Models

Browse available models and their capabilities.

List Models

GET /v1/models

Returns a list of all available models.

Example Request

curl https://api.routerhub.ai/v1/models \
  -H "Authorization: Bearer $ROUTERHUB_API_KEY"

Example Response

{
  "object": "list",
  "data": [
    {
      "id": "anthropic/claude-sonnet-4",
      "object": "model",
      "created": 1700000000,
      "owned_by": "anthropic"
    }
  ]
}

Claude Models

Model ID Description Structured Output Reasoning
anthropic/claude-opus-4.6 Most capable Claude model (Opus 4.6) Yes (native) Yes
anthropic/claude-opus-4.5 Most capable Claude model (Opus 4.5) Yes (native) Yes
anthropic/claude-sonnet-4.6 High-performance balance (Sonnet 4.6) Yes (native) Yes
anthropic/claude-sonnet-4.5 High-performance balance (Sonnet 4.5) Yes (native) Yes
anthropic/claude-sonnet-4 Fast and capable (Sonnet 4) Yes Yes
anthropic/claude-opus-4.1 Previous-gen Opus (4.1) Yes Yes
anthropic/claude-haiku-4.5 Fastest Claude model (Haiku 4.5) Yes (native) Yes
anthropic/claude-3.5-haiku Legacy Haiku 3.5 Yes No

Gemini Models

Model ID Description Structured Output Reasoning
google/gemini-3.1-pro-preview Latest Gemini Pro preview Yes Yes
google/gemini-3-flash-preview Gemini 3 Flash preview Yes Yes
google/gemini-2.5-pro Gemini 2.5 Pro Yes Yes
google/gemini-2.5-flash Gemini 2.5 Flash Yes Yes
google/gemini-2.5-flash-lite Gemini 2.5 Flash Lite Yes Yes

Gemini Image Generation Models

Model ID Description Endpoint
google/gemini-2.5-flash-image Gemini 2.5 Flash with image generation /v1beta/models/{model}:generateContent
google/gemini-3-pro-image-preview Gemini 3 Pro image generation preview /v1beta/models/{model}:generateContent
google/gemini-3.1-flash-image-preview Gemini 3.1 Flash image generation preview /v1beta/models/{model}:generateContent

Image generation models use a different endpoint and request format from the text models above. See Image Generation for full documentation.

GPT Models

Model ID Description Structured Output Reasoning
openai/gpt-5 GPT-5 Yes Yes
openai/gpt-5.4-pro GPT-5.4 Pro Yes Yes
openai/gpt-5.4 GPT-5.4 Yes Yes
openai/gpt-5.4-mini GPT-5.4 Mini Yes Yes
openai/gpt-5.4-nano GPT-5.4 Nano Yes Yes
openai/gpt-5.3-chat GPT-5.3 Chat Yes Yes
openai/gpt-5.2-chat GPT-5.2 Chat Yes Yes
openai/gpt-5.2 GPT-5.2 Yes Yes
openai/gpt-5.3-codex GPT-5.3 Codex Yes Yes
openai/gpt-5.2-codex GPT-5.2 Codex Yes Yes
openai/gpt-5.1 GPT-5.1 Yes Yes
openai/gpt-5.1-codex GPT-5.1 Codex Yes Yes
openai/gpt-5.1-codex-mini GPT-5.1 Codex Mini Yes Yes
openai/gpt-4.1 GPT-4.1 Yes No
openai/gpt-4o GPT-4o Yes No

All models support tool calling. Structured output and reasoning support varies by model — see the tables above.

API Compatibility

Every text model (Claude, Gemini, GPT) works on all three API surfaces:

  • POST /v1/chat/completions — OpenAI-compatible format. See Chat Completions.
  • POST /v1/messages — Anthropic-compatible format. See Messages.
  • POST /v1beta/models/{model}:generateContent and :streamGenerateContent — Native Gemini format. See Generate Content.

Use the same model ID on every surface. For example, anthropic/claude-sonnet-4 works identically whether you call it via the OpenAI Chat Completions endpoint, the Anthropic Messages endpoint, or the Gemini Generate Content endpoint.

Image generation models share the /v1beta/ URL pattern but use image-specific request and response shapes: