> ## Documentation Index > Fetch the complete documentation index at: https://docs.omniall.ai/llms.txt > Use this file to discover all available pages before exploring further. # List models > Returns models available to the authenticated API key / user group. Response shape is selected by headers / query (same as routing in the gateway): - Default (Bearer / OpenAI-style): OpenAI list format (`object` + `data`) - `x-api-key` + `anthropic-version`: Anthropic-style list - `x-goog-api-key` or `key` query: Gemini-style list Use each model's `id` as the `model` field in chat, image, video, and other APIs. See also the Model Square: https://omniall.ai/pricing ## OpenAPI ````yaml openapi/xgapi-public.yaml GET /v1/models openapi: 3.0.3 info: title: Omniall AI Public API description: >- Omniall AI public API. Website: https://omniall.ai — API host: https://api.omniall.ai — Model Square: https://omniall.ai/pricing version: 1.1.0 servers: - url: https://api.omniall.ai description: Production security: - bearerAuth: [] tags: - name: Models description: List models available to your API key. - name: ChatGPT Chat Completions x-group: ChatGPT description: OpenAI Chat Completions (`POST /v1/chat/completions`). - name: Responses description: OpenAI Responses API (`POST /v1/responses`). - name: Claude description: Anthropic Messages API (`POST /v1/messages`). - name: Gemini description: Google Gemini generateContent / streamGenerateContent. - name: Images description: >- Image generation (OpenAI Images), vendor guides, and Midjourney proxy APIs. - name: Video description: Async video tasks. - name: Audio description: Speech and related audio APIs. - name: Rerank description: Document reranking. paths: /v1/models: get: tags: - Models summary: List models description: > Returns models available to the authenticated API key / user group. Response shape is selected by headers / query (same as routing in the gateway): - Default (Bearer / OpenAI-style): OpenAI list format (`object` + `data`) - `x-api-key` + `anthropic-version`: Anthropic-style list - `x-goog-api-key` or `key` query: Gemini-style list Use each model's `id` as the `model` field in chat, image, video, and other APIs. See also the Model Square: https://omniall.ai/pricing operationId: listModels parameters: - name: x-api-key in: header required: false description: > Anthropic-compatible API key. When present together with `anthropic-version`, the response uses Anthropic list format. The gateway also accepts this value as the token (equivalent to `Authorization: Bearer ...`). schema: type: string example: sk-xxxxxxxx - name: anthropic-version in: header required: false description: >- Anthropic API version header. Pair with `x-api-key` to request Anthropic response format. schema: type: string example: '2023-06-01' - name: x-goog-api-key in: header required: false description: >- Gemini-compatible API key. When present, the response uses Gemini list format. schema: type: string example: sk-xxxxxxxx - name: key in: query required: false description: >- Alternate Gemini-compatible API key (query). Same effect as `x-goog-api-key`. schema: type: string example: sk-xxxxxxxx responses: '200': description: > Success. Default body is OpenAI-compatible (`success`, `object`, `data`). Anthropic / Gemini shapes apply when the corresponding headers/query are used. content: application/json: schema: $ref: '#/components/schemas/ModelsListResponse' examples: openai: summary: OpenAI format (default) value: success: true object: list data: - id: gpt-4o-mini object: model created: 1626777600 owned_by: openai supported_endpoint_types: - openai - id: kling-2.5 object: model created: 1626777600 owned_by: custom supported_endpoint_types: - openai-video anthropic: summary: Anthropic format (x-api-key + anthropic-version) value: data: - id: claude-sonnet-4 created_at: '2021-07-20T00:00:00Z' display_name: claude-sonnet-4 type: model first_id: claude-sonnet-4 has_more: false last_id: claude-sonnet-4 gemini: summary: Gemini format (x-goog-api-key or key) value: models: - name: gemini-2.0-flash displayName: gemini-2.0-flash nextPageToken: null '401': description: Missing or invalid API key / token. content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' examples: missing_or_invalid: summary: Invalid token value: error: message: '无效的令牌 (request id: 20260302120000-xxxxxxxx)' type: new_api_error code: '' '403': description: > Authenticated but not allowed (for example user banned, IP not in token allowlist, or no access to the token's group). content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' examples: user_banned: summary: User disabled value: error: message: '该用户已被封禁 (request id: 20260302120000-xxxxxxxx)' type: new_api_error code: '' ip_denied: summary: IP not allowed by token value: error: message: '您的 IP 不在令牌允许访问的列表中 (request id: 20260302120000-xxxxxxxx)' type: new_api_error code: access_denied '500': description: >- Server / database error while validating the token or loading user data. content: application/json: schema: $ref: '#/components/schemas/OpenAIErrorResponse' example: error: message: '数据库错误 (request id: 20260302120000-xxxxxxxx)' type: new_api_error code: '' components: schemas: ModelsListResponse: type: object description: Default OpenAI-compatible model list response. required: - object - data properties: success: type: boolean description: >- Gateway success flag; `true` when the list was returned successfully. example: true object: type: string description: Always `list`. example: list data: type: array description: Array of models available to the current API key / group. items: $ref: '#/components/schemas/ModelObject' OpenAIErrorResponse: type: object description: OpenAI-style error envelope returned on auth/request failures. required: - error properties: error: type: object required: - message - type properties: message: type: string description: >- Human-readable error. The gateway may append a request id for support. type: type: string description: Error type, commonly `new_api_error`. example: new_api_error code: type: string description: >- Optional machine-readable code (e.g. `access_denied`). May be an empty string. description: Error object. ModelObject: type: object description: One model entry from `GET /v1/models`. required: - id - object - created - owned_by properties: id: type: string description: >- Model identifier. Copy this exact string into the `model` field of chat/image/video/audio requests. example: gpt-4o-mini object: type: string description: Always `model`. example: model created: type: integer description: Unix timestamp associated with the model metadata. example: 1626777600 owned_by: type: string description: >- Provider/owner label such as `openai`, `anthropic`, or `custom` for gateway-registered models. example: openai supported_endpoint_types: type: array description: >- Which Omniall endpoint families this model can use (e.g. `openai`, `anthropic`, `gemini`, `openai-video`). Helps you pick the correct API style. items: type: string enum: - openai - openai-response - openai-response-compact - anthropic - gemini - jina-rerank - image-generation - embeddings - openai-video example: - openai securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API Key description: 'Use Authorization: Bearer sk-... from https://omniall.ai/dashboard' ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.