> ## Documentation Index > Fetch the complete documentation index at: https://docs.inb.cc/llms.txt > Use this file to discover all available pages before exploring further. # List available models (Gemini format) > Return all InfinityBlue models in Google Gemini native format ## Available models A selection of real models available today (full list is dynamic — use the API): | name | displayName | | ------------------------------- | ---------------------- | | `models/gemini-3.1-pro-preview` | Gemini 3.1 Pro Preview | | `models/gemini-2.5-pro` | Gemini 2.5 Pro | | `models/gpt-5.4` | GPT-5.4 | | `models/gpt-5.4-mini` | GPT-5.4 Mini | | `models/deepseek-v4-pro` | DeepSeek V4 Pro | See the [pricing page](https://api.getinfinityblue.com/pricing) for the full list. ## Using the Google Generative AI SDK ```python import google.generativeai as genai genai.configure( api_key="YOUR_API_KEY", client_options={"api_endpoint": "https://api.getinfinityblue.com"} ) for model in genai.list_models(): print(model.name, model.display_name) ``` ## Field notes `supportedGenerationMethods` lists the invocation modes the model supports. Common values: `generateContent`, `streamGenerateContent`, `embedContent`. ## OpenAPI ````yaml /openapi/models.en.yaml get /v1beta/models openapi: 3.1.0 info: title: InfinityBlue API — Models version: 1.0.0 summary: List currently available AI models description: > This file covers the InfinityBlue model listing endpoints: - `GET /v1/models` — OpenAI-compatible format, works with any OpenAI SDK - `GET /v1beta/models` — Gemini native format, works with the Google Generative AI SDK Both endpoints expose the same underlying pool of models in different response shapes. The model list is dynamic and updated as InfinityBlue onboards new providers. See the [pricing page](https://api.getinfinityblue.com/pricing) for the full list and pricing. ## Authentication Every request must include your API key in the header: ``` Authorization: Bearer YOUR_API_KEY ``` Create and manage your API keys in the [console](https://api.getinfinityblue.com/console). contact: name: InfinityBlue url: https://getinfinityblue.com servers: - url: https://api.getinfinityblue.com description: Production security: - bearerAuth: [] tags: - name: Models description: | List all AI models currently available through InfinityBlue. Supports both the OpenAI-compatible and Gemini native response formats. paths: /v1beta/models: get: tags: - Models summary: List available models (Gemini format) description: > Returns the list of all currently available models in Google Gemini native format. Works with the Google Generative AI SDK — point `api_endpoint` at InfinityBlue and call `genai.list_models()` to enumerate all available models. Response fields match the Gemini API specification exactly, including `name`, `displayName`, `description`, `inputTokenLimit`, `outputTokenLimit`, and `supportedGenerationMethods`. The model list is dynamic and reflects the latest set of models available through InfinityBlue. operationId: listModelsGemini responses: '200': description: Successfully returned the model list content: application/json: schema: $ref: '#/components/schemas/GeminiModelListResponse' examples: default: summary: Typical response value: models: - name: models/gemini-3.1-pro-preview version: '003' displayName: Gemini 3.1 Pro Preview description: >- Gemini flagship multimodal model with 1M context window inputTokenLimit: 1048576 outputTokenLimit: 65536 supportedGenerationMethods: - generateContent - streamGenerateContent - name: models/gemini-2.5-pro version: '001' displayName: Gemini 2.5 Pro description: Strong reasoning and code generation capabilities inputTokenLimit: 1048576 outputTokenLimit: 65536 supportedGenerationMethods: - generateContent - streamGenerateContent - name: models/gpt-5.4 version: '001' displayName: GPT-5.4 description: >- GPT-5 flagship with top reasoning and agentic capabilities inputTokenLimit: 1000000 outputTokenLimit: 32768 supportedGenerationMethods: - generateContent - streamGenerateContent - name: models/deepseek-v4-pro version: '001' displayName: DeepSeek V4 Pro description: DeepSeek cost-effective reasoning model inputTokenLimit: 131072 outputTokenLimit: 16384 supportedGenerationMethods: - generateContent - streamGenerateContent '400': description: Invalid request parameters content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Invalid or missing API key content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: GeminiModelListResponse: type: object description: Gemini native format model list response. properties: models: type: array description: The list of available models. items: $ref: '#/components/schemas/GeminiModelInfo' ErrorResponse: type: object description: Standard error response. properties: error: type: object properties: message: type: string description: Error message. examples: - Invalid API key provided. type: type: string description: Error type. examples: - invalid_request_error param: type: - string - 'null' description: The parameter related to the error, or null if not applicable. examples: - model code: type: - string - 'null' description: Machine-readable error code, or null if not applicable. examples: - invalid_api_key GeminiModelInfo: type: object description: A single model descriptor in Gemini native format. properties: name: type: string description: | Resource name in the form `models/{model-id}`. Used to identify the model in the Gemini SDK. examples: - models/gemini-3.1-pro-preview version: type: string description: Model version string. examples: - '003' displayName: type: string description: Human-readable model name. examples: - Gemini 3.1 Pro Preview description: type: string description: Brief description of the model's capabilities. examples: - Gemini flagship multimodal model with 1M context window inputTokenLimit: type: integer description: Maximum number of input tokens per request (context window size). examples: - 1048576 outputTokenLimit: type: integer description: Maximum number of output tokens per request. examples: - 65536 supportedGenerationMethods: type: array description: | Generation modes supported by this model. Common values: - `generateContent`: non-streaming generation - `streamGenerateContent`: streaming generation - `embedContent`: text embedding items: type: string examples: - - generateContent - streamGenerateContent securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: > Bearer token authentication, format: `Authorization: Bearer sk-xxxxxx`. Get your API key in the [console](https://api.getinfinityblue.com/console). ````