edit Spicy Source: https://docs.siray.ai/model-apis/alibaba/qwen-image-3-pro-edit-spicy Qwen Image 3 Pro Edit Spicy by Alibaba Cloud is a Spicy image editing model for prompt-guided retouching and compositing. It supports mature, boundary-pushing content with polished results. ### Model Use Cases Use Qwen Image 3 Pro Edit Spicy by Alibaba Cloud for prompt-guided image editing, retouching, compositing, and mature or boundary-pushing creative concepts. > **[Try Qwen Image 3 Pro Edit Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with precise natural-language instructions. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Prompt Control:** Applies targeted edits while following subject, composition, and style requirements. * **Professional Quality:** Targets polished outputs for demanding design, marketing, and production workflows. * **Creative Iteration:** Enables rapid variations for campaigns, concepts, and visual development workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/qwen-image-3-pro-edit-spicy)** # Qwen Image 3 Pro t2i Spicy Source: https://docs.siray.ai/model-apis/alibaba/qwen-image-3-pro-t2i-spicy Qwen Image 3 Pro t2i Spicy by Alibaba Cloud is a Spicy text-to-image model for concept art, marketing visuals, and creative design. It supports mature, boundary-pushing content with polished results. ### Model Use Cases Use Qwen Image 3 Pro t2i Spicy by Alibaba Cloud to create concept art, campaign visuals, product imagery, and mature or boundary-pushing creative content. > **[Try Qwen Image 3 Pro t2i Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates polished visuals from natural-language prompts and creative concepts for fast iteration. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Prompt Adherence:** Follows subject, composition, style, and mood instructions with strong prompt control. * **Professional Quality:** Targets polished outputs for demanding design, marketing, and production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, product visuals, and creative exploration workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/qwen-image-3-pro-t2i-spicy)** # Qwen Image 3 t2i Source: https://docs.siray.ai/model-apis/alibaba/qwen-image-3-t2i Qwen Image 3 t2i Spicy by Alibaba Cloud is a Spicy text-to-image model for concept art, marketing visuals, and creative design. It supports mature, boundary-pushing content with polished results. ### Model Use Cases Use Qwen Image 3 Pro t2i Spicy by Alibaba Cloud to create concept art, campaign visuals, product imagery, and mature or boundary-pushing creative content. > **[Try Qwen Image 3 t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates polished visuals from natural-language prompts and creative concepts for fast iteration. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Prompt Adherence:** Follows subject, composition, style, and mood instructions with strong prompt control. * **Professional Quality:** Targets polished outputs for demanding design, marketing, and production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, product visuals, and creative exploration workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/qwen-image-3-t2i)** # Qwen Image 3 t2i Spicy Source: https://docs.siray.ai/model-apis/alibaba/qwen-image-3-t2i-spicy Qwen Image 3 t2i Spicy by Alibaba Cloud is a Spicy text-to-image model for concept art, marketing visuals, and creative design. It supports mature, boundary-pushing content with polished results. ### Model Use Cases Use Qwen Image 3 Pro t2i Spicy by Alibaba Cloud to create concept art, campaign visuals, product imagery, and mature or boundary-pushing creative content. > **[Try Qwen Image 3 t2i Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates polished visuals from natural-language prompts and creative concepts for fast iteration. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Prompt Adherence:** Follows subject, composition, style, and mood instructions with strong prompt control. * **Professional Quality:** Targets polished outputs for demanding design, marketing, and production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, product visuals, and creative exploration workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/qwen-image-3-t2i-spicy)** # Qwen3 Coder 480B A35B Instruct Source: https://docs.siray.ai/model-apis/alibaba/qwen3-coder-480b-a35b-instruct Qwen3 Coder 480B A35B Instruct by Alibaba Cloud: coding and reasoning AI for code generation and technical reasoning, built for high-quality outputs, reliable control, and scalable production use. ### Model Use Cases Use Qwen3 Coder 480B A35B Instruct by Alibaba Cloud for software development, code generation, and technical problem solving. > **[Try Qwen3 Coder 480B A35B Instruct on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Code Generation:** Writes, explains, refactors, and reviews software code across creative and business applications. * **Technical Reasoning:** Breaks down complex engineering tasks into clear steps across creative and business applications. * **Instruction Following:** Adapts responses to detailed development requirements across creative and business applications. * **Developer Workflows:** Supports debugging, documentation, testing, and automation for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/qwen3-coder-480b-a35b-instruct)** # Wan 2.6 i2v Source: https://docs.siray.ai/model-apis/alibaba/wan-2.6-i2v Wan 2.6 i2v by Alibaba Cloud is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Wan 2.6 i2v by Alibaba Cloud for image animation, camera movement, and cinematic clips. > **[Try Wan 2.6 i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-2.6-i2v)** # Wan 2.6 t2v Source: https://docs.siray.ai/model-apis/alibaba/wan-2.6-t2v Wan 2.6 t2v by Alibaba Cloud is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Wan 2.6 t2v by Alibaba Cloud for text-to-video creation, storytelling, and marketing content. > **[Try Wan 2.6 t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-2.6-t2v)** # Wan 2.7 i2v Spicy Source: https://docs.siray.ai/model-apis/alibaba/wan-2.7-i2v-spicy Wan 2.7 i2v Spicy by Alibaba Cloud: image-to-video AI for image animation and cinematic video, with mature and boundary-pushing creative content and reliable production control. ### Model Use Cases Use Wan 2.7 i2v Spicy by Alibaba Cloud for image animation, camera movement, and cinematic clips; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Wan 2.7 i2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-2.7-i2v-spicy)** # Wan 2.7 i2v Uncensored Source: https://docs.siray.ai/model-apis/alibaba/wan-2.7-i2v-uncensored Wan 2.7 i2v Uncensored by Alibaba Cloud: image-to-video AI for image animation and cinematic video, with broader, less-filtered creative content and reliable production control. ### Model Use Cases Use Wan 2.7 i2v Uncensored by Alibaba Cloud for image animation, camera movement, and cinematic clips; its Uncensored variant supports broader, less-filtered creative concepts. > **[Try Wan 2.7 i2v Uncensored on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. * **Uncensored Variant:** Supports broader, less-filtered creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-2.7-i2v-uncensored)** # Wan 2.7 Image i2i Spicy Source: https://docs.siray.ai/model-apis/alibaba/wan-2.7-image-i2i-spicy Wan 2.7 Image i2i Spicy by Alibaba Cloud is a Spicy image editing model for prompt-guided retouching and compositing. It supports mature, boundary-pushing content with polished results. ### Model Use Cases Use Wan 2.7 Image i2i Spicy by Alibaba Cloud for prompt-guided image editing, retouching, compositing, and mature or boundary-pushing creative concepts. > **[Try Wan 2.7 Image i2i Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with precise natural-language instructions. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Prompt Control:** Applies targeted edits while following subject, composition, and style requirements. * **Professional Quality:** Targets polished outputs for demanding design, marketing, and production workflows. * **Creative Iteration:** Enables rapid variations for campaigns, concepts, and visual development workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-2.7-image-i2i-spicy)** # Wan 2.7 Image Pro i2i Spicy Source: https://docs.siray.ai/model-apis/alibaba/wan-2.7-image-pro-i2i-spicy Wan 2.7 Image Pro i2i Spicy by Alibaba Cloud is a Spicy image editing model for prompt-guided retouching and compositing. It supports mature, boundary-pushing content with polished results. ### Model Use Cases Use Wan 2.7 Image Pro i2i Spicy by Alibaba Cloud for prompt-guided image editing, retouching, compositing, and mature or boundary-pushing creative concepts. > **[Try Wan 2.7 Image Pro i2i Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with precise natural-language instructions. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Prompt Control:** Applies targeted edits while following subject, composition, and style requirements. * **Professional Quality:** Targets polished outputs for demanding design, marketing, and production workflows. * **Creative Iteration:** Enables rapid variations for campaigns, concepts, and visual development workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-2.7-image-pro-i2i-spicy)** # Wan 2.7 Image Pro t2i Spicy Source: https://docs.siray.ai/model-apis/alibaba/wan-2.7-image-pro-t2i-spicy Wan 2.7 Image Pro t2i Spicy by Alibaba Cloud is a Spicy text-to-image model for concept art, marketing visuals, and creative design. It supports mature, boundary-pushing content with polished results. ### Model Use Cases Use Wan 2.7 Image Pro t2i Spicy by Alibaba Cloud to create concept art, campaign visuals, product imagery, and mature or boundary-pushing creative content. > **[Try Wan 2.7 Image Pro t2i Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates polished visuals from natural-language prompts and creative concepts for fast iteration. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Prompt Adherence:** Follows subject, composition, style, and mood instructions with strong prompt control. * **Professional Quality:** Targets polished outputs for demanding design, marketing, and production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, product visuals, and creative exploration workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-2.7-image-pro-t2i-spicy)** # Wan 2.7 Image t2i Spicy Source: https://docs.siray.ai/model-apis/alibaba/wan-2.7-image-t2i-spicy Wan 2.7 Image t2i Spicy by Alibaba Cloud is a Spicy text-to-image model for concept art, marketing visuals, and creative design. It supports mature, boundary-pushing content with polished results. ### Model Use Cases Use Wan 2.7 Image t2i Spicy by Alibaba Cloud to create concept art, campaign visuals, product imagery, and mature or boundary-pushing creative content. > **[Try Wan 2.7 Image t2i Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates polished visuals from natural-language prompts and creative concepts for fast iteration. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Prompt Adherence:** Follows subject, composition, style, and mood instructions with strong prompt control. * **Professional Quality:** Targets polished outputs for demanding design, marketing, and production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, product visuals, and creative exploration workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-2.7-image-t2i-spicy)** # Wan 2.7 ref2v Uncensored Source: https://docs.siray.ai/model-apis/alibaba/wan-2.7-ref2v-uncensored Wan 2.7 ref2v Uncensored by Alibaba Cloud is a reference-to-video AI model for reference-guided video. Its Uncensored variant supports broader, less-filtered creative content for production workflows. ### Model Use Cases Use Wan 2.7 ref2v Uncensored by Alibaba Cloud for reference-guided video, animation, and visual continuity with broader, less-filtered creative concepts. > **[Try Wan 2.7 ref2v Uncensored on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference Guidance:** Uses visual references to steer subjects, style, and scenes for dependable production workflows. * **Video Generation:** Turns concepts into animated clips for rapid iteration across creative and business applications. * **Temporal Coherence:** Maintains subject identity and visual continuity across frames for dependable production workflows. * **Creative Control:** Supports repeatable direction for production-ready concepts for dependable production workflows. * **Uncensored Variant:** Supports broader, less-filtered creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-2.7-ref2v-uncensored)** # Wan 2.7 t2v Uncensored Source: https://docs.siray.ai/model-apis/alibaba/wan-2.7-t2v-uncensored Wan 2.7 t2v Uncensored by Alibaba Cloud is a text-to-video AI model for text-to-video storytelling. Its Uncensored variant supports broader, less-filtered creative content for production workflows. ### Model Use Cases Use Wan 2.7 t2v Uncensored by Alibaba Cloud for text-to-video creation, storytelling, and marketing content with broader, less-filtered creative concepts. > **[Try Wan 2.7 t2v Uncensored on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. * **Uncensored Variant:** Supports broader, less-filtered creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-2.7-t2v-uncensored)** # Wan 3.0 i2v Source: https://docs.siray.ai/model-apis/alibaba/wan-3.0-i2v Wan 3.0 i2v by Alibaba Cloud is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Wan 3.0 i2v by Alibaba Cloud for image animation, camera movement, and cinematic clips. > **[Try Wan 3.0 i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-3.0-i2v)** # Wan 3.0 i2v Prime Spicy Source: https://docs.siray.ai/model-apis/alibaba/wan-3.0-i2v-prime-spicy Wan 3.0 i2v Prime Spicy by Alibaba Cloud is a Prime image-to-video model for animating images into clips. Its Spicy variant supports mature, boundary-pushing content with premium visual quality. ### Model Use Cases Use Wan 3.0 i2v Prime Spicy by Alibaba Cloud for cinematic image animation, marketing clips, storyboards, and mature or boundary-pushing creative concepts. > **[Try Wan 3.0 i2v Prime Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image-to-Video:** Transforms still images into cinematic clips with expressive movement and scene dynamics. * **Prime Variant:** Targets premium visual quality, richer detail, and consistent production-ready results. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Temporal Coherence:** Maintains subject identity, motion continuity, and visual consistency across frames. * **Camera Direction:** Supports controlled pans, zooms, camera movement, and cinematic visual storytelling. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-3.0-i2v-prime-spicy)** # Wan 3.0 i2v Spicy Source: https://docs.siray.ai/model-apis/alibaba/wan-3.0-i2v-spicy Wan 3.0 i2v Spicy by Alibaba Cloud: image-to-video AI for image animation and cinematic video, with mature and boundary-pushing creative content and reliable production control. ### Model Use Cases Use Wan 3.0 i2v Spicy by Alibaba Cloud for image animation, camera movement, and cinematic clips; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Wan 3.0 i2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-3.0-i2v-spicy)** # Wan 3.0 ref2v Source: https://docs.siray.ai/model-apis/alibaba/wan-3.0-ref2v Wan 3.0 ref2v by Alibaba Cloud is a reference-to-video AI model for reference-guided video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Wan 3.0 ref2v by Alibaba Cloud for reference-guided video, animation, and visual continuity. > **[Try Wan 3.0 ref2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference Guidance:** Uses visual references to steer subjects, style, and scenes for dependable production workflows. * **Video Generation:** Turns concepts into animated clips for rapid iteration across creative and business applications. * **Temporal Coherence:** Maintains subject identity and visual continuity across frames for dependable production workflows. * **Creative Control:** Supports repeatable direction for production-ready concepts for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-3.0-ref2v)** # Wan 3.0 ref2v Prime Spicy Source: https://docs.siray.ai/model-apis/alibaba/wan-3.0-ref2v-prime-spicy Wan 3.0 ref2v Prime Spicy by Alibaba Cloud is a Prime reference-to-video model for reference-guided animation. Its Spicy variant supports mature, boundary-pushing content with premium quality. ### Model Use Cases Use Wan 3.0 ref2v Prime Spicy by Alibaba Cloud for reference-guided animation, character continuity, visual storytelling, and mature creative concepts. > **[Try Wan 3.0 ref2v Prime Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference-to-Video:** Uses visual references to guide subjects, style, composition, and scene direction. * **Prime Variant:** Targets premium visual quality, richer detail, and consistent production-ready results. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Visual Consistency:** Preserves key subject identity, style cues, and scene context across generated frames. * **Creative Direction:** Supports repeatable animation, story development, and reference-led production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-3.0-ref2v-prime-spicy)** # Wan 3.0 ref2v Spicy Source: https://docs.siray.ai/model-apis/alibaba/wan-3.0-ref2v-spicy Wan 3.0 ref2v Spicy by Alibaba Cloud is a reference-to-video AI model for reference-guided video. Its Spicy variant supports mature and boundary-pushing creative content for production workflows. ### Model Use Cases Use Wan 3.0 ref2v Spicy by Alibaba Cloud for reference-guided video, animation, and visual continuity; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Wan 3.0 ref2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference Guidance:** Uses visual references to steer subjects, style, and scenes for dependable production workflows. * **Video Generation:** Turns concepts into animated clips for rapid iteration across creative and business applications. * **Temporal Coherence:** Maintains subject identity and visual continuity across frames for dependable production workflows. * **Creative Control:** Supports repeatable direction for production-ready concepts for dependable production workflows. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-3.0-ref2v-spicy)** # Wan 3.0 t2v Source: https://docs.siray.ai/model-apis/alibaba/wan-3.0-t2v Wan 3.0 t2v by Alibaba Cloud is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Wan 3.0 t2v by Alibaba Cloud for text-to-video creation, storytelling, and marketing content. > **[Try Wan 3.0 t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-3.0-t2v)** # Wan 3.0 t2v Prime Spicy Source: https://docs.siray.ai/model-apis/alibaba/wan-3.0-t2v-prime-spicy Wan 3.0 t2v Prime Spicy by Alibaba Cloud is a Prime text-to-video model for cinematic stories and creative production. Its Spicy variant supports mature, boundary-pushing content with premium quality. ### Model Use Cases Use Wan 3.0 t2v Prime Spicy by Alibaba Cloud for cinematic stories, advertising, social videos, concept development, and mature or boundary-pushing creative content. > **[Try Wan 3.0 t2v Prime Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates cinematic scenes from natural-language prompts and detailed creative direction. * **Prime Variant:** Targets premium visual quality, richer detail, and consistent production-ready results. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration with broader visual latitude. * **Cinematic Motion:** Builds camera movement, action, atmosphere, and pacing into generated video clips. * **Prompt Control:** Follows subject, setting, style, mood, and narrative instructions with strong control. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-3.0-t2v-prime-spicy)** # Wan 3.0 t2v Spicy Source: https://docs.siray.ai/model-apis/alibaba/wan-3.0-t2v-spicy Wan 3.0 t2v Spicy by Alibaba Cloud is a text-to-video AI model for text-to-video storytelling. Its Spicy variant supports mature and boundary-pushing creative content for production workflows. ### Model Use Cases Use Wan 3.0 t2v Spicy by Alibaba Cloud for text-to-video creation, storytelling, and marketing content; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Wan 3.0 t2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/wan-3.0-t2v-spicy)** # Z-Image Spicy Pro t2i Source: https://docs.siray.ai/model-apis/alibaba/z-image-spicy-pro-t2i Z-Image Spicy Pro t2i by Alibaba Cloud is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Z-Image Turbo t2i by Alibaba Cloud for text-to-image generation, concept art, and marketing visuals. > **[Try Z-Image Spicy Pro t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/z-image-spicy-pro-t2i)** # Z-Image Turbo t2i Source: https://docs.siray.ai/model-apis/alibaba/z-image-turbo-t2i Z-Image Turbo t2i by Alibaba Cloud is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Z-Image Turbo t2i by Alibaba Cloud for text-to-image generation, concept art, and marketing visuals. > **[Try Z-Image Turbo t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/z-image-turbo-t2i)** # Claude Fable 5.1 Source: https://docs.siray.ai/model-apis/anthropic/claude-fable-5.1 Claude Fable 5.1 by Anthropic is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Claude Opus 4.5 by Anthropic for writing, analysis, automation, and multimodal applications. > **[Try Claude Fable 5.1 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/claude-fable-5.1)** # Claude Haiku 4.5 Source: https://docs.siray.ai/model-apis/anthropic/claude-haiku-4.5 Claude Haiku 4.5 by Anthropic is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Claude Haiku 4.5 by Anthropic for writing, analysis, automation, and multimodal applications. > **[Try Claude Haiku 4.5 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/claude-haiku-4.5)** # Claude Haiku 5.5 Source: https://docs.siray.ai/model-apis/anthropic/claude-haiku-5.5 Claude Haiku 5.5 by Anthropic is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Claude Haiku 5.5 by Anthropic for writing, analysis, automation, and multimodal applications. > **[Try Claude Haiku 5.5 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/claude-haiku-5.5)** # Claude Opus 4.6 Source: https://docs.siray.ai/model-apis/anthropic/claude-opus-4.6 Claude Opus 4.6 by Anthropic is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Claude Opus 4.6 by Anthropic for writing, analysis, automation, and multimodal applications. > **[Try Claude Opus 4.6 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/claude-opus-4.6)** # Claude Opus 5.5 Source: https://docs.siray.ai/model-apis/anthropic/claude-opus-5.5 Claude Opus 5.5 by Anthropic is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Claude Opus 5.5 by Anthropic for writing, analysis, automation, and multimodal applications. > **[Try Claude Opus 5.5 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/claude-opus-5.5)** # Claude Sonnet 4.5 Source: https://docs.siray.ai/model-apis/anthropic/claude-sonnet-4.5 Claude Sonnet 4.5 by Anthropic is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Claude Sonnet 4.5 by Anthropic for writing, analysis, automation, and multimodal applications. > **[Try Claude Sonnet 4.5 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/claude-sonnet-4.5)** # Claude Sonnet 4.6 Source: https://docs.siray.ai/model-apis/anthropic/claude-sonnet-4.6 Claude Sonnet 4.6 by Anthropic is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Claude Sonnet 4.6 by Anthropic for writing, analysis, automation, and multimodal applications. > **[Try Claude Sonnet 4.6 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/claude-sonnet-4.6)** # Claude Sonnet 5.5 Source: https://docs.siray.ai/model-apis/anthropic/claude-sonnet-5.5 Claude Sonnet 5.5 by Anthropic is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Claude Sonnet 5.5 by Anthropic for writing, analysis, automation, and multimodal applications. > **[Try Claude Sonnet 5.5 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/claude-sonnet-5.5)** # API Integration Source: https://docs.siray.ai/model-apis/api-integration Siray API is designed to provide a consistent interface across multiple platforms, simplifying development. ### 1. Authentication All API requests require an authentication token. Please ensure you have your `SIRAY_API_TOKEN` set as an environment variable or passed directly to the client library. * **Token:** `SIRAY_API_TOKEN` * **Security:** Pass the token via an environment variable to prevent hardcoding secrets in your source code. > [!TIP] > > Check [api keys](https://console.siray.ai/keys) to get your key. > > API Port: [https://api.siray.ai/](https://api.siray.ai/) ### 2. Unified API Overview The core of the Siray platform is the "Unified API," which allows you to interact with various models using a consistent `run()` method. The key components of an API call are: 1. **Model Identifier:** E.g., `"black-forest-labs/flux-kontext-i2i-pro"`. 2. **Input Payload:** A dictionary/object containing parameters like `prompt` and the input `image`. ### 3. Integration Examples **Node.js** ```javascript theme={null} // install using npm // npm install siray import { Siray } from 'siray'; const client = new Siray({ apiKey: 'your-api-key-here', }); // Optional: turn a local file into a base64 data URL you can pass as the `image` field const initImage = await client.loadFromLocal('path/to/image.jpg'); const status = await client.image.run( { model: 'black-forest-labs/flux-kontext-i2i-pro', prompt: 'A cinematic portrait photo of a cyberpunk samurai', image: initImage, }, { pollIntervalMs: 3000, timeoutMs: 3 * 60 * 1000, } ); if (status.isCompleted()) { console.log('Generated image:', status.result); } else if (status.isFailed()) { console.log('Error:', status.fail_reason); } else { console.log('Final status:', status.status); } ``` > [!TIP] > > Note: Always use the latest model identifiers from the Siray model catalog. # Flux 1.1 Pro i2i Source: https://docs.siray.ai/model-apis/black-forest-labs/flux-1.1-pro-i2i Black Forest Labs' Flux 1.1 Pro is an advanced, high-speed Image-to-Image model ideal for fast, high-quality style transfer and image-guided generation. ### Model Use Cases FLUX1.1 Pro is a robust and proven image-to-image baseline for generating high-quality visuals. It combines state-of-the-art inference speeds with strong prompt adherence, ideal for scalable, text-based image generation. > **[Try Flux 1.1 Pro i2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **High Performance:** It generates images up to six times faster than its predecessor, the original Flux 1.0 Pro. * **Superior Image Quality:** The model produces high-quality images with enhanced detail, better prompt adherence, and output diversity. * **High Resolution:** It supports the generation of high-resolution images, up to 2K, without sacrificing quality or speed. * **Versatility:** It can generate various styles of images, including photorealistic, cartoon, and painted styles. * **Modes:** It features an "Ultra Mode" for maximum resolution (up to 4MP) and a "Raw Mode" for more natural, photorealistic results that reduce the "AI look". > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/flux-1.1-pro-i2i)** # Flux 1.1 Pro t2i Source: https://docs.siray.ai/model-apis/black-forest-labs/flux-1.1-pro-t2i Black Forest Labs' Flux 1.1 Pro is a fast, state-of-the-art Text-to-Image model for high-quality visual generation with superior speed and prompt adherence. ### Model Use Cases Flux Pro T2I is a fast, state-of-the-art Text-to-Image model. It delivers high-quality visual generation with superior speed and faithful adherence to complex text prompts. > **[Try Flux 1.1 Pro t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Superior Image Quality:** Generates high-quality, photorealistic, and creative images comparable to premium closed-source text-to-image models. * **Accurate Prompt Interpretation:** Excels at understanding complex and detailed text prompts and translating them into precise visuals. * **High-Resolution Output:** Produces professional-quality images at 1024×1024 resolution, suitable for digital art and design. * **Versatile Artistic Styles:** Supports a wide range of styles, from photorealistic portraits to abstract and painted artwork. * **Text Integration Capability:** Accurately incorporates text into images, ideal for labels, signs, or annotations in generated visuals. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/flux-1.1-pro-t2i)** # Flux 1.1 Pro Ultra i2i Source: https://docs.siray.ai/model-apis/black-forest-labs/flux-1.1-pro-ultra-i2i Black Forest Labs' Flux 1.1 Pro Ultra is a premium Image-to-Image model for ultra-high-resolution style transfer and image-guided generation up to 4MP. ### Model Use Cases A premium Image-to-Image model for ultra-high-resolution style transfer and image-guided generation up to 4MP, supporting professional workflows. > **[Try Flux 1.1 Pro Ultra i2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Ultra-High Resolution:** Generates images up to 4MP, four times higher than the standard model, ideal for printing and professional visuals. * **High Speed:** Produces high-resolution results in under 10 seconds, outperforming most AI image generators. * **Commercial Ready:** Outputs are suitable for business and marketing use with full commercial rights. * **Dual Modes:** * **Ultra Mode:** Focuses on fine details and prompt accuracy. * **Raw Mode:** Delivers natural, lifelike results with reduced “AI look.” > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/flux-1.1-pro-ultra-i2i)** # Flux 1.1 Pro Ultra t2i Source: https://docs.siray.ai/model-apis/black-forest-labs/flux-1.1-pro-ultra-t2i Black Forest Labs' Flux 1.1 Pro Ultra is a flagship Text-to-Image model that generates ultra-fast, high-fidelity images up to 4MP resolution with new Ultra/Raw modes. ### Model Use Cases Flux 1.1 Pro Ultra is an advanced text-to-image (T2I) AI model developed by Black Forest Labs. It enables ultra-high-resolution and photorealistic image generation from detailed text prompts, delivering fast and efficient performance for creative and professional applications. > **[Try Flux 1.1 Pro Ultra t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Ultra-High Resolution:** Generates images up to 4MP (2048×2048), four times higher than the standard Flux 1.1 Pro. Ideal for professional prints, detailed artwork, and large web visuals. * **High Realism & Detail:** Produces photorealistic images with rich textures, accurate lighting, and lifelike human representations. * **Prompt Adherence:** Delivers precise alignment with text prompts, ensuring generated images accurately match user intent. * **Dual Modes:** * **Ultra Mode:** Optimized for high-resolution detail and visual clarity. * **Raw Mode:** Designed for natural, film-like aesthetics, excelling in portraits and nature scenes. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/flux-1.1-pro-ultra-t2i)** # Flux 3 i2v Source: https://docs.siray.ai/model-apis/black-forest-labs/flux-3-i2v Flux 3 i2v is Black Forest Labs' image-to-video model built on the Flux architecture. Transform static images into dynamic videos with natural motion and strong visual fidelity. ### Model Use Cases Animate product shots, artwork, or photos into engaging video content with Black Forest Labs' advanced Flux image-to-video generation technology. > **[Try Flux 3 i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Flux Architecture:** Built on Black Forest Labs' proven generative engine. * **Image Animation:** Transform still images into dynamic video sequences. * **Natural Motion:** Generates realistic, physically plausible movement. * **Source Fidelity:** Preserves key visual elements from input images. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/flux-3-i2v)** # Flux 3 t2v Source: https://docs.siray.ai/model-apis/black-forest-labs/flux-3-t2v Flux 3 t2v is Black Forest Labs' text-to-video model built on the Flux architecture. Generate high-quality videos from text prompts with strong visual coherence and detail. ### Model Use Cases Create marketing videos, creative content, or visual storytelling from text descriptions using Black Forest Labs' advanced Flux video generation technology. > **[Try Flux 3 t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Flux Architecture:** Built on Black Forest Labs' proven generative engine. * **Text-to-Video Creation:** Generate complete videos from natural language prompts. * **Strong Visual Coherence:** Maintains consistent detail across generated frames. * **High-Quality Output:** Produces detailed, professional-grade video results. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/flux-3-t2v)** # Flux 3 v2v Source: https://docs.siray.ai/model-apis/black-forest-labs/flux-3-v2v Flux 3 v2v is Black Forest Labs' video extension model built on the Flux architecture. Continue existing clips beyond their final frame with seamless, motion-consistent footage. ### Model Use Cases Extend short video clips, continue animations, or add additional footage to existing videos while maintaining consistent motion and scene continuity. > **[Try Flux 3 v2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Flux Architecture:** Built on Black Forest Labs' proven generative engine. * **Video Extension:** Continues clips beyond their final frame seamlessly. * **Motion Consistency:** Maintains original movement patterns in new footage. * **Scene Continuity:** Preserves scene context and visual coherence. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/flux-3-v2v)** # Flux Kontext i2i Max Source: https://docs.siray.ai/model-apis/black-forest-labs/flux-kontext-i2i-max Black Forest Labs' Flux Kontext Max is the premium In-Context Image Editing model offering maximum performance in precise editing, style consistency, and typography control. ### Model Use Cases Flux Kontext I2I Max is the premium, top-tier version of the Flux generative AI model, specifically designed for advanced image-to-image (I2I) editing, high-fidelity transformations, and professional creative workflows. > **[Try Flux Kontext i2i Max on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Advanced Image-to-Image Editing:** High-quality I2I transformations for modifying or enhancing existing images. * **High Consistency Across Edits:** Maintains characters, objects, and composition over multiple iterative changes. * **Professional-Grade Output:** Produces high-resolution, detailed visuals suitable for commercial and creative workflows. * **Style Transfer & Reference Integration:** Supports reference images for consistent style and continuity. * **Fast & Efficient Performance:** Optimized for quick inference while handling complex edits without quality loss. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/flux-kontext-i2i-max)** # Flux Kontext i2i Pro Source: https://docs.siray.ai/model-apis/black-forest-labs/flux-kontext-i2i-pro Black Forest Labs' Flux Kontext Pro is a powerful In-Context Image Editing model for precise, consistent edits, object modifications, and local region control via text. ### Model Use Cases Flux Kontext I2I Pro is an advanced generative AI model developed by Black Forest Labs, designed for context-aware image-to-image (I2I) editing, enabling high-quality, precise, and professional-grade image transformations. > **[Try Flux Kontext i2i Pro on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Advanced Image-to-Image Editing:** Performs high-quality I2I transformations for modifying or enhancing images with precision. * **Context-Aware Modifications:** Understands image content and context to make accurate local and global edits. * **Multimodal Input Support:** Accepts both images and text prompts, allowing for flexible, natural-language-guided edits. * **Iterative Editing Workflow:** Supports multi-step, chat-style editing, preserving character and style consistency across iterations. * **Style Transfer & Reference Integration:** Use reference images to maintain consistent style or apply artistic transformations without extra fine-tuning. * **High-Quality Output:** Produces professional-grade, detailed images suitable for creative, commercial, and professional projects. * **Fast and Efficient Performance:** Optimized for quick inference, enabling smooth, iterative creative workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/flux-kontext-i2i-pro)** # Flux Kontext t2i Max Source: https://docs.siray.ai/model-apis/black-forest-labs/flux-kontext-t2i-max Black Forest Labs' Flux Kontext Max is the highest-tier Generative Flow model pushing prompt precision, superior typography, and character consistency in T2I. ### Model Use Cases Flux Kontext Max T2I generates photorealistic and cinematic-quality images with exceptional detail, optimized for high-end visuals, including realistic human portraits, polished product renders, and professional creative content. > **[Try Flux Kontext t2i Max on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Maximum Prompt Adherence:** Accurately follows complex and nuanced text instructions, ideal for professional artists and creators. * **Premium Image Quality & Consistency:** Generates high-resolution, detailed images while maintaining character likeness and visual consistency across multiple edits, minimizing visual drift. * **Advanced Typography:** Produces readable, well-integrated text within images, overcoming challenges common to AI-generated graphics. * **Object Modification:** Edit specific objects without affecting the rest of the image. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/flux-kontext-t2i-max)** # Flux Kontext t2i Pro Source: https://docs.siray.ai/model-apis/black-forest-labs/flux-kontext-t2i-pro Black Forest Labs' Flux Kontext Pro is a unified Generative Flow model for text-to-image generation that excels in maintaining character and style consistency. ### Model Use Cases Flux Kontext T2I Pro is an advanced generative AI model that combines text-to-image (T2I) generation with context-aware image editing, enabling users to create high-quality, editable visuals from text prompts. > **[Try Flux Kontext t2i Pro on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Advanced Contextual Understanding:** Uses a generative flow-matching approach to accurately interpret both text and image content, allowing precise modifications while preserving overall composition. * **High-Quality, Fast Performance:** Delivers professional-grade visuals with rapid inference speed, ideal for quick, iterative creative workflows. * **Commercial-Grade Capabilities:** Designed for professional and commercial applications, with precise control over typography, objects, and multi-scene consistency. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/flux-kontext-t2i-pro)** # Seed 1.6 Source: https://docs.siray.ai/model-apis/bytedance/seed-1.6 Seed 1.6 by ByteDance is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seed 1.6 by ByteDance for writing, analysis, automation, and multimodal applications. > **[Try Seed 1.6 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seed-1.6)** # Seedance 1.0 Lite i2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-1.0-lite-i2v Seedance 1.0 Lite i2v by ByteDance is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 1.0 Lite i2v by ByteDance for image animation, camera movement, and cinematic clips. > **[Try Seedance 1.0 Lite i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-1.0-lite-i2v)** # Seedance 1.0 Lite t2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-1.0-lite-t2v Seedance 1.0 Lite t2v by ByteDance is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 1.0 Lite t2v by ByteDance for text-to-video creation, storytelling, and marketing content. > **[Try Seedance 1.0 Lite t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-1.0-lite-t2v)** # Seedance 1.0 Pro Fast t2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-1.0-pro-fast-t2v Seedance 1.0 Pro Fast t2v by ByteDance is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 1.0 Pro Fast t2v by ByteDance for text-to-video creation, storytelling, and marketing content. > **[Try Seedance 1.0 Pro Fast t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-1.0-pro-fast-t2v)** # Seedance 1.0 Pro i2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-1.0-pro-i2v Seedance 1.0 Pro i2v by ByteDance is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 1.0 Pro i2v by ByteDance for image animation, camera movement, and cinematic clips. > **[Try Seedance 1.0 Pro i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-1.0-pro-i2v)** # Seedance 1.0 Pro t2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-1.0-pro-t2v Seedance 1.0 Pro t2v by ByteDance is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 1.0 Pro t2v by ByteDance for text-to-video creation, storytelling, and marketing content. > **[Try Seedance 1.0 Pro t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-1.0-pro-t2v)** # Seedance 1.5 Pro i2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-1.5-pro-i2v Seedance 1.5 Pro i2v by ByteDance is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 1.5 Pro i2v by ByteDance for image animation, camera movement, and cinematic clips. > **[Try Seedance 1.5 Pro i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-1.5-pro-i2v)** # Seedance 1.5 Pro se2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-1.5-pro-se2v Seedance 1.5 Pro se2v by ByteDance is a start/end-frame-to-video AI model for controlled video transitions. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 1.5 Pro se2v by ByteDance for transitions, story beats, and controlled animation. > **[Try Seedance 1.5 Pro se2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Frame Guidance:** Uses starting and ending frames to shape the generated transition for fast, repeatable AI workflows. * **Controlled Animation:** Creates directed movement between defined visual states across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Story Beats:** Helps visualize transitions, scenes, and narrative moments for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-1.5-pro-se2v)** # Seedance 1.5 Pro t2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-1.5-pro-t2v Seedance 1.5 Pro t2v by ByteDance is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 1.5 Pro t2v by ByteDance for text-to-video creation, storytelling, and marketing content. > **[Try Seedance 1.5 Pro t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-1.5-pro-t2v)** # Seedance 2.0 Fast i2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.0-fast-i2v Seedance 2.0 Fast i2v by ByteDance is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 2.0 Fast i2v by ByteDance for image animation, camera movement, and cinematic clips. > **[Try Seedance 2.0 Fast i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.0-fast-i2v)** # Seedance 2.0 Fast t2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.0-fast-t2v Seedance 2.0 Fast t2v by ByteDance is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 2.0 Fast t2v by ByteDance for text-to-video creation, storytelling, and marketing content. > **[Try Seedance 2.0 Fast t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.0-fast-t2v)** # Seedance 2.0 i2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.0-i2v Seedance 2.0 i2v by ByteDance is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 2.0 i2v by ByteDance for image animation, camera movement, and cinematic clips. > **[Try Seedance 2.0 i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.0-i2v)** # Seedance 2.0 i2v Spicy Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.0-i2v-spicy Seedance 2.0 i2v Spicy by ByteDance: image-to-video AI for image animation and cinematic video, with mature and boundary-pushing creative content and reliable production control. ### Model Use Cases Use Seedance 2.0 i2v Spicy by ByteDance for image animation, camera movement, and cinematic clips; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Seedance 2.0 i2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.0-i2v-spicy)** # Seedance 2.0 ref2v Spicy Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.0-ref2v-spicy Seedance 2.0 ref2v Spicy by ByteDance is a reference-to-video AI model for reference-guided video. Its Spicy variant supports mature and boundary-pushing creative content for production workflows. ### Model Use Cases Use Seedance 2.0 ref2v Spicy by ByteDance for reference-guided video, animation, and visual continuity; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Seedance 2.0 ref2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference Guidance:** Uses visual references to steer subjects, style, and scenes for dependable production workflows. * **Video Generation:** Turns concepts into animated clips for rapid iteration across creative and business applications. * **Temporal Coherence:** Maintains subject identity and visual continuity across frames for dependable production workflows. * **Creative Control:** Supports repeatable direction for production-ready concepts for dependable production workflows. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.0-ref2v-spicy)** # Seedance 2.0 t2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.0-t2v Seedance 2.0 t2v by ByteDance is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 2.0 t2v by ByteDance for text-to-video creation, storytelling, and marketing content. > **[Try Seedance 2.0 t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.0-t2v)** # Seedance 2.0 t2v Spicy Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.0-t2v-spicy Seedance 2.0 t2v Spicy by ByteDance is a text-to-video AI model for text-to-video storytelling. Its Spicy variant supports mature and boundary-pushing creative content for production workflows. ### Model Use Cases Use Seedance 2.0 t2v Spicy by ByteDance for text-to-video creation, storytelling, and marketing content; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Seedance 2.0 t2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.0-t2v-spicy)** # Seedance 2.5 i2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.5-i2v Seedance 2.5 i2v by ByteDance is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 2.5 i2v by ByteDance for image animation, camera movement, and cinematic clips. > **[Try Seedance 2.5 i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.5-i2v)** # Seedance 2.5 i2v Spicy Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.5-i2v-spicy Seedance 2.5 i2v Spicy by ByteDance: image-to-video AI for image animation and cinematic video, with mature and boundary-pushing creative content and reliable production control. ### Model Use Cases Use Seedance 2.5 i2v Spicy by ByteDance for image animation, camera movement, and cinematic clips; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Seedance 2.5 i2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.5-i2v-spicy)** # Seedance 2.5 ref2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.5-ref2v Seedance 2.5 ref2v by ByteDance is a reference-to-video AI model for reference-guided video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 2.5 ref2v by ByteDance for reference-guided video, animation, and visual continuity. > **[Try Seedance 2.5 ref2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference Guidance:** Uses visual references to steer subjects, style, and scenes for dependable production workflows. * **Video Generation:** Turns concepts into animated clips for rapid iteration across creative and business applications. * **Temporal Coherence:** Maintains subject identity and visual continuity across frames for dependable production workflows. * **Creative Control:** Supports repeatable direction for production-ready concepts for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.5-ref2v)** # Seedance 2.5 ref2v Spicy Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.5-ref2v-spicy Seedance 2.5 ref2v Spicy by ByteDance is a reference-to-video AI model for reference-guided video. Its Spicy variant supports mature and boundary-pushing creative content for production workflows. ### Model Use Cases Use Seedance 2.5 ref2v Spicy by ByteDance for reference-guided video, animation, and visual continuity; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Seedance 2.5 ref2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference Guidance:** Uses visual references to steer subjects, style, and scenes for dependable production workflows. * **Video Generation:** Turns concepts into animated clips for rapid iteration across creative and business applications. * **Temporal Coherence:** Maintains subject identity and visual continuity across frames for dependable production workflows. * **Creative Control:** Supports repeatable direction for production-ready concepts for dependable production workflows. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.5-ref2v-spicy)** # Seedance 2.5 t2v Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.5-t2v Seedance 2.5 t2v by ByteDance is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedance 2.5 t2v by ByteDance for text-to-video creation, storytelling, and marketing content. > **[Try Seedance 2.5 t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.5-t2v)** # Seedance 2.5 t2v Spicy Source: https://docs.siray.ai/model-apis/bytedance/seedance-2.5-t2v-spicy Seedance 2.5 t2v Spicy by ByteDance is a text-to-video AI model for text-to-video storytelling. Its Spicy variant supports mature and boundary-pushing creative content for production workflows. ### Model Use Cases Use Seedance 2.5 t2v Spicy by ByteDance for text-to-video creation, storytelling, and marketing content; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Seedance 2.5 t2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedance-2.5-t2v-spicy)** # Seedream 4.0 i2i Source: https://docs.siray.ai/model-apis/bytedance/seedream-4.0-i2i Seedream 4.0 i2i by ByteDance is a image editing AI model for image editing and compositing. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedream 4.0 i2i by ByteDance for image editing, compositing, and visual refinement. > **[Try Seedream 4.0 i2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Visual Quality:** Produces refined outputs for creative and production use across creative and business applications. * **Workflow Friendly:** Supports fast iteration across design and marketing tasks across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedream-4.0-i2i)** # Seedream 4.0 ref2i Source: https://docs.siray.ai/model-apis/bytedance/seedream-4.0-ref2i Seedream 4.0 ref2i by ByteDance is a reference-to-image AI model for reference-guided image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedream 4.0 ref2i by ByteDance for reference-guided design, character consistency, and creative assets. > **[Try Seedream 4.0 ref2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference Control:** Uses one or more references to guide the generated image across creative and business applications. * **Visual Consistency:** Preserves key subjects, composition, or style cues across creative and business applications. * **Image Generation:** Creates polished visuals for design and content workflows across creative and business applications. * **Creative Iteration:** Enables rapid variations without restarting from scratch across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedream-4.0-ref2i)** # Seedream 4.0 t2i Source: https://docs.siray.ai/model-apis/bytedance/seedream-4.0-t2i Seedream 4.0 t2i by ByteDance is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedream 4.0 t2i by ByteDance for text-to-image generation, concept art, and marketing visuals. > **[Try Seedream 4.0 t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedream-4.0-t2i)** # Seedream 4.5 i2i Source: https://docs.siray.ai/model-apis/bytedance/seedream-4.5-i2i Seedream 4.5 i2i by ByteDance is a image editing AI model for image editing and compositing. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedream 4.5 i2i by ByteDance for image editing, compositing, and visual refinement. > **[Try Seedream 4.5 i2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Visual Quality:** Produces refined outputs for creative and production use across creative and business applications. * **Workflow Friendly:** Supports fast iteration across design and marketing tasks across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedream-4.5-i2i)** # Seedream 4.5 i2i Spicy Source: https://docs.siray.ai/model-apis/bytedance/seedream-4.5-i2i-spicy Seedream 4.5 i2i Spicy by ByteDance is a image editing AI model for image editing and compositing. Its Spicy variant supports mature and boundary-pushing creative content for production workflows. ### Model Use Cases Use Seedream 4.5 i2i Spicy by ByteDance for image editing, compositing, and visual refinement; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Seedream 4.5 i2i Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Visual Quality:** Produces refined outputs for creative and production use across creative and business applications. * **Workflow Friendly:** Supports fast iteration across design and marketing tasks across creative and business applications. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedream-4.5-i2i-spicy)** # Seedream 4.5 ref2i Source: https://docs.siray.ai/model-apis/bytedance/seedream-4.5-ref2i Seedream 4.5 ref2i by ByteDance is a reference-to-image AI model for reference-guided image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedream 4.5 ref2i by ByteDance for reference-guided design, character consistency, and creative assets. > **[Try Seedream 4.5 ref2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference Control:** Uses one or more references to guide the generated image across creative and business applications. * **Visual Consistency:** Preserves key subjects, composition, or style cues across creative and business applications. * **Image Generation:** Creates polished visuals for design and content workflows across creative and business applications. * **Creative Iteration:** Enables rapid variations without restarting from scratch across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedream-4.5-ref2i)** # Seedream 4.5 ref2i Spicy Source: https://docs.siray.ai/model-apis/bytedance/seedream-4.5-ref2i-spicy Seedream 4.5 ref2i Spicy by ByteDance: reference-to-image AI for reference-guided image generation, with mature and boundary-pushing creative content and reliable production control. ### Model Use Cases Use Seedream 4.5 ref2i Spicy by ByteDance for reference-guided design, character consistency, and creative assets with mature or boundary-pushing creative concepts. > **[Try Seedream 4.5 ref2i Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference Control:** Uses one or more references to guide the generated image across creative and business applications. * **Visual Consistency:** Preserves key subjects, composition, or style cues across creative and business applications. * **Image Generation:** Creates polished visuals for design and content workflows across creative and business applications. * **Creative Iteration:** Enables rapid variations without restarting from scratch across creative and business applications. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedream-4.5-ref2i-spicy)** # Seedream 4.5 t2i Source: https://docs.siray.ai/model-apis/bytedance/seedream-4.5-t2i Seedream 4.5 t2i by ByteDance is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Seedream 4.5 t2i by ByteDance for text-to-image generation, concept art, and marketing visuals. > **[Try Seedream 4.5 t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedream-4.5-t2i)** # Seedream 4.5 t2i Spicy Source: https://docs.siray.ai/model-apis/bytedance/seedream-4.5-t2i-spicy Seedream 4.5 t2i Spicy by ByteDance is a text-to-image AI model for text-to-image generation. Its Spicy variant supports mature and boundary-pushing creative content for production workflows. ### Model Use Cases Use Seedream 4.5 t2i Spicy by ByteDance for text-to-image generation, concept art, and marketing visuals; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Seedream 4.5 t2i Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedream-4.5-t2i-spicy)** # Seedream 5.0 Pro i2i Spicy Source: https://docs.siray.ai/model-apis/bytedance/seedream-5.0-pro-i2i-spicy Seedream 5.0 Pro i2i Spicy by ByteDance is a image editing AI model for image editing and compositing. Its Spicy variant supports mature and boundary-pushing creative content for production workflows. ### Model Use Cases Use Seedream 5.0 Pro i2i Spicy by ByteDance for image editing, compositing, and visual refinement; its Spicy variant supports mature or boundary-pushing creative concepts. > **[Try Seedream 5.0 Pro i2i Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Workflow Friendly:** Supports fast iteration across design and marketing tasks across creative and business applications. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedream-5.0-pro-i2i-spicy)** # Seedream 5.0 Pro t2i Spicy Source: https://docs.siray.ai/model-apis/bytedance/seedream-5.0-pro-t2i-spicy Seedream 5.0 Pro t2i Spicy by ByteDance is a text-to-image AI model for text-to-image generation. Its Spicy variant supports mature and boundary-pushing creative content for production workflows. ### Model Use Cases Use Seedream 5.0 Pro t2i Spicy by ByteDance for text-to-image generation, concept art, and marketing visuals with mature or boundary-pushing creative concepts. > **[Try Seedream 5.0 Pro t2i Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. * **Spicy Variant:** Supports mature and boundary-pushing creative exploration across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/seedream-5.0-pro-t2i-spicy)** # claude-haiku-4-5-20251001 Source: https://docs.siray.ai/model-apis/claude-haiku-4-5-20251001 Anthropic's Claude Haiku 4.5 is the efficient LLM that scales its context window past 200K tokens, ideal for specialized, massive long-context document analysis. ### Model Use Cases This configuration of Anthropic's Claude Haiku 4.5 handles inputs exceeding the 200K token context window. It's tailored for specialized, massive long-context document analysis and retrieval tasks. > **[Try claude-haiku-4-5-20251001 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * Anthropic's Claude Haiku 4.5 is the efficient LLM that scales its context window past 200K tokens, ideal for specialized, massive long-context document analysis. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/claude-haiku-4-5-20251001)** # claude-sonnet-4-5-20250929 Source: https://docs.siray.ai/model-apis/claude-sonnet-4-5-20250929 Claude Sonnet 4.5 delivers enterprise-grade AI performance with enhanced reasoning, safety, and stability for production-ready applications. ### Model Use Cases Ideal for enterprise AI platforms, internal copilots, customer support automation, and knowledge management systems at scale. > **[Try claude-sonnet-4-5-20250929 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Production Stability:** Designed for consistent, high-volume workloads. * **Safety-Focused Design:** Reduced risk in sensitive or regulated use cases. * **Contextual Accuracy:** Maintains intent across long interactions. * **Fast Response Time:** Balances speed with reasoning quality. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/claude-sonnet-4-5-20250929)** # DeepSeek V4 Flash Source: https://docs.siray.ai/model-apis/deepseek/deepseek-v4-flash DeepSeek V4 Flash by DeepSeek is a fast reasoning model for 1M-context agents, coding, and complex analysis. It supports thinking and non-thinking modes for flexible, cost-aware production workflows. ### Model Use Cases Use DeepSeek V4 Flash by DeepSeek for fast coding, long-context analysis, agent automation, structured generation, and cost-aware production workloads. > **[Try DeepSeek V4 Flash on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Fast Inference:** Optimizes responsive generation for cost-aware applications and high-volume workloads. * **1M Context:** Handles long documents, codebases, and multi-step workflows in one context window. * **Flexible Reasoning:** Supports thinking and non-thinking modes for speed or deeper analysis per task. * **Tool Use:** Supports function calls and agent workflows for practical task automation across production systems. * **Structured Output:** Supports JSON-style responses for reliable integrations, automation, and data pipelines. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/deepseek-v4-flash)** # DeepSeek V4 Pro Source: https://docs.siray.ai/model-apis/deepseek/deepseek-v4-pro DeepSeek V4 Pro by DeepSeek is an advanced reasoning model for 1M-context agents, coding, and complex analysis. It delivers world knowledge, reasoning, and tool use for demanding production tasks. ### Model Use Cases Use DeepSeek V4 Pro by DeepSeek for complex reasoning, agentic coding, long-context research, technical analysis, and demanding production automation. > **[Try DeepSeek V4 Pro on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Advanced Reasoning:** Handles complex analysis, planning, mathematics, coding, and multi-step problem solving. * **Agentic Workflows:** Supports capable agents for coding, research, document generation, and task execution. * **World Knowledge:** Provides broad knowledge coverage for research, analysis, and professional workflows. * **1M Context:** Processes long documents, codebases, and extended conversations in one context window. * **Tool Use:** Supports function calls and API integrations for practical workflow automation in production. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/deepseek-v4-pro)** # DeepSeek V4.1 Flash 1017 Source: https://docs.siray.ai/model-apis/deepseek/deepseek-v4.1-flash DeepSeek V4.1 Flash by DeepSeek is a fast reasoning model for 1M-context agents, coding, and complex analysis. It supports thinking and non-thinking modes for flexible, cost-aware production workflows. ### Model Use Cases Use DeepSeek V4.1 Flash 1017 by DeepSeek for fast coding, long-context analysis, agent automation, structured generation, and cost-aware production workloads. > **[Try DeepSeek V4.1 Flash 1017 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Fast Inference:** Optimizes responsive generation for cost-aware applications and high-volume workloads. * **1M Context:** Handles long documents, codebases, and multi-step workflows in one context window. * **Flexible Reasoning:** Supports thinking and non-thinking modes for speed or deeper analysis per task. * **Tool Use:** Supports function calls and agent workflows for practical task automation across production systems. * **Structured Output:** Supports JSON-style responses for reliable integrations, automation, and data pipelines. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/deepseek-v4.1-flash)** # Gemini 2.5 Flash Source: https://docs.siray.ai/model-apis/google/gemini-2.5-flash Gemini 2.5 Flash by Google is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Gemini 2.5 Flash by Google for writing, analysis, automation, and multimodal applications. > **[Try Gemini 2.5 Flash on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gemini-2.5-flash)** # Gemini 2.5 Pro Source: https://docs.siray.ai/model-apis/google/gemini-2.5-pro Gemini 2.5 Pro by Google is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Gemini 2.5 Pro by Google for writing, analysis, automation, and multimodal applications. > **[Try Gemini 2.5 Pro on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gemini-2.5-pro)** # Gemini 3 Flash Preview Source: https://docs.siray.ai/model-apis/google/gemini-3-flash-preview Gemini 3 Flash Preview by Google is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Gemini 3 Flash Preview by Google for writing, analysis, automation, and multimodal applications. > **[Try Gemini 3 Flash Preview on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gemini-3-flash-preview)** # Gemini 3.1 Pro Preview Source: https://docs.siray.ai/model-apis/google/gemini-3.1-pro-preview Gemini 3.1 Pro Preview by Google is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Gemini 3.1 Pro Preview by Google for writing, analysis, automation, and multimodal applications. > **[Try Gemini 3.1 Pro Preview on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gemini-3.1-pro-preview)** # Google Omni 1.1 Flash i2v Source: https://docs.siray.ai/model-apis/google/google-omni-1.1-flash-i2v Google Omni 1.1 Flash i2v by Google is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Google Omni 1.1 Flash by Google for image animation, camera movement, and cinematic clips. > **[Try Google Omni 1.1 Flash i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/google-omni-1.1-flash-i2v)** # Google Omni 1.1 Flash ref2v Source: https://docs.siray.ai/model-apis/google/google-omni-1.1-flash-ref2v Google Omni 1.1 Flash ref2v by Google is a reference-to-video AI model for reference-guided video. It delivers high-quality results for rapid iteration and dependable production workflows. *** For 'extend' task type, the billable duration is calculated based on the `duration` value plus the length of the input video. ### Model Use Cases Use Google Omni 1.1 Flash by Google for reference-guided video, animation, and visual continuity. > **[Try Google Omni 1.1 Flash ref2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference Guidance:** Uses visual references to steer subjects, style, and scenes for dependable production workflows. * **Video Generation:** Turns concepts into animated clips for rapid iteration across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/google-omni-1.1-flash-ref2v)** # Google Omni 1.1 Flash t2v Source: https://docs.siray.ai/model-apis/google/google-omni-1.1-flash-t2v Google Omni 1.1 Flash t2v by Google is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Google Omni 1.1 Flash by Google for text-to-video creation, storytelling, and marketing content. > **[Try Google Omni 1.1 Flash t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/google-omni-1.1-flash-t2v)** # Nano Banana 2 i2i Source: https://docs.siray.ai/model-apis/google/nano-banana-2-i2i Nano Banana 2 i2i by Google is a image editing AI model for image editing and compositing. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Nano Banana 2 i2i by Google for image editing, compositing, and visual refinement. > **[Try Nano Banana 2 i2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Visual Quality:** Produces refined outputs for creative and production use across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/nano-banana-2-i2i)** # Nano Banana 2 Lite Edit Source: https://docs.siray.ai/model-apis/google/nano-banana-2-lite-edit Nano Banana 2 Lite Edit by Google is a image editing AI model for image editing and compositing. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Nano Banana 2 Lite Edit by Google for image editing, compositing, and visual refinement. > **[Try Nano Banana 2 Lite Edit on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Visual Quality:** Produces refined outputs for creative and production use across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/nano-banana-2-lite-edit)** # Nano Banana 2 Lite t2i Source: https://docs.siray.ai/model-apis/google/nano-banana-2-lite-t2i Nano Banana 2 Lite t2i by Google is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Nano Banana 2 Lite t2i by Google for text-to-image generation, concept art, and marketing visuals. > **[Try Nano Banana 2 Lite t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/nano-banana-2-lite-t2i)** # Nano Banana 2 t2i Source: https://docs.siray.ai/model-apis/google/nano-banana-2-t2i Nano Banana 2 t2i by Google is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Nano Banana 2 t2i by Google for text-to-image generation, concept art, and marketing visuals. > **[Try Nano Banana 2 t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/nano-banana-2-t2i)** # Nano Banana 2.1 i2i Source: https://docs.siray.ai/model-apis/google/nano-banana-2.1-i2i Nano Banana 2.1 i2i by Google is a image editing AI model for image editing and compositing. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Nano Banana 2.1 i2i by Google for image editing, compositing, and visual refinement. > **[Try Nano Banana 2.1 i2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Visual Quality:** Produces refined outputs for creative and production use across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/nano-banana-2.1-i2i)** # Nano Banana 2.1 t2i Source: https://docs.siray.ai/model-apis/google/nano-banana-2.1-t2i Nano Banana 2.1 t2i by Google is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Nano Banana 2.1 t2i by Google for text-to-image generation, concept art, and marketing visuals. > **[Try Nano Banana 2.1 t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/nano-banana-2.1-t2i)** # Nano Banana i2i Source: https://docs.siray.ai/model-apis/google/nano-banana-i2i Nano Banana i2i by Google is a image editing AI model for image editing and compositing. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Nano Banana i2i by Google for image editing, compositing, and visual refinement. > **[Try Nano Banana i2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Visual Quality:** Produces refined outputs for creative and production use across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/nano-banana-i2i)** # Nano Banana Pro i2i Source: https://docs.siray.ai/model-apis/google/nano-banana-pro-i2i Nano Banana Pro i2i by Google is a image editing AI model for image editing and compositing. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Nano Banana Pro i2i by Google for image editing, compositing, and visual refinement. > **[Try Nano Banana Pro i2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/nano-banana-pro-i2i)** # Nano Banana Pro t2i Source: https://docs.siray.ai/model-apis/google/nano-banana-pro-t2i Nano Banana Pro t2i by Google is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Nano Banana Pro t2i by Google for text-to-image generation, concept art, and marketing visuals. > **[Try Nano Banana Pro t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/nano-banana-pro-t2i)** # Nano Banana t2i Source: https://docs.siray.ai/model-apis/google/nano-banana-t2i Nano Banana t2i by Google is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use Nano Banana t2i by Google for text-to-image generation, concept art, and marketing visuals. > **[Try Nano Banana t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/nano-banana-t2i)** # Veo 3.1 i2v Source: https://docs.siray.ai/model-apis/google/veo-3.1-i2v Veo 3.1 i2v by Google is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Veo 3.1 i2v by Google for image animation, camera movement, and cinematic clips. > **[Try Veo 3.1 i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/veo-3.1-i2v)** # Veo 3.1 t2v Source: https://docs.siray.ai/model-apis/google/veo-3.1-t2v Veo 3.1 t2v by Google is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use Veo 3.1 t2v by Google for text-to-video creation, storytelling, and marketing content. > **[Try Veo 3.1 t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/veo-3.1-t2v)** # Kling 2.6 Motion Control Source: https://docs.siray.ai/model-apis/kuaishou/kling-2.6-motion-control Kling 2.6 Motion Control by Kuaishou is a video motion-control AI model for motion control and animation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Kling 2.6 Motion Control by Kuaishou for directed motion, choreography, and video control. > **[Try Kling 2.6 Motion Control on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Motion Control:** Directs movement, poses, or camera action from user inputs for dependable production workflows. * **Temporal Coherence:** Keeps motion stable across frames for smoother clips across creative and business applications. * **Creative Direction:** Enables repeatable choreography and visual storytelling across creative and business applications. * **Video Production:** Fits animation, advertising, and controlled content workflows for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/kling-2.6-motion-control)** # Kling 2.6 Pro i2v Source: https://docs.siray.ai/model-apis/kuaishou/kling-2.6-pro-i2v Kling 2.6 Pro i2v by Kuaishou is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Kling 2.6 Pro i2v by Kuaishou for image animation, camera movement, and cinematic clips. > **[Try Kling 2.6 Pro i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/kling-2.6-pro-i2v)** # Kling 2.6 Pro Motion Control Source: https://docs.siray.ai/model-apis/kuaishou/kling-2.6-pro-motion-control Kling 2.6 Pro Motion Control by Kuaishou is a video motion-control AI model for motion control and animation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Kling 2.6 Pro Motion Control by Kuaishou for directed motion, choreography, and video control. > **[Try Kling 2.6 Pro Motion Control on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Motion Control:** Directs movement, poses, or camera action from user inputs for dependable production workflows. * **Temporal Coherence:** Keeps motion stable across frames for smoother clips across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Video Production:** Fits animation, advertising, and controlled content workflows for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/kling-2.6-pro-motion-control)** # Kling 2.6 Pro t2v Source: https://docs.siray.ai/model-apis/kuaishou/kling-2.6-pro-t2v Kling 2.6 Pro t2v by Kuaishou is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Kling 2.6 Pro t2v by Kuaishou for text-to-video creation, storytelling, and marketing content. > **[Try Kling 2.6 Pro t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/kling-2.6-pro-t2v)** # Kling 3 Motion Control Source: https://docs.siray.ai/model-apis/kuaishou/kling-3-motion-control Kling 3 Motion Control by Kuaishou is a video motion-control AI model for motion control and animation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Kling 3 Motion Control by Kuaishou for directed motion, choreography, and video control. > **[Try Kling 3 Motion Control on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Motion Control:** Directs movement, poses, or camera action from user inputs for dependable production workflows. * **Temporal Coherence:** Keeps motion stable across frames for smoother clips across creative and business applications. * **Creative Direction:** Enables repeatable choreography and visual storytelling across creative and business applications. * **Video Production:** Fits animation, advertising, and controlled content workflows for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/kling-3-motion-control)** # Kling 3.0 i2v Source: https://docs.siray.ai/model-apis/kuaishou/kling-3.0-i2v Kling 3.0 i2v by Kuaishou is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Kling 3.0 i2v by Kuaishou for image animation, camera movement, and cinematic clips. > **[Try Kling 3.0 i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/kling-3.0-i2v)** # Kling 3.0 t2v Source: https://docs.siray.ai/model-apis/kuaishou/kling-3.0-t2v Kling 3.0 t2v by Kuaishou is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Kling 3.0 t2v by Kuaishou for text-to-video creation, storytelling, and marketing content. > **[Try Kling 3.0 t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/kling-3.0-t2v)** # LTX 2.3 22B i2v Source: https://docs.siray.ai/model-apis/lightricks/ltx-2.3-22b-i2v LTX 2.3 22B i2v by Lightricks is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use LTX 2.3 22B i2v by Lightricks for image animation, camera movement, and cinematic clips. > **[Try LTX 2.3 22B i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/ltx-2.3-22b-i2v)** # LTX 2.3 22B t2v Source: https://docs.siray.ai/model-apis/lightricks/ltx-2.3-22b-t2v LTX 2.3 22B t2v by Lightricks is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use LTX 2.3 22B t2v by Lightricks for text-to-video creation, storytelling, and marketing content. > **[Try LTX 2.3 22B t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/ltx-2.3-22b-t2v)** # Midjourney Niji 6 t2i Source: https://docs.siray.ai/model-apis/midjourney/midjourney-niji-6-t2i Midjourney Niji 6 t2i by Midjourney is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Midjourney Niji 6 t2i by Midjourney for text-to-image generation, concept art, and marketing visuals. > **[Try Midjourney Niji 6 t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/midjourney-niji-6-t2i)** # Midjourney Niji 7 t2i Source: https://docs.siray.ai/model-apis/midjourney/midjourney-niji-7-t2i Midjourney Niji 7 t2i by Midjourney is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Midjourney Niji 7 t2i by Midjourney for text-to-image generation, concept art, and marketing visuals. > **[Try Midjourney Niji 7 t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/midjourney-niji-7-t2i)** # Midjourney V6 t2i Source: https://docs.siray.ai/model-apis/midjourney/midjourney-v6-t2i Midjourney V6 t2i by Midjourney is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Midjourney V6 t2i by Midjourney for text-to-image generation, concept art, and marketing visuals. > **[Try Midjourney V6 t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/midjourney-v6-t2i)** # Midjourney V6.1 t2i Source: https://docs.siray.ai/model-apis/midjourney/midjourney-v6.1-t2i Midjourney V6.1 t2i by Midjourney is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Midjourney V6.1 t2i by Midjourney for text-to-image generation, concept art, and marketing visuals. > **[Try Midjourney V6.1 t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/midjourney-v6.1-t2i)** # Midjourney V7 t2i Source: https://docs.siray.ai/model-apis/midjourney/midjourney-v7-t2i Midjourney V7 t2i by Midjourney is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Midjourney V7 t2i by Midjourney for text-to-image generation, concept art, and marketing visuals. > **[Try Midjourney V7 t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/midjourney-v7-t2i)** # Midjourney V8.2 t2i Source: https://docs.siray.ai/model-apis/midjourney/midjourney-v8.2-t2i Midjourney V8.2 t2i by Midjourney is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Midjourney V8.2 t2i by Midjourney for text-to-image generation, concept art, and marketing visuals. > **[Try Midjourney V8.2 t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/midjourney-v8.2-t2i)** # MiniMax H3 i2v Source: https://docs.siray.ai/model-apis/minimax/minimax-h3-i2v MiniMax H3 i2v by MiniMax is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use MiniMax H3 i2v by MiniMax for image animation, camera movement, and cinematic clips. > **[Try MiniMax H3 i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/minimax-h3-i2v)** # MiniMax H3 i2v Spicy Source: https://docs.siray.ai/model-apis/minimax/minimax-h3-i2v-spicy MiniMax H3 i2v by MiniMax is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use MiniMax H3 i2v by MiniMax for image animation, camera movement, and cinematic clips. > **[Try MiniMax H3 i2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/minimax-h3-i2v-spicy)** # MiniMax H3 ref2v Source: https://docs.siray.ai/model-apis/minimax/minimax-h3-ref2v MiniMax H3 ref2v by MiniMax is a reference-to-video AI model for reference-guided video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use MiniMax H3 ref2v by MiniMax for reference-guided video, animation, and visual continuity. > **[Try MiniMax H3 ref2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference Guidance:** Uses visual references to steer subjects, style, and scenes for dependable production workflows. * **Video Generation:** Turns concepts into animated clips for rapid iteration across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/minimax-h3-ref2v)** # MiniMax H3 ref2v Spicy Source: https://docs.siray.ai/model-apis/minimax/minimax-h3-ref2v-spicy MiniMax H3 ref2v by MiniMax is a reference-to-video AI model for reference-guided video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use MiniMax H3 ref2v by MiniMax for reference-guided video, animation, and visual continuity. > **[Try MiniMax H3 ref2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Reference Guidance:** Uses visual references to steer subjects, style, and scenes for dependable production workflows. * **Video Generation:** Turns concepts into animated clips for rapid iteration across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/minimax-h3-ref2v-spicy)** # MiniMax H3 t2v Source: https://docs.siray.ai/model-apis/minimax/minimax-h3-t2v MiniMax H3 t2v by MiniMax is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use MiniMax H3 t2v by MiniMax for text-to-video creation, storytelling, and marketing content. > **[Try MiniMax H3 t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/minimax-h3-t2v)** # MiniMax H3 t2v Spicy Source: https://docs.siray.ai/model-apis/minimax/minimax-h3-t2v-spicy MiniMax H3 t2v by MiniMax is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use MiniMax H3 t2v by MiniMax for text-to-video creation, storytelling, and marketing content. > **[Try MiniMax H3 t2v Spicy on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Professional Quality:** Targets demanding creative and production use cases across creative and business applications. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/minimax-h3-t2v-spicy)** # Kimi K3 Source: https://docs.siray.ai/model-apis/moonshotai/kimi-k3 Kimi K3 by Moonshot AI is a native multimodal reasoning model for long-horizon coding, agents, and knowledge work. Its long-context understanding and tool use support complex end-to-end tasks. ### Model Use Cases Use Kimi K3 by Moonshot AI for long-horizon coding, visual understanding, agent orchestration, research, and end-to-end knowledge work. > **[Try Kimi K3 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Native Vision:** Understands visual inputs alongside text for multimodal analysis and agent workflows. * **Long-Context Reasoning:** Maintains context across extended documents, codebases, and complex multi-step tasks. * **Long-Horizon Coding:** Supports planning, implementation, debugging, and verification across software projects. * **Agentic Tool Use:** Works with tool calls and structured interactions for autonomous task execution. * **Always-On Thinking:** Uses persistent reasoning to support deeper analysis, planning, and complex decisions. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/kimi-k3)** # GPT 4.1 Source: https://docs.siray.ai/model-apis/openai/gpt-4.1 GPT 4.1 by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use GPT 4.1 by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT 4.1 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-4.1)** # GPT 4.1 Mini Source: https://docs.siray.ai/model-apis/openai/gpt-4.1-mini GPT 4.1 Mini by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use GPT 4.1 Mini by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT 4.1 Mini on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-4.1-mini)** # GPT 4o Source: https://docs.siray.ai/model-apis/openai/gpt-4o GPT 4o by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use GPT 4o by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT 4o on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-4o)** # GPT 4o mini Source: https://docs.siray.ai/model-apis/openai/gpt-4o-mini GPT 4o mini by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use GPT 4o mini by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT 4o mini on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-4o-mini)** # GPT 5 Nano Source: https://docs.siray.ai/model-apis/openai/gpt-5-nano GPT 5 Nano by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use GPT 5 Nano by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT 5 Nano on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-5-nano)** # GPT 5.2 Source: https://docs.siray.ai/model-apis/openai/gpt-5.2 GPT 5.2 by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use GPT 5.2 by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT 5.2 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-5.2)** # GPT 5.4 Source: https://docs.siray.ai/model-apis/openai/gpt-5.4 GPT 5.4 by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use GPT 5.4 by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT 5.4 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-5.4)** # GPT 5.4 Mini Source: https://docs.siray.ai/model-apis/openai/gpt-5.4-mini GPT 5.4 Mini by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use GPT 5.4 Mini by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT 5.4 Mini on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Efficient Inference:** Designed for responsive, cost-aware production workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-5.4-mini)** # GPT 5.5 Source: https://docs.siray.ai/model-apis/openai/gpt-5.5 GPT 5.5 by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use GPT 5.5 by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT 5.5 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-5.5)** # GPT 6 Astra Source: https://docs.siray.ai/model-apis/openai/gpt-6-astra GPT 6 Astra by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use GPT 6 by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT 6 Astra on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-6-astra)** # GPT 6 Luna Source: https://docs.siray.ai/model-apis/openai/gpt-6-luna GPT 6 Luna by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use GPT 6 Luna by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT 6 Luna on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-6-luna)** # GPT 6.1 Sol Source: https://docs.siray.ai/model-apis/openai/gpt-6.1-sol GPT 6.1 Sol by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use GPT 6.1 Sol by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT 6.1 Sol on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-6.1-sol)** # GPT Image 2 Edit Source: https://docs.siray.ai/model-apis/openai/gpt-image-2-edit GPT Image 2 Edit by OpenAI is a image editing AI model for image editing and compositing. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use GPT Image 2 Edit by OpenAI for image editing, compositing, and visual refinement. > **[Try GPT Image 2 Edit on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Visual Quality:** Produces refined outputs for creative and production use across creative and business applications. * **Workflow Friendly:** Supports fast iteration across design and marketing tasks across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-image-2-edit)** # GPT Image 2 t2i Source: https://docs.siray.ai/model-apis/openai/gpt-image-2-t2i GPT Image 2 t2i by OpenAI is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use GPT Image 2 t2i by OpenAI for text-to-image generation, concept art, and marketing visuals. > **[Try GPT Image 2 t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-image-2-t2i)** # GPT Image 2.5 Flare Edit Source: https://docs.siray.ai/model-apis/openai/gpt-image-2.5-flare-edit GPT Image 2.5 Flare Edit by OpenAI is a image editing AI model for image editing and compositing. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use GPT Image 2.5 Edit by OpenAI for image editing, compositing, and visual refinement. > **[Try GPT Image 2.5 Flare Edit on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Visual Quality:** Produces refined outputs for creative and production use across creative and business applications. * **Workflow Friendly:** Supports fast iteration across design and marketing tasks across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-image-2.5-flare-edit)** # GPT Image 2.5 Flare t2i Source: https://docs.siray.ai/model-apis/openai/gpt-image-2.5-flare-t2i GPT Image 2.5 Flare t2i by OpenAI is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use GPT Image 2.5 t2i by OpenAI for text-to-image generation, concept art, and marketing visuals. > **[Try GPT Image 2.5 Flare t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-image-2.5-flare-t2i)** # GPT Image 2.5 Sunburst Edit Source: https://docs.siray.ai/model-apis/openai/gpt-image-2.5-sunburst-edit GPT Image 2.5 Sunburst Edit by OpenAI is a image editing AI model for image editing and compositing. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use GPT Image 2.5 Edit by OpenAI for image editing, compositing, and visual refinement. > **[Try GPT Image 2.5 Sunburst Edit on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Visual Quality:** Produces refined outputs for creative and production use across creative and business applications. * **Workflow Friendly:** Supports fast iteration across design and marketing tasks across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-image-2.5-sunburst-edit)** # GPT Image 2.5 Sunburst t2i Source: https://docs.siray.ai/model-apis/openai/gpt-image-2.5-sunburst-t2i GPT Image 2.5 Sunburst t2i by OpenAI is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration, dependable production workflows, and scalable AI applications. ### Model Use Cases Use GPT Image 2.5 t2i by OpenAI for text-to-image generation, concept art, and marketing visuals. > **[Try GPT Image 2.5 Sunburst t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-image-2.5-sunburst-t2i)** # GPT oss 20b Source: https://docs.siray.ai/model-apis/openai/gpt-oss-20b GPT oss 20b by OpenAI is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use GPT oss 20b by OpenAI for writing, analysis, automation, and multimodal applications. > **[Try GPT oss 20b on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/gpt-oss-20b)** # PixVerse C1 i2v Source: https://docs.siray.ai/model-apis/pixverse/pixverse-c1-i2v PixVerse C1 i2v by PixVerse is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use PixVerse C1 i2v by PixVerse for image animation, camera movement, and cinematic clips. > **[Try PixVerse C1 i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/pixverse-c1-i2v)** # PixVerse C1 t2v Source: https://docs.siray.ai/model-apis/pixverse/pixverse-c1-t2v PixVerse C1 t2v by PixVerse is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use PixVerse C1 t2v by PixVerse for text-to-video creation, storytelling, and marketing content. > **[Try PixVerse C1 t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/pixverse-c1-t2v)** # PixVerse V5.6 i2v Source: https://docs.siray.ai/model-apis/pixverse/pixverse-v5.6-i2v PixVerse V5.6 i2v by PixVerse is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use PixVerse V5.6 i2v by PixVerse for image animation, camera movement, and cinematic clips. > **[Try PixVerse V5.6 i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/pixverse-v5.6-i2v)** # PixVerse V5.6 t2v Source: https://docs.siray.ai/model-apis/pixverse/pixverse-v5.6-t2v PixVerse V5.6 t2v by PixVerse is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use PixVerse V5.6 t2v by PixVerse for text-to-video creation, storytelling, and marketing content. > **[Try PixVerse V5.6 t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/pixverse-v5.6-t2v)** # PixVerse V6 i2v Source: https://docs.siray.ai/model-apis/pixverse/pixverse-v6-i2v PixVerse V6 i2v by PixVerse is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use PixVerse V6 i2v by PixVerse for image animation, camera movement, and cinematic clips. > **[Try PixVerse V6 i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/pixverse-v6-i2v)** # PixVerse V6 t2v Source: https://docs.siray.ai/model-apis/pixverse/pixverse-v6-t2v PixVerse V6 t2v by PixVerse is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use PixVerse V6 t2v by PixVerse for text-to-video creation, storytelling, and marketing content. > **[Try PixVerse V6 t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/pixverse-v6-t2v)** # Hunyuan Image 3 Instruct i2i Source: https://docs.siray.ai/model-apis/tencent/hunyuan-image-3-instruct-i2i Hunyuan Image 3 Instruct i2i by Tencent is a image editing AI model for image editing and compositing. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Hunyuan Image 3 Instruct i2i by Tencent for image editing, compositing, and visual refinement. > **[Try Hunyuan Image 3 Instruct i2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Editing:** Transforms, retouches, or recomposes images with instructions for dependable production workflows. * **Prompt Control:** Applies targeted changes while following natural-language intent for fast, repeatable AI workflows. * **Visual Quality:** Produces refined outputs for creative and production use across creative and business applications. * **Workflow Friendly:** Supports fast iteration across design and marketing tasks across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/hunyuan-image-3-instruct-i2i)** # Hunyuan Image 3 Instruct t2i Source: https://docs.siray.ai/model-apis/tencent/hunyuan-image-3-instruct-t2i Hunyuan Image 3 Instruct t2i by Tencent is a text-to-image AI model for text-to-image generation. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Hunyuan Image 3 Instruct t2i by Tencent for text-to-image generation, concept art, and marketing visuals. > **[Try Hunyuan Image 3 Instruct t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image:** Creates visuals from natural-language prompts and concepts for dependable production workflows. * **Prompt Adherence:** Follows composition, subject, and style instructions closely for dependable production workflows. * **Visual Quality:** Delivers polished imagery for creative production workflows for dependable production workflows. * **Rapid Ideation:** Accelerates concept art, campaigns, and design exploration for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/hunyuan-image-3-instruct-t2i)** # Hunyuan3d V2.5 Rapid image-to-3d Source: https://docs.siray.ai/model-apis/tencent/hunyuan3d-v2.5-rapid-image-to-3d Hunyuan3d V2.5 Rapid image-to-3d by Tencent is a 3D generation AI model for 3D assets and visualization. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Hunyuan3d V2.5 Rapid image-to-3d by Tencent for 3D assets, product visualization, and game development. > **[Try Hunyuan3d V2.5 Rapid image-to-3d on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **3D Asset Creation:** Generates usable 3D content from text or image references across creative and business applications. * **Reference Guidance:** Preserves important shapes, materials, and visual cues across creative and business applications. * **Rapid Prototyping:** Speeds concept exploration for games, products, and design for dependable production workflows. * **Production Workflows:** Supports asset iteration for visualization and content teams for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/hunyuan3d-v2.5-rapid-image-to-3d)** # Hunyuan3d V2.5 Rapid text-to-3d Source: https://docs.siray.ai/model-apis/tencent/hunyuan3d-v2.5-rapid-text-to-3d Hunyuan3d V2.5 Rapid text-to-3d by Tencent is a 3D generation AI model for 3D assets and visualization. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Hunyuan3d V2.5 Rapid text-to-3d by Tencent for 3D assets, product visualization, and game development. > **[Try Hunyuan3d V2.5 Rapid text-to-3d on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **3D Asset Creation:** Generates usable 3D content from text or image references across creative and business applications. * **Reference Guidance:** Preserves important shapes, materials, and visual cues across creative and business applications. * **Rapid Prototyping:** Speeds concept exploration for games, products, and design for dependable production workflows. * **Production Workflows:** Supports asset iteration for visualization and content teams for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/hunyuan3d-v2.5-rapid-text-to-3d)** # Tripo3D V2.5 image-to-3d Source: https://docs.siray.ai/model-apis/tripo/tripo3d-v2.5-image-to-3d Tripo3D V2.5 image-to-3d by Tripo AI is a 3D generation AI model for 3D assets and visualization. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Tripo3D V2.5 image-to-3d by Tripo AI for 3D assets, product visualization, and game development. > **[Try Tripo3D V2.5 image-to-3d on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **3D Asset Creation:** Generates usable 3D content from text or image references across creative and business applications. * **Reference Guidance:** Preserves important shapes, materials, and visual cues across creative and business applications. * **Rapid Prototyping:** Speeds concept exploration for games, products, and design for dependable production workflows. * **Production Workflows:** Supports asset iteration for visualization and content teams for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/tripo3d-v2.5-image-to-3d)** # Vidu Q2-pro-fast i2v Source: https://docs.siray.ai/model-apis/vidu/vidu-q2-pro-fast-i2v Vidu Q2-pro-fast i2v by ShengShu Technology: image-to-video AI for image animation and cinematic video, built for high-quality outputs, reliable control, and scalable production use. ### Model Use Cases Use Vidu Q2-pro-fast i2v by ShengShu Technology for image animation, camera movement, and cinematic clips. > **[Try Vidu Q2-pro-fast i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/vidu-q2-pro-fast-i2v)** # Vidu Q2-pro i2v Source: https://docs.siray.ai/model-apis/vidu/vidu-q2-pro-i2v Vidu Q2-pro i2v by ShengShu Technology is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Vidu Q2-pro i2v by ShengShu Technology for image animation, camera movement, and cinematic clips. > **[Try Vidu Q2-pro i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/vidu-q2-pro-i2v)** # Vidu Q2-pro se2v Source: https://docs.siray.ai/model-apis/vidu/vidu-q2-pro-se2v Vidu Q2-pro se2v by ShengShu Technology: start/end-frame-to-video AI for controlled video transitions, built for high-quality outputs, reliable control, and scalable production use. ### Model Use Cases Use Vidu Q2-pro se2v by ShengShu Technology for transitions, story beats, and controlled animation. > **[Try Vidu Q2-pro se2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Frame Guidance:** Uses starting and ending frames to shape the generated transition for fast, repeatable AI workflows. * **Controlled Animation:** Creates directed movement between defined visual states across creative and business applications. * **Temporal Coherence:** Produces smoother frame-to-frame progression across creative and business applications. * **Story Beats:** Helps visualize transitions, scenes, and narrative moments for dependable production workflows. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/vidu-q2-pro-se2v)** # Vidu Q2 t2v Source: https://docs.siray.ai/model-apis/vidu/vidu-q2-t2v Vidu Q2 t2v by ShengShu Technology is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Vidu Q2 t2v by ShengShu Technology for text-to-video creation, storytelling, and marketing content. > **[Try Vidu Q2 t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/vidu-q2-t2v)** # Vidu Q3-pro i2v Source: https://docs.siray.ai/model-apis/vidu/vidu-q3-pro-i2v Vidu Q3-pro i2v by ShengShu Technology is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Vidu Q3-pro i2v by ShengShu Technology for image animation, camera movement, and cinematic clips. > **[Try Vidu Q3-pro i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/vidu-q3-pro-i2v)** # Vidu Q3-pro t2v Source: https://docs.siray.ai/model-apis/vidu/vidu-q3-pro-t2v Vidu Q3-pro t2v by ShengShu Technology is a text-to-video AI model for text-to-video storytelling. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Vidu Q3-pro t2v by ShengShu Technology for text-to-video creation, storytelling, and marketing content. > **[Try Vidu Q3-pro t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video:** Generates animated scenes from natural-language prompts across creative and business applications. * **Cinematic Motion:** Builds camera movement, action, and atmosphere into clips across creative and business applications. * **Prompt Control:** Translates scene descriptions into directed visual results for dependable production workflows. * **Creative Production:** Accelerates storytelling, advertising, and social content across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/vidu-q3-pro-t2v)** # Vidu Q4 i2v Source: https://docs.siray.ai/model-apis/vidu/vidu-q4-i2v Vidu Q4 i2v by ShengShu Technology is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Vidu Q3-pro i2v by ShengShu Technology for image animation, camera movement, and cinematic clips. > **[Try Vidu Q4 i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/vidu-q4-i2v)** # Vidu Q4 ref2v Source: https://docs.siray.ai/model-apis/vidu/vidu-q4-ref2v Vidu Q4 ref2v by ShengShu Technology is a image-to-video AI model for image animation and cinematic video. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use Vidu Q3-pro i2v by ShengShu Technology for image animation, camera movement, and cinematic clips. > **[Try Vidu Q4 ref2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Animation:** Turns still images into expressive, moving video clips across creative and business applications. * **Camera Motion:** Adds pans, zooms, and cinematic movement from prompts across creative and business applications. * **Subject Consistency:** Keeps the main subject recognizable throughout the clip across creative and business applications. * **Fast Iteration:** Supports social, marketing, and creative video workflows across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/vidu-q4-ref2v)** # Grok 4.1 Fast Non Reasoning Source: https://docs.siray.ai/model-apis/x-ai/grok-4.1-fast-non-reasoning xAI's speed demon variant, delivering instant responses for casual chat, content creation, and simple queries without visible reasoning steps. ### Model Use Cases Good to build real-time chatbots, customer support agents, mobile assistants, content generation tools, or any high-volume application where speed and cost matter more than visible reasoning steps. > **[Try Grok 4.1 Fast Non Reasoning on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Ideal for Creative & Casual Use:** Excels at writing, brainstorming, humor & general conversation. * **Full 256K Context at Max Speed:** Keeps long memory while prioritizing instant output. * **Seamless Integration:** Powers customer support bots, mobile apps & quick lookups effortlessly. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/grok-4.1-fast-non-reasoning)** # Grok 4.1 Fast Reasoning Source: https://docs.siray.ai/model-apis/x-ai/grok-4.1-fast-reasoning xAI's cutting-edge AI model launched in 2025, optimized for lightning-fast logical analysis, multi-step problem solving, and advanced reasoning tasks with top-tier accuracy. ### Model Use Cases Grok 4.1 fast reasoning is best for researchers, developers, and analysts tackling hard technical problems, competitive programming, scientific modeling, or any task requiring deep, verifiable reasoning under time pressure. > **[Try Grok 4.1 Fast Reasoning on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Ultra-Fast Reasoning Engine:** Solves complex math, science & coding problems in seconds with full depth. * **256K Context Window:** Reasons over massive documents or codebases without losing details. * **Advanced Tool Use:** Masters browsing, code execution & function calling with rapid, accurate logic. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/grok-4.1-fast-reasoning)** # Grok Imagine Image i2i Source: https://docs.siray.ai/model-apis/x-ai/grok-imagine-image-i2i Grok Imagine Image i2i is xAI's image-to-image model for creative image transformation. Edit and restyle images with Grok's distinctive AI capabilities and unique visual approach. ### Model Use Cases Transform photos, restyle artwork, or enhance visuals with xAI's Grok-powered image editing delivering creative and expressive image transformations. > **[Try Grok Imagine Image i2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image Transformation:** Edit and restyle existing images with AI guidance. * **Grok AI Engine:** Powered by xAI's advanced Grok model architecture. * **Creative Style Transfer:** Apply unique artistic styles to input images. * **Source Preservation:** Maintains key elements while applying edits. * **Flexible Control:** Adjustable transformation strength and style. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/grok-imagine-image-i2i)** # Grok Imagine Image t2i Source: https://docs.siray.ai/model-apis/x-ai/grok-imagine-image-t2i Grok Imagine Image t2i is xAI's text-to-image model for creative image generation. Create unique visuals from text prompts with Grok's distinctive AI style and artistic flair. ### Model Use Cases Generate original images for creative projects, social media, or marketing content directly from text descriptions using xAI's Grok-powered image generation. > **[Try Grok Imagine Image t2i on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Image Generation:** Create images directly from natural language prompts. * **Grok AI Engine:** Powered by xAI's advanced Grok model architecture. * **Distinctive Visual Style:** Unique aesthetic with creative artistic output. * **Strong Prompt Adherence:** Accurately interprets detailed scene descriptions. * **High-Quality Output:** Produces detailed, visually appealing images. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/grok-imagine-image-t2i)** # Grok Imagine Video Extension Source: https://docs.siray.ai/model-apis/x-ai/grok-imagine-video-extension Grok Imagine Video Extension is xAI's video extension model for seamlessly extending existing videos. Expand video duration with coherent continuation powered by Grok AI technology. ### Model Use Cases Extend short video clips, continue animations, or add additional footage to existing videos with smooth, context-aware continuation maintaining visual consistency. > **[Try Grok Imagine Video Extension on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Video Extension:** Seamlessly extend existing videos with new content. * **Context-Aware Continuation:** Understands video context for coherent extensions. * **Grok AI Engine:** Powered by xAI's advanced Grok model architecture. * **Visual Consistency:** Maintains style and motion across extended frames. * **Flexible Duration:** Extend videos by customizable time increments. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/grok-imagine-video-extension)** # Grok Imagine Video i2v Source: https://docs.siray.ai/model-apis/x-ai/grok-imagine-video-i2v Grok Imagine Video i2v is xAI's image-to-video model for dynamic video generation. Transform static images into engaging video sequences with Grok's creative AI capabilities. ### Model Use Cases Animate images for social content, marketing videos, or creative projects with xAI's Grok-powered video generation delivering unique and expressive motion output. > **[Try Grok Imagine Video i2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Image-to-Video Generation:** Transform still images into dynamic video content. * **Grok AI Engine:** Powered by xAI's advanced Grok model architecture. * **Creative Motion Synthesis:** Generates expressive, engaging movement from stills. * **Source Fidelity:** Preserves key visual elements from input images. * **Versatile Output:** Suitable for social media, marketing, and creative use. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/grok-imagine-video-i2v)** # Grok Imagine Video t2v Source: https://docs.siray.ai/model-apis/x-ai/grok-imagine-video-t2v Grok Imagine Video t2v is xAI's text-to-video model for creative video generation. Create dynamic videos from text prompts with Grok's unique AI personality and visual style. ### Model Use Cases Generate original video content for social media, creative projects, or marketing campaigns directly from text descriptions using xAI's Grok-powered video engine. > **[Try Grok Imagine Video t2v on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Text-to-Video Generation:** Create videos directly from natural language prompts. * **Grok AI Engine:** Powered by xAI's advanced Grok model architecture. * **Creative Visual Style:** Distinctive aesthetic with expressive video output. * **Strong Prompt Following:** Accurately interprets scene and action descriptions. * **Engaging Motion Quality:** Produces dynamic, attention-grabbing video content. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/grok-imagine-video-t2v)** # MiMo V2 Flash Source: https://docs.siray.ai/model-apis/xiaomi/mimo-v2-flash MiMo V2 Flash by Xiaomi is a multimodal language AI model for multimodal AI applications. It delivers high-quality results for rapid iteration and dependable production workflows. ### Model Use Cases Use MiMo V2 Flash by Xiaomi for writing, analysis, automation, and multimodal applications. > **[Try MiMo V2 Flash on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Multimodal Understanding:** Works across text and supported visual inputs across creative and business applications. * **Instruction Following:** Produces focused responses for complex user requests across creative and business applications. * **Content Generation:** Creates useful text, summaries, plans, and structured output for dependable production workflows. * **Business Workflows:** Supports analysis, automation, research, and productivity across creative and business applications. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/mimo-v2-flash)** # GLM 4.6V Flash Source: https://docs.siray.ai/model-apis/z-ai/glm-4.6v-flash GLM 4.6V Flash is a high-speed multimodal model designed for instant reasoning, image understanding, and lightweight workloads. It delivers fast responses while keeping accuracy and context handling reliable. ### Model Use Cases Ideal for real-time assistants, rapid image Q\&A, quick product tagging, and lightweight data tasks. Works well for chatbots, support tools, and batch labeling workflows. > **[Try GLM 4.6V Flash on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Lightning-fast inference:** Optimized for quick replies without sacrificing clarity. * **Strong visual understanding:** Reads images, screenshots, and diagrams with solid accuracy. * **Efficient for high-volume tasks:** Handles bulk queries and lightweight processing with minimal latency. * **Context-aware reasoning:** Maintains conversation flow and interprets follow-up questions smoothly. * **Low-resource friendly:** Works well in environments that require speed and reduced compute load. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/glm-4.6v-flash)** # GLM 4.7 Source: https://docs.siray.ai/model-apis/z-ai/glm-4.7 GLM 4.7 is a powerful multimodal large language model designed for fast reasoning, high-quality generation, and reliable enterprise-level AI applications. ### Model Use Cases Ideal for chatbots, content generation, coding assistance, data analysis, and multimodal tasks requiring strong reasoning and stable performance. > **[Try GLM 4.7 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Advanced Reasoning:** Handles complex logic and long-context tasks with consistency. * **Multimodal Support:** Works across text and vision inputs in unified workflows. * **High Throughput:** Optimized for low latency and scalable API usage. * **Enterprise Ready:** Stable outputs suited for production environments. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/glm-4.7)** # GLM 5 Source: https://docs.siray.ai/model-apis/z-ai/glm-5 GLM 5 is Zhipu AI's flagship large language model with advanced reasoning and multilingual capabilities. Excel at complex tasks with state-of-the-art Chinese and English understanding. ### Model Use Cases Handle sophisticated reasoning, code generation, content creation, and analysis tasks with Zhipu's most powerful AI model optimized for Chinese language excellence. > **[Try GLM 5 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Advanced Reasoning:** Excels at complex logical and analytical problem solving. * **Bilingual Excellence:** Native-level understanding of both Chinese and English. * **Strong Code Generation:** Capable coding assistant across multiple languages. * **Extended Context Window:** Handles long documents and complex conversations. * **Knowledge Integration:** Comprehensive knowledge base with accurate responses. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/glm-5)** # GLM 5.2 Source: https://docs.siray.ai/model-apis/z-ai/glm-5.2 GLM 5.2 is Zhipu AI's enhanced large language model with refined reasoning and multilingual capabilities. Deliver improved performance across complex tasks and language understanding. ### Model Use Cases Handle sophisticated reasoning, code generation, content creation, and analysis with Zhipu's updated GLM model featuring incremental performance gains. > **[Try GLM 5.2 on Siray.ai](https://console.siray.ai/model-api)** ### Key Features * **Refined Reasoning:** Improved logical and analytical problem solving. * **Bilingual Excellence:** Native-level Chinese and English understanding. * **Enhanced Code Generation:** Upgraded coding assistant capabilities. * **Extended Context:** Handles long documents and conversations. > **[Get Started with the API](https://docs.siray.ai/api-reference/model-api/glm-5.2)** # Quickstart Source: https://docs.siray.ai/quickstart Siray is the first enterprise-grade model library covering the full spectrum of AI models (LLMs, Vision, OCR, Video Generation etc.). ## Get started in two steps ### Step 1: Create an account Visit [Siray.ai](https://www.siray.ai?ytag=doc_quickstart_quickstart_1104) to create your account. ### Step 2: **Start running** * If you need to access APIs, you can go to[ setting page](https://console.siray.ai/keys) to manage your API keys. > [!NOTE] > > Need help? Reach out through: > > * Email: [support@siray.ai](mailto:support@siray.ai) > * Community: [Join our Discord](https://discord.gg/QePXvrWcYJ) # Automatic Top-up Source: https://docs.siray.ai/resources/automatic-top-up Enabling Auto Top-Up ensures your service never stops by automatically adding funds when your account balance falls below a threshold you set. ### 1. Add a Payment Method 1. Go to [Payment section](https://console.siray.ai/payments) in the console. 2. If you haven't added one, click **“Add payment method.”** ### 2. Configure and Enable Auto Top-Up 1. In the payment panel, click **“Edit”** to open the settings. 2. Set the values for two key fields: * The trigger balance. * The amount to add. 3. Click **“Save”** to complete the setup. # FAQs Source: https://docs.siray.ai/resources/faq Before contacting support, please check our Frequently Asked Questions (FAQs) below to quickly find the answers you need. ## Payments ### **1. How can I prevent top-up failures?** Top-up failures typically stem from two primary areas. Please review the relevant points below to quickly resolve the issue: **A. Issues with Your Card Issuer (Bank)** These failures are generally caused by your bank's side. **Please contact your card issuer** to check details related to the following common reasons: * **Payment Channel Status:** The corresponding payment channel may not be activated for online or international transactions. * **Card Status:** The credit card may have expired or been frozen. * **Insufficient Funds:** The credit card balance is insufficient to cover the transaction. * **Incorrect Card Details:** The card number or security code (CVV/CVC) entered is incorrect. **B. Issues with Payment Channel Risk Control (Stripe/Processor)** These security measures are implemented by the payment processor to prevent fraud. Please check your account settings and contact us if you need further clarification: * **Card Association:** The device ID you are using is associated with a high number of different cards. * **High Decline Rate:** The number of cards that have been declined while associated with your email address is very high. * **New Card/Device:** The time since this card was first used on the payment network with this device is very short (a common fraud indicator). * **Low Authorization Rate:** The overall authorization success rate associated with your email address is unusually low. * **Name Mismatch:** The name on your email address does not match the name on the credit card. ### **2. What is Siray’s policy on refunds and credits?** If you have questions before committing, please join our [Discord ](https://discord.com/invite/CmSbUzPSVP)or email [contact@siray.ai](contact@siray.ai). You can start with a top-up of just \$10. **We currently do not offer refunds or trial credits.** Please plan your initial commitment accordingly. ### **3. Can I withdraw the free credits?** No. Free trial credits provided upon registration are limited to designated services and cannot be withdrawn, transferred, or redeemed for cash. ### 4. Do you offer discounts? Yes. Volume-based discounts are available for high-usage customers. If you are a large-scale purchaser, please email [**contact@siray.ai**](mailto:contact@siray.ai) to request a discount. ## **GPU Instance** ### **1. How can I check the pricing for GPU instances?** You can view detailed pricing information, including container disk, volume disk, and network volume costs, during the instance configuration process. ### **2. When does billing for a GPU instance begin?** Billing begins once the instance status changes to “Pulling.” ## API Service ### **1. What are the rate limits for the API service?** | | per min | | - | - | | Image Generation | 500 images | | Videos Generations | 60 Videos | | LLM | 1000 Requests | | Max Concurrent | 100 Tasks | ### 2. Can I use the generated outputs for commercial purposes? Each model has its own licensing terms. Most endpoints available on [Siray.ai](http://Siray.ai) can be used for commercial purposes. Please refer to the model’s official website for detailed license information. # Payment Methods Source: https://docs.siray.ai/resources/payment-methods Siray uses Stripe for all payment processing. You can manually top up their account with an amount greater than \$10. Alternatively, you may enable [**Auto Top-Up**](/resources/automatic-top-up) to instantly add credit when your balance drops below your set threshold. > [!NOTE] > > All payment information is securely processed and stored by Stripe. We do not collect or retain any payment details on our servers.