> ## Documentation Index > Fetch the complete documentation index at: https://docs.inworld.ai/llms.txt > Use this file to discover all available pages before exploring further. # List models > List all available models along with their capabilities, pricing, and specifications. ## OpenAPI ````yaml get /llm/v1alpha/models openapi: 3.0.0 info: title: Inworld Models API version: v1alpha contact: name: Inworld AI url: https://inworld.ai email: support@inworld.ai servers: - url: https://api.inworld.ai security: - inworld_basic: [] tags: - name: ModelService paths: /llm/v1alpha/models: get: tags: - ModelService summary: List models description: >- List all available models along with their capabilities, pricing, and specifications. operationId: ModelService_ListModels responses: '200': description: A successful response. content: application/json: schema: $ref: '#/components/schemas/v1alphaListModelsResponse' examples: successful_response: summary: List of available models description: >- Real example response from DEV (api.dev.inworld.ai), truncated to 1 model. value: models: - model: gemini-2.5-flash provider: google modelCreator: Google pricing: prompt: 3.e-7 completion: 0.0000025 spec: inputModalities: - text - image - audio - video outputModalities: - text contextLength: 1048576 maxCompletionTokens: 65535 supportedParameters: - reasoning - include_reasoning - structured_outputs - response_format - max_tokens - temperature - top_p - seed - stop - tools - tool_choice capabilities: functionCalling: true webSearch: true reasoning: true promptCaching: true responseSchema: true vision: true isSupported: true 4XX: description: An error response. content: application/json: schema: $ref: '#/components/schemas/rpcStatus' x-codeSamples: - lang: bash label: cURL source: |- curl --location 'https://api.inworld.ai/llm/v1alpha/models' \ --header "Authorization: Basic $INWORLD_API_KEY" - lang: python label: Python source: |- import os import requests url = "https://api.inworld.ai/llm/v1alpha/models" headers = { "Authorization": f"Basic {os.getenv('INWORLD_API_KEY')}" } response = requests.get(url, headers=headers) print(response.json()) - lang: javascript label: JavaScript source: |- const url = 'https://api.inworld.ai/llm/v1alpha/models'; const response = await fetch(url, { headers: { 'Authorization': `Basic ${process.env.INWORLD_API_KEY}`, }, }); const data = await response.json(); console.log(data); components: schemas: v1alphaListModelsResponse: type: object properties: models: type: array items: $ref: '#/components/schemas/v1alphaModel' description: The list of available models. rpcStatus: type: object properties: code: type: integer format: int32 description: >- The error code, as specified by [gRPC status codes](https://grpc.io/docs/guides/status-codes/). example: 16 message: type: string description: A short description of the error. example: Unauthenticated details: type: array items: $ref: '#/components/schemas/protobufAny' example: [] v1alphaModel: type: object properties: model: type: string description: >- 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. example: gpt-4o provider: type: string description: >- The service provider hosting the model. Maps to the `serviceProvider` field in completion requests. example: openai modelCreator: type: string description: >- The organization that created the model. May differ from the provider (e.g., a Meta model hosted on Groq). example: OpenAI pricing: $ref: '#/components/schemas/v1alphaModelPricing' spec: $ref: '#/components/schemas/v1alphaModelSpec' isSupported: type: boolean description: >- 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. required: - model - provider protobufAny: type: object properties: '@type': type: string additionalProperties: {} v1alphaModelPricing: type: object description: Per-token pricing information for the model (in USD). properties: prompt: type: number format: double description: Cost per input (prompt) token in USD. example: 0.0000025 completion: type: number format: double description: Cost per output (completion) token in USD. example: 0.00001 v1alphaModelSpec: type: object description: Technical specifications and capabilities of the model. properties: inputModalities: type: array items: type: string enum: - text - image - audio - video description: The input modalities supported by the model. example: - text - image outputModalities: type: array items: type: string enum: - text - image - audio description: The output modalities supported by the model. example: - text contextLength: type: integer format: int32 description: >- The maximum number of tokens the model can process as input (context window size). example: 128000 maxCompletionTokens: type: integer format: int32 description: >- The maximum number of tokens the model can generate in a single response. example: 16384 supportedParameters: type: array items: type: string description: >- 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`. example: - max_tokens - temperature - top_p - stop - tools - tool_choice capabilities: $ref: '#/components/schemas/v1alphaModelCapabilities' v1alphaModelCapabilities: type: object description: >- High-level capability flags for the model. Only capabilities that are `true` are included in the response. properties: functionCalling: type: boolean description: Whether the model supports function/tool calling. webSearch: type: boolean description: Whether the model supports web search (grounding). reasoning: type: boolean description: Whether the model supports chain-of-thought reasoning. promptCaching: type: boolean description: Whether prompt caching is available for this model. responseSchema: type: boolean description: >- Whether the model supports structured output with a response schema (JSON mode). vision: type: boolean description: Whether the model supports image/vision input. securitySchemes: inworld_basic: type: apiKey in: header name: Authorization description: >- Your [authentication](../../../api-reference/introduction) credentials. For Basic authentication, please populate `Basic $INWORLD_API_KEY` ````