---
title: "Models"
method: GET
path: "/v1/models"
---

# Models

`GET /v1/models`

List all available models

## Query parameters

- `include_deactivated` string — Include deactivated models in the response
- `exclude_deprecated` string — Exclude deprecated models from the response
- `no_training` string — Only return models and provider mappings whose provider does not train on API data
- `mapped` string — Return one entry per provider mapping with `provider/model-id` ids (the gateway's provider-pinned request format) instead of one aggregated entry per model. Each entry carries that specific mapping's pricing, context length, and capabilities.

## Response `200`

List of available models

- object
  - `data` object[], required
    - `id` string, required
    - `name` string, required
    - `display_name` string, required — Human-readable model label, mirroring `name`. Anthropic-format clients such as Claude Code read this field when populating their model picker from gateway model discovery.
    - `aliases` string[]
    - `created` number
    - `description` string
    - `family` string, required
    - `architecture` object, required
      - `input_modalities` string[], required
      - `output_modalities` string[], required
      - `tokenizer` string
    - `top_provider` object, required
      - `is_moderated` boolean, required
    - `providers` object[], required
      - `providerId` string, required
      - `externalId` string, required
      - `supportedVideoSizes` string[]
      - `supportsVideoAudio` boolean
      - `supportsVideoWithoutAudio` boolean
      - `pricing` object
        - `prompt` string, required
        - `completion` string, required
        - `image` string
        - `input_audio` string
        - `input_audio_cache_read` string
        - `output_audio` string
        - `per_second` object
        - `per_image` object
        - `request` string
        - `input_cache_read` string
        - `input_cache_write` string
        - `input_cache_write_1h` string
        - `ocr_page` string
        - `input_audio_hour` string
      - `streaming` union, required
        - boolean
        - 'only'
      - `vision` boolean, required
      - `realtime` boolean — Whether this mapping is served via the /v1/realtime WebSocket endpoint instead of /v1/chat/completions.
      - `cancellation` boolean, required
      - `tools` boolean, required
      - `parallelToolCalls` boolean, required
      - `reasoning` boolean, required
      - `reasoning_efforts` string[] — Exact reasoning_effort values this provider mapping accepts, in ascending order of effort. Omitted when the supported values are not declared for the mapping.
      - `min_cacheable_tokens` number — Minimum prompt length (in tokens) the provider requires before a prompt-cache write can occur. cache_control markers on shorter prompts are accepted but silently not cached by the provider.
      - `max_output` number — Maximum output tokens this provider mapping accepts as max_tokens; larger requests are rejected with HTTP 400. Omitted when the mapping declares no limit (any max_tokens is accepted).
      - `stability` 'stable' | 'beta' | 'unstable' | 'experimental'
    - `pricing` object, required
      - `prompt` string, required
      - `completion` string, required
      - `image` string
      - `input_audio` string
      - `input_audio_cache_read` string
      - `output_audio` string
      - `per_second` object
      - `per_image` object
      - `request` string
      - `input_cache_read` string
      - `input_cache_write` string
      - `input_cache_write_1h` string
      - `web_search` string
      - `internal_reasoning` string
      - `ocr_page` string
      - `input_audio_hour` string
    - `context_length` number
    - `max_output` number — Largest max_tokens value guaranteed to be accepted regardless of which provider mapping serves the request (the minimum across still-servable mappings that declare a limit; deactivated mappings are excluded). Omitted when no such mapping declares one.
    - `per_request_limits` object
    - `supported_parameters` string[]
    - `json_output` boolean, required
    - `structured_outputs` boolean, required
    - `free` boolean
    - `deprecated_at` string
    - `deactivated_at` string
    - `stability` 'stable' | 'beta' | 'unstable' | 'experimental'

## Other responses

- `429` — Rate limited. Back off until Retry-After elapses.
- `500` — Internal server error.
- `503` — Service unavailable.

---

[API](https://skmtc.dev/llmgateway/apis/llmgateway-api.md) · [All operations](https://skmtc.dev/llmgateway/apis/llmgateway-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/llmgateway/llmgateway-api/revisions/aaf167e3d8cc/schema)