Models

Returns the list of all available models on the platform, including their capabilities, context limits, and credit pricing.

GET /models

---

Authentication

Requires one of:

• X-Api-Key header with a valid API key

• Authorization and X-Firebase-AppCheck headers for browser-based auth

---

Parameters

This endpoint takes no parameters.

---

Request Example

curl -X GET https://inference-api-611798501438.us-central1.run.app/models \
  -H "X-Api-Key: inf_your_api_key_here"

---

Response

Returns a JSON object containing an array of model objects.

{
  "models": [
    {
      "id": "claude-sonnet",
      "name": "Claude Sonnet 4.6",
      "provider": "anthropic",
      "context_window": 200000,
      "max_output_tokens": 64000,
      "cost_per_1k_input": 4.20,
      "cost_per_1k_output": 21.00,
      "supports_tools": true,
      "supports_vision": true
    },
    {
      "id": "gpt-5.2",
      "name": "GPT-5.2",
      "provider": "openai",
      "context_window": 400000,
      "max_output_tokens": 32768,
      "cost_per_1k_input": 2.10,
      "cost_per_1k_output": 14.00,
      "supports_tools": true,
      "supports_vision": true
    },
    {
      "id": "gemini-3-flash",
      "name": "Gemini 3 Flash",
      "provider": "vertex",
      "context_window": 1048576,
      "max_output_tokens": 64000,
      "cost_per_1k_input": 0.70,
      "cost_per_1k_output": 4.20,
      "supports_tools": true,
      "supports_vision": true
    }
  ]
}

Note: The response above is illustrative. The actual model list, pricing, and capabilities are subject to change. Always query this endpoint for the current catalog.

---

Model Object

Field	Type	Description
id	string	Unique model identifier. Pass this value as the model parameter in /chat and /code requests.
name	string	Human-readable display name.
provider	string	Upstream provider: openai, anthropic, vertex, or openrouter.
context_window	integer	Maximum total tokens (input + output) the model supports.
max_output_tokens	integer	Maximum number of tokens the model can generate in a single response.
cost_per_1k_input	float	Credit cost per 1,000 input tokens. Includes the platform's 1.4x margin.
cost_per_1k_output	float	Credit cost per 1,000 output tokens. Includes the platform's 1.4x margin.
supports_tools	boolean	Whether the model supports tool-use (function calling). Required for /code.
supports_vision	boolean	Whether the model supports image inputs.

---

Providers

The platform routes requests to four upstream providers:

Provider	Description
openai	OpenAI API (GPT-5.2, GPT-5 Mini, GPT-5.2 Codex, CMO Agent)
anthropic	Anthropic API (Claude Sonnet 4.6, Claude Haiku 4.5, Claude Opus 4.6)
vertex	Google Vertex AI (Gemini 3 Flash, Gemini 3.1 Pro, Seedream 4.5)
openrouter	OpenRouter aggregator (Llama 4, DeepSeek, Qwen3, Kimi, Grok)

---

Error Responses

Status	Description
401	Missing or invalid authentication
500	Internal server error