---
title: "List models"
method: GET
path: "/llm/v1alpha/models"
tags: ["ModelService"]
---

# List models

`GET /llm/v1alpha/models`

List all available models along with their capabilities, pricing, and specifications.

## Response `200`

A successful response.

- V1alphaListModelsResponse
  - `models` V1alphaModel[] — The list of available models.
    - `model` string, required — The unique identifier of the model. Use this value in the `model` field when making [LLM completions](../../../api-reference/llmAPI/llmservice/generate-chat-completion-response) or [Router](../../../api-reference/routerAPI/chat-completions) requests.
    - `provider` string, required — The service provider hosting the model. Maps to the `serviceProvider` field in completion requests.
    - `modelCreator` string — The organization that created the model. May differ from the provider (e.g., a Meta model hosted on Groq).
    - `pricing` V1alphaModelPricing — Per-token pricing information for the model (in USD).
      - `prompt` number, double — Cost per input (prompt) token in USD.
      - `completion` number, double — Cost per output (completion) token in USD.
    - `spec` V1alphaModelSpec — Technical specifications and capabilities of the model.
      - `inputModalities` string[] — The input modalities supported by the model.
      - `outputModalities` string[] — The output modalities supported by the model.
      - `contextLength` integer — The maximum number of tokens the model can process as input (context window size).
      - `maxCompletionTokens` integer — The maximum number of tokens the model can generate in a single response.
      - `supportedParameters` string[] — The generation parameters supported by this model. Common values include: `max_tokens`, `temperature`, `top_p`, `stop`, `seed`, `response_format`, `structured_outputs`, `tools`, `tool_choice`, `reasoning`, `include_reasoning`, `frequency_penalty`, `presence_penalty`.
      - `capabilities` V1alphaModelCapabilities — High-level capability flags for the model. Only capabilities that are `true` are included in the response.
        - `functionCalling` boolean — Whether the model supports function/tool calling.
        - `webSearch` boolean — Whether the model supports web search (grounding).
        - `reasoning` boolean — Whether the model supports chain-of-thought reasoning.
        - `promptCaching` boolean — Whether prompt caching is available for this model.
        - `responseSchema` boolean — Whether the model supports structured output with a response schema (JSON mode).
        - `vision` boolean — Whether the model supports image/vision input.
    - `isSupported` boolean — Indicates whether this model is currently supported and recommended for use. Models without this flag or with `false` may be experimental, deprecated, or not yet generally available.

## Other responses

- `4XX` — An error response.

---

[API](https://skmtc.net/inworld/apis/inworld-text-to-speech-api.md) · [All operations](https://skmtc.net/inworld/apis/inworld-text-to-speech-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/inworld/inworld-text-to-speech-api/revisions/e79009799a0d/schema)