> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openference.com/llms.txt
> Use this file to discover all available pages before exploring further.

# GET /v1/models

> Discover available models filtered by the caller's key permissions.

# GET /v1/models

Returns the list of models the authenticated key is allowed to use.

Used by Cursor's "Verify" button, Cline, and most clients at startup.

Response shape:

```json theme={null}
{
  "object": "list",
  "data": [
    {
      "id": "GLM-5.2",
      "object": "model",
      "created": 0,
      "owned_by": "openference",
      "permission": [],
      "root": "GLM-5.2",
      "parent": null,
      "context_length": 850000,
      "max_output_tokens": 128000,
      "pricing": {
        "prompt": "0.00000014",
        "completion": "0.00000028"
      }
    }
  ]
}
```

Filtered automatically by key model restrictions.

## Context metadata

* `context_length` — the model's maximum **input** context window in tokens
  (OpenRouter-style field). Use it to configure your client's context window
  setting (e.g. OpenCode `limit.context`, Cline "Context Window Size") so the
  client doesn't fall back to a small default and compact conversations early.
  This is the safe input budget — it already accounts for the model's
  `max_output_tokens`, so input + output stays within the model's total context
  wall. For example GLM-5.2 advertises `context_length: 850000` and
  `max_output_tokens: 128000` (≈ 1M total).
* `max_output_tokens` — the maximum completion tokens the model supports per
  response.

Either field may be absent for models where the value is not published.

## Pricing

* `pricing.prompt` — the model's per-token price for input (prompt) tokens, as
  a USD string. Multiply by the `usage.prompt_tokens` count returned by
  `/v1/chat/completions` to get the input cost for a request.
* `pricing.completion` — the model's per-token price for output (completion)
  tokens, as a USD string. Multiply by `usage.completion_tokens` for the output
  cost.

These are the same per-token rates the billing system applies when a request
falls outside your plan's included quota (e.g. credit-balance usage), so
analytics dashboards that pull token counts from chat completions and the
advertised price from `/v1/models` can compute accurate cost-per-turn and
usage graphs. Prices are expressed per-token (not per-million) as a string to
match the OpenRouter shape; `"0"` indicates a free model or a model priced
per-image instead of per-token (see `architecture.modality` for image models).