> ## Documentation Index > Fetch the complete documentation index at: https://docs.flex.ai/llms.txt > Use this file to discover all available pages before exploring further. # List available models > Returns text, chat, and embedding models in OpenAI's `Model` shape — see [the model catalog](https://flex.ai/models) for the complete set with pricing and capabilities. Each entry is enriched with OpenRouter-spec metadata so third-party catalog ingesters can consume `/v1/models` directly. The OpenAI-compatible top-level keys (`id`, `object`, `created`, `owned_by`) stay byte-identical for back-compat with the OpenAI Python SDK. `owned_by` is always `"flexai"` — clients branching on the legacy `"openai"` placeholder must update. ## OpenAPI ````yaml /inference-api/openapi.yaml get /v1/models openapi: 3.1.0 info: title: FlexAI Inference API version: 1.0.0 description: | OpenAI-compatible inference API for text, code, reasoning, vision, and embedding models hosted by FlexAI. Use any OpenAI SDK by pointing the `base_url` at this service. contact: name: FlexAI Support email: support@flex.ai url: https://docs.flex.ai/inference-api/overview servers: - url: https://tokens.flex.ai description: Production security: - bearerAuth: [] tags: - name: Chat description: Chat completions (streaming, tool use, vision). - name: Completions description: Legacy text completions. - name: Embeddings description: Generate vector embeddings for text. - name: Models description: Discover available models. - name: Usage description: Programmatic spend and quota for the calling key. paths: /v1/models: get: tags: - Models summary: List available models description: | Returns text, chat, and embedding models in OpenAI's `Model` shape — see [the model catalog](https://flex.ai/models) for the complete set with pricing and capabilities. Each entry is enriched with OpenRouter-spec metadata so third-party catalog ingesters can consume `/v1/models` directly. The OpenAI-compatible top-level keys (`id`, `object`, `created`, `owned_by`) stay byte-identical for back-compat with the OpenAI Python SDK. `owned_by` is always `"flexai"` — clients branching on the legacy `"openai"` placeholder must update. operationId: listModels responses: '200': description: Successful response content: application/json: schema: type: object properties: object: type: string enum: - list data: type: array items: type: object required: - id - object - created - owned_by properties: id: type: string description: | Model id. Use this value as the `model` field in `/v1/chat/completions`. object: type: string enum: - model created: type: integer description: Unix timestamp. owned_by: type: string enum: - flexai description: | Constant `"flexai"`. (Earlier releases returned a legacy `"openai"` placeholder — clients branching on it must update.) hugging_face_id: type: string description: > HF Hub id when the model is published on Hugging Face. name: type: string description: Human-readable display label. category: type: string enum: - text - code - reasoning - multimodal - vision - embedding - image - audio - video description: > Model family / modality. Tells you which endpoint to call: `text`/`code`/`reasoning`/`multimodal`/`vision` → `/v1/chat/completions`; `embedding` → `/v1/embeddings`; `image` → `/v1/images/generations`; `audio` → `/v1/audio/speech` (text-to-speech) or `/v1/audio/transcriptions` (speech-to-text, when `input_modalities` includes `audio`); `video` → `/v1/videos/generations`. input_modalities: type: array items: type: string enum: - text - image - audio - file description: | Modalities the model accepts as input. output_modalities: type: array items: type: string enum: - text - image - video - audio - embedding description: | Modalities the model produces. quantization: type: string enum: - int4 - int8 - fp4 - fp6 - fp8 - fp16 - bf16 - fp32 description: | Weight precision. Omitted for quantization schemes whose precision varies per checkpoint (AWQ, GPTQ, MXFP4). context_length: type: integer description: Max context window in tokens. max_output_length: type: integer description: Max completion length in tokens. pricing: type: object description: | Per-token USD rates as decimal strings. Emitted when the model has at least one rate set. Zero-rated keys (request/image/web_search/ internal_reasoning) are included so the object always carries the full OpenRouter pricing shape. properties: prompt: type: string completion: type: string request: type: string image: type: string web_search: type: string internal_reasoning: type: string supported_features: type: array items: type: string enum: - tools - json_mode description: | OpenRouter feature flags. Tool-use and function-calling support both surface as `"tools"`. supported_sampling_parameters: type: array items: type: string description: | OpenAI sampling parameters the model accepts. Empty array for non-chat models (embeddings, TTS/STT, image/video gen, OCR) so clients reading this endpoint don't ask `bge-m3` for `temperature`. '401': $ref: '#/components/responses/Unauthorized' components: responses: Unauthorized: description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/Error' schemas: Error: type: object required: - error properties: error: type: object required: - message - type properties: message: type: string type: type: string example: invalid_request_error code: type: string description: | Stable machine-readable code for the failure. Present on most error paths; OMITTED on FastAPI default-validation bodies. Do not assume always present. doc_url: type: string format: uri description: | FlexAI extension. Link to the relevant dashboard / docs page for the failure mode (e.g. invalid key → /dashboard/keys). Present on auth and quota errors. securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: sk-xxxx description: | Virtual API key. Create one from the [FlexAI dashboard](https://tokens.flex.ai/dashboard/keys). Pass as `Authorization: Bearer sk-xxxx`. ````