Models

code

GET /api/v1/models

List all available models. No authentication required.

A bare GET /api/v1/models (what OpenAI SDKs send) returns the strict OpenAI format: {"object": "list", "data": [{"id", "object", "created", "owned_by"}]}. GET /api/v1/models/{id} retrieves a single model the same way.

Adding any of the query parameters below switches to the rich format with pricing, throughput, and latency stats.

Query parameters

Parameter	Type	Description
`q`	string	Free-text search across name, ID, and description
`order`	string	Sort: `top-weekly`, `newest`, `pricing-low-to-high`, `pricing-high-to-low`, `context-high`, `throughput-high`, `latency-low`
`provider`	string	Filter by provider slug (e.g. `openai`, `anthropic`)
`modality`	string	Filter by modality: `text`, `image`, etc.
`minCtx` / `maxCtx`	number	Context length range
`pricingMin` / `pricingMax`	number	Price-per-million range
`active`	boolean	`false` to include inactive models

Response

json

{  "data": [    {      "id": "cuid",      "openrouterId": "openai/gpt-4o",      "slug": "gpt-4o",      "name": "GPT-4o",      "description": "OpenAI's flagship multimodal model...",      "contextLength": 128000,      "pricing": {        "prompt": 0.000005,        "completion": 0.000015,        "image": 0,        "request": 0      },      "modalities": ["text"],      "provider": "openai",      "authorName": "OpenAI",      "avgThroughputTps": 123.4,      "avgLatencyMs": 450,      "isActive": true    }  ]}

Pricing values in the response already include the 1.20× markup.