---
title: "Lists the currently available models, and provides basic information about each one such as the owner and availability."
method: GET
path: "/models"
tags: ["Models"]
---

# Lists the currently available models, and provides basic information about each one such as the owner and availability.

`GET /models`

Lists the currently available models, and provides basic information
about each one such as the owner and availability.

## Query parameters

- `provider` 'ollama' | 'ollama_cloud' | 'groq' | 'llamacpp' | 'openai' | 'cloudflare' | 'cohere' | 'anthropic' | 'deepseek' | 'google' | 'mistral' | 'minimax' | 'moonshot' | 'nvidia' | 'zai'
- `include` string[]

## Response `200`

List of available models

- ListModelsResponse — Response structure for listing models
  - `provider` 'ollama' | 'ollama_cloud' | 'groq' | 'llamacpp' | 'openai' | 'cloudflare' | 'cohere' | 'anthropic' | 'deepseek' | 'google' | 'mistral' | 'minimax' | 'moonshot' | 'nvidia' | 'zai'
  - `object` string, required
  - `data` Model[], required
    - `id` string, required
    - `object` string, required
    - `created` integer, required
    - `owned_by` string, required
    - `served_by` 'ollama' | 'ollama_cloud' | 'groq' | 'llamacpp' | 'openai' | 'cloudflare' | 'cohere' | 'anthropic' | 'deepseek' | 'google' | 'mistral' | 'minimax' | 'moonshot' | 'nvidia' | 'zai', required
    - `context_window` ModelContextWindow — Effective context window a client may safely use for the model. Present only when requested via `include=context_window`; `null` when requested but the window could not be resolved. The value reflects what the serving runtime is actually configured with when available, which can be smaller than the model's theoretical maximum.
      - `tokens` integer, required — Effective context window size in tokens.
      - `source` 'runtime' | 'provider', required — Where the value was resolved from. `runtime` means the serving runtime reported its configured window (e.g. llama.cpp `/props`, Ollama's show API); `provider` means the upstream provider published the window in its model listing.
    - `pricing` ModelPricing — Normalized public per-token pricing for the model. Present only when requested via `include=pricing`; `null` when requested but the model has no public per-token cost (subscription-based providers, locally hosted models, or providers that publish no pricing). Monetary values are decimal strings to avoid floating-point precision loss. Rates the provider does not publish are omitted entirely, never `0` or `null`.
      - `currency` string, required — ISO 4217 currency code the rates are denominated in.
      - `input_per_token` string — Cost per input (prompt) token, as a decimal string.
      - `output_per_token` string — Cost per output (completion) token, as a decimal string.
      - `cache_read_per_token` string — Cost per token read from the provider's prompt cache, as a decimal string. Present only when the provider publishes a cached-input rate.
      - `cache_write_per_token` string — Cost per token written to the provider's prompt cache, as a decimal string. Present only when the provider publishes a cache-creation rate.
      - `source` 'provider' | 'community', required — Where the rates were resolved from. `provider` means the upstream provider published them in its model listing; `community` means they were synced from the community-maintained models.dev dataset.
      - `updated_at` string, date-time — When the rates were last refreshed, if known.

## Other responses

- `401` — Unauthorized
- `500` — Internal server error

## Changes

- **2026-07-20** `a377fa5d64dd` — 1 warning
  - added the new `community` enum value to the `data/items/pricing/source` response property for the response status `200`
- **2026-07-20** `cef96016490d` — 7 info
  - added the optional property `data/items/pricing/cache_read_per_token` to the response with the `200` status
  - added the optional property `data/items/pricing/cache_write_per_token` to the response with the `200` status
  - added the optional property `data/items/pricing/input_per_token` to the response with the `200` status
  - added the optional property `data/items/pricing/output_per_token` to the response with the `200` status
  - …3 more
- **2026-07-20** `65bb820067ab` — 1 breaking, 2 info
  - the `data/items/context_window` response's property type/format changed from `integer`/`int64` to `object`/`` for status `200`
  - added the required property `data/items/context_window/source` to the response with the `200` status
  - added the required property `data/items/context_window/tokens` to the response with the `200` status
- **2026-07-20** `479fdc43325d` — 3 info
  - added the new optional `query` request parameter `include`
  - added the optional property `data/items/context_window` to the response with the `200` status
  - added the optional property `data/items/pricing` to the response with the `200` status
- …earlier changes not shown

[Full history](https://skmtc.dev/inference-gateway/apis/inference-gateway-api/changes/models/get.md)

---

[API](https://skmtc.dev/inference-gateway/apis/inference-gateway-api.md) · [All operations](https://skmtc.dev/inference-gateway/apis/inference-gateway-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/inference-gateway/inference-gateway-api/revisions/a377fa5d64dd/schema)