GET /api/v1/models

Returns a list of all available models with pricing and capability information.

Response

JSON

{
  "models": [
    {
      "id": "claude-sonnet-4-6",
      "name": "Claude Sonnet 4.6",
      "cost": { "input": 3.00, "output": 15.00 },
      "limit": { "context": 200000, "output": 16384 },
      "supportsImages": true,
      "description": "General purpose, coding"
    },
    {
      "id": "gemini-3.1-pro-preview",
      "name": "Gemini 3.1 Pro Preview",
      "cost": { "input": 2.00, "output": 12.00 },
      "limit": { "context": 1048576, "output": 65536 },
      "reasoning": true,
      "supportsImages": true,
      "supportsVideo": true,
      "supportsAudio": true
    }
  ]
}

Fields

idstring

Model identifier. Pass this as the model field in the chat endpoint.

namestring

Human-readable model name.

costobject

input and output pricing in USD per 1M tokens.

limitobject

context (max input tokens) and output (max output tokens).

reasoningboolean?

Present and true for models that support extended thinking / chain-of-thought reasoning.

supportsImagesboolean?

Present and true for models that accept image file inputs in the parts array.

supportsVideoboolean?

Present and true for models that accept video file inputs (e.g. Gemini models).

supportsAudioboolean?

Present and true for models that accept audio file inputs (e.g. Gemini models, GPT-4o).

descriptionstring?

Short description of the model's strengths, when available.

Fetch live model list

Popular Models

Model	Best For
claude-sonnet-4-6	General purpose, coding
claude-opus-4-6	Complex reasoning
claude-haiku-4-5	Fast, lightweight
gpt-5.6-sol	Flagship reasoning, long-horizon agentic work
gpt-5.6-luna	Fast, affordable OpenAI reasoning
gemini-3.1-pro-preview	Multimodal, long context
grok-4	General purpose
deepseek-v3-2	Coding, math

Studio Models (Video & Image)

Video and image generation models are invoked through the Studio endpoints rather than /api/v1/chat. Pass the model ID in the body of the corresponding Studio call (see /api/v1/studio/video/generate and /api/v1/studio/image/generate).

Model	Kind	Notes
veo	Video	Google Veo 3.1 — audio, 4/6/8s
kling-3.0-pro	Video	Kling 3.0 Pro — 3-15s, audio
seedance-2.0	Video	ByteDance Seedance 2.0 — 480p/720p, audio
nano-banana	Image	Gemini Flash via fal.ai — generate + edit
seedream	Image	ByteDance Seedream v4.5 — generate + edit
imagen-ultra	Image	Google Imagen 4 Ultra — high-fidelity generation
gpt-image	Image	OpenAI GPT Image 1