> ## Documentation Index > Fetch the complete documentation index at: https://docs.deepshi.ai/llms.txt > Use this file to discover all available pages before exploring further. > ## Agent Instructions > The Deepshi API is an OpenAI-compatible gateway. Base URL: https://api.deepshi.ai/v1. API keys start with sk-bf- and go in the Authorization: Bearer header. Prefer the official OpenAI SDKs pointed at the Deepshi base URL. Model ids are clean with no provider prefix (e.g. deepshi-3.0, claude-opus-4.8, gpt-5.5). Chat and image requests are synchronous; video and music requests are asynchronous job APIs (create, then poll). Every synchronous response carries usage.cost.total_cost in USD. Do not reference the internal /api/* admin plane or virtual keys. # List available models > Lists the models the authenticated key is allowed to call. Each entry's `id` is the value to pass as `model` on a request. ## OpenAPI ````yaml /api-reference/openapi.json get /v1/models openapi: 3.1.0 info: title: Deepshi API description: >- OpenAI-compatible REST API for Deepshi's own models and leading third-party models. Authenticate with your Deepshi API key as a bearer token, and reference a model by its id (e.g. `deepshi-3.0`, `gpt-4o`) in the `model` field. version: 1.0.0 servers: - url: https://api.deepshi.ai description: Deepshi API security: - BearerAuth: [] paths: /v1/models: get: tags: - Models summary: List available models description: >- Lists the models the authenticated key is allowed to call. Each entry's `id` is the value to pass as `model` on a request. operationId: listModels responses: '200': description: The list of models the key can use. content: application/json: schema: $ref: '#/components/schemas/ListModelsResponse' example: object: list data: - id: deepshi-3.0 object: model output_modalities: - text input_modalities: - text - image - id: claude-opus-4.8 object: model output_modalities: - text input_modalities: - text - image - id: grok-imagine-video object: model output_modalities: - video input_modalities: - text - image '401': $ref: '#/components/responses/Unauthorized' '500': $ref: '#/components/responses/InternalError' components: schemas: ListModelsResponse: type: object properties: object: type: string example: list data: type: array items: $ref: '#/components/schemas/Model' Model: type: object description: A model entry in the OpenAI `list` shape. properties: id: type: string description: The bare model id to pass as `model` (e.g. `deepshi-3.0`). example: deepshi-3.0 object: type: string example: model created: type: integer format: int64 owned_by: type: string example: deepshi parameters: type: object description: >- Image and media models only. The model's public configuration surface — the parameters you may send for this model, keyed by name. Each entry describes the parameter's type, allowed `values` (for enums) or range, and `default`. Use it to discover which sizing/quality fields a model accepts. Pricing is not included here; every response returns the actual `usage.cost`. additionalProperties: type: object properties: type: type: string description: '`enum`, `int`, `float`, `string`, or `boolean`.' values: type: array items: type: string description: Allowed values, for enum parameters. default: description: The value used when you omit the parameter. nullable: true example: resolution: type: enum values: - 1K - 2K - 4K default: 2K aspect_ratio: type: enum values: - auto - '16:9' - '1:1' - '9:16' default: auto edit: type: object description: >- Image and media models only. Reference-image edit capability for `/v1/images/edits`. properties: supported: type: boolean max_reference_images: type: integer description: Maximum reference images accepted. Absent when not applicable. example: supported: true max_reference_images: 14 prompt_max_length: type: integer description: >- Image and media models only. Maximum prompt length in characters. A longer prompt returns `400 PROMPT_TOO_LONG`. example: 50000 input_modalities: type: array items: type: string description: What the model accepts, e.g. `["text"]` or `["text", "image"]`. example: - text output_modalities: type: array items: type: string description: What the model produces, e.g. `["image"]`. example: - image Error: type: object description: Error envelope, matching the OpenAI shape. required: - error properties: error: type: object properties: message: type: string description: Human-readable description of the error. type: type: string description: >- Error category, e.g. `invalid_request_error` or `insufficient_quota`. code: type: string nullable: true description: >- Machine-readable error code, e.g. `invalid_api_key`, `model_not_found`, `insufficient_quota` (may be null). param: type: string nullable: true description: The request parameter the error relates to, when applicable. responses: Unauthorized: description: Missing, malformed, or unknown API key. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Incorrect API key provided. type: invalid_request_error code: invalid_api_key param: null InternalError: description: Temporary server error. Retry with backoff. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: >- The server had an error while processing your request. Please retry. type: api_error code: null param: null securitySchemes: BearerAuth: type: http scheme: bearer description: 'Your Deepshi API key, sent as `Authorization: Bearer `.' ````