Models
SIRAYA Model Router gives you one interface to a broad catalog of models across chat,
image, video, and audio. You select a model by name in the model field of your request;
the router resolves the best backend for it automatically — see
How Routing Works.
Availability is account-specific. The exact models you can call depend on your configuration. Call
GET /v1/modelsto discover the models available to your key — see Model Availability.
For how parameters behave across model families, see Parameter Support by Model and Per-Model Details.
Chat & completion models
| Family | Models |
|---|---|
| Claude | Claude Haiku 4.5, Sonnet 4.5, Sonnet 4.6, Opus 4.5, Opus 4.6, Opus 4.7, Opus 4.8 |
| GPT | GPT 4.1, 4.1 Mini, 5, 5.1, 5.1 Codex, 5.1 Codex Max, 5.1 Codex Mini, 5.2 Codex, 5.3 Chat, 5.3 Codex, 5.4, 5.4 Mini, 5.4 Pro, 5.5 |
| Gemini | Gemini 2.5 Flash, 2.5 Pro, 3 Flash Preview, 3.1 Pro Preview, 3.1 Flash Lite Preview, 3.1 Flash-Lite |
| Qwen | Qwen Turbo, Qwen3 Max, Qwen3.5 Flash, Qwen3.5 Plus, Qwen3.6 Plus, Qwen3.7 Max, Qwen3.7 Plus |
| GLM | GLM 5, GLM 5 Turbo, GLM 5.1 |
| DeepSeek | DeepSeek V4 Flash, DeepSeek V4 Pro |
| Grok | Grok 3, Grok 4.1 Fast |
| MiniMax | MiniMax M2.5, MiniMax M2.7 |
| Kimi | Kimi K2.5 |
| Seed | Seed 1.8, Seed SC, Seed 2.0 lite, Seed 2.0 mini, Seed 2.0 pro |
Call any of these through any chat format — Chat Completions, Responses, or Messages.
Image generation models
| Family | Models | Endpoint |
|---|---|---|
| GPT Image | GPT-Image-2 | /v1/images/generations |
| Imagen | Imagen 4 | /v1/images/generations |
| Seedream | Seedream 5.0 lite, Seedream 4.5, Seedream 4.0 | /v1/images/generations |
Video generation models
| Family | Models | Notes |
|---|---|---|
| Veo | Veo 3.1 | Text-to-video and image-to-video |
| Seedance | Seedance 1.0 pro, Seedance 1.0 pro fast | Standard / fast variants |
| Seedance | Seedance 1.5 pro (Audio) | Includes AI audio generation |
| SIRAYA Seedance | SIRAYA Seedance 2.0, SIRAYA Seedance 2.0 fast | Reference-guided generation |
Video generation is asynchronous — see the Video API.
Audio & speech models
| Capability | Model | Endpoint |
|---|---|---|
| Speech-to-Text | Qwen3 ASR Flash | /v1/audio/transcriptions |
Additional speech-to-text models are being added. Use
GET /v1/modelsto see what's currently available to you.