Models

Browse available models and query the models endpoint.

GET /v1/models

Returns all supported models with per-task benchmark scores and metadata. No authentication required.

{
  "models": [
    {
      "modelId": "claude-sonnet-4",
      "provider": "anthropic",
      "taskType": "coding",
      "score": 87.3,
      "costPer1kInput": 0.003,
      "costPer1kOutput": 0.015,
      "avgLatencyMs": 450,
      "supportsEu": false,
      "supportsUs": true,
      "ecoScore": 65,
      "available": true
    }
  ]
}

Each model appears multiple times — once per task type. Use taskType to filter for your use case.

Supported models

PathFinder routes across 17 models from 6 providers. You never choose a model — the router selects the best one for your task.

Provider	Models
Anthropic	claude-sonnet-4, claude-haiku-4-5, claude-opus-4-5
OpenAI	gpt-4o, gpt-4o-mini, o3-mini
Google	gemini-2.0-flash, gemini-1.5-pro, gemini-1.5-flash
Mistral	mistral-small-latest, mistral-large-latest
DeepSeek	deepseek-coder-v2, deepseek-chat
Groq	llama-3.3-70b-versatile, llama-3.1-8b-instant, mixtral-8x7b-32768

Model scores are updated weekly from 10 public benchmark sources. See Routing → Models for live scores.