> ## Documentation Index > Fetch the complete documentation index at: https://edenai-auto-update-feature-docs.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Image Generations > OpenAI-compatible image generation endpoint. ## OpenAPI ````yaml https://api.edenai.run/v3/docs/openapi.json post /v3/images/generations openapi: 3.1.0 info: title: Eden AI API V3 version: 3.0.0 servers: - url: https://api.edenai.run description: Production server security: [] paths: /v3/images/generations: post: tags: - Images summary: Image Generations description: OpenAI-compatible image generation endpoint. operationId: image_generations_v3_images_generations_post requestBody: content: application/json: schema: $ref: '#/components/schemas/ImageGenerationBody' required: true responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ImageResponse' '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - AuthBearer: [] components: schemas: ImageGenerationBody: properties: routing: anyOf: - $ref: '#/components/schemas/ProviderRoutingPreferences' - type: 'null' description: >- How to pick between the providers that serve the requested model. Applies when `model` is a model name with no provider prefix (e.g. 'gpt-5.5'); ignored for a concrete 'provider/model' id, which already names its provider. With model='@edenai' the platform chooses the model too: `quality_cost` steers that choice, and the provider fields apply whenever the chosen model is a provider-less name. model: type: string title: Model description: provider/model, e.g. 'openai/gpt-image-2' prompt: type: string maxLength: 32000 minLength: 1 title: Prompt 'n': anyOf: - type: integer maximum: 10 minimum: 1 - type: 'null' title: 'N' size: anyOf: - type: string - type: 'null' title: Size description: >- Provider-specific size string. OpenAI accepts '1024x1024', '1536x1024', '1024x1536', 'auto'. Vertex Imagen accepts square or aspect-ratio strings. Validation is delegated to the provider. user: anyOf: - type: string - type: 'null' title: User description: End-user identifier for abuse tracking. metadata: anyOf: - additionalProperties: true type: object - type: 'null' title: Metadata description: Arbitrary metadata attached to the request. extra_headers: anyOf: - additionalProperties: type: string type: object - type: 'null' title: Extra Headers description: >- Additional HTTP headers forwarded to the provider API. Credential headers (Authorization, x-api-key, ...) are rejected. quality: anyOf: - type: string - type: 'null' title: Quality description: >- Provider-specific quality string (e.g. 'low', 'medium', 'high', 'standard', 'hd', 'auto'). Accepted values depend on the model. response_format: anyOf: - type: string - type: 'null' title: Response Format description: >- Legacy DALL-E parameter. Ignored by gpt-image-* and forwarded to the provider for any model that still honors it. additionalProperties: true type: object required: - model - prompt title: ImageGenerationBody description: OpenAI-compatible ``POST /v1/images/generations`` request body. ImageResponse: properties: cost: anyOf: - type: number - type: 'null' title: Cost provider: anyOf: - type: string - type: 'null' title: Provider created: anyOf: - type: integer - type: 'null' title: Created data: items: $ref: '#/components/schemas/ImageDataItem' type: array title: Data usage: anyOf: - additionalProperties: true type: object - type: 'null' title: Usage additionalProperties: true type: object title: ImageResponse description: >- OpenAI-compatible image response + Eden ``cost`` / ``provider`` fields. Shared by ``POST /v3/images/generations`` and ``POST /v3/images/edits`` — the wire shape is identical. HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ProviderRoutingPreferences: properties: sort: anyOf: - type: string enum: - cost - speed - latency - exact - type: 'null' title: Sort description: >- What to optimise for when several providers serve the requested model. 'cost' (default) picks the cheapest for this request's shape; 'speed' the highest tokens/second; 'latency' the fastest to first token; 'exact' the most reliable at producing well-formed tool calls / structured output. Health is always a filter first — no mode will route you to a failing provider. Can also be written as a model suffix, e.g. 'gpt-5.5:speed'. sticky: anyOf: - type: boolean - type: 'null' title: Sticky description: >- Keep a conversation on the provider holding its prompt cache. On by default, and only ever active for models whose providers discount cache reads. Set false to route every request independently on price instead. Naming an explicit `sort` also takes priority over cache affinity. allow_fallbacks: type: boolean title: Allow Fallbacks description: >- Whether other providers of the same model may be tried when the chosen one fails. Set false to pin the request to the single best provider: it then fails rather than silently moving to another seller. useful when a cache-warm prompt would cold-miss elsewhere. This governs PROVIDERS of the requested model only; models you list in `fallbacks` are your own choice and are always kept. default: true quality_cost: anyOf: - type: integer maximum: 10 minimum: 0 - type: 'null' title: Quality Cost description: >- Only with model='@edenai': how far to trade answer quality for cost when the platform chooses the MODEL. 0 asks for the best model for the request, 10 for the cheapest model that can still handle it, values in between blend the two; omit it to leave the choice to the platform (quality first). This is the one `routing` field that steers the model rather than the provider — `sort` never changes which model is chosen. allowed_providers: anyOf: - items: type: string type: array - type: 'null' title: Allowed Providers description: >- Restrict routing to these providers, e.g. ['openai', 'anthropic']. Only providers that serve the requested model are considered, so an entry that does not sell it is simply inert. If none of them do, the request fails rather than falling back to a provider you excluded. Case-insensitive. Applies to routed providers only. a concrete 'provider/model' you named in `fallbacks` is your own choice and is kept. type: object title: ProviderRoutingPreferences description: >- How to choose between SELLERS of one model — and, with ``@edenai``, how far to trade quality for cost when the platform chooses the model. The seller fields are only meaningful when `model` is a canonical name (`gpt-5.5`) rather than a concrete `provider/model` — with a concrete id there is nothing to choose between. For choosing the MODEL itself see ``router_candidates`` and ``model="@edenai"``, which is a different router; ``quality_cost`` below is the one field here that speaks to it. ImageDataItem: properties: url: anyOf: - type: string - type: 'null' title: Url b64_json: anyOf: - type: string - type: 'null' title: B64 Json revised_prompt: anyOf: - type: string - type: 'null' title: Revised Prompt additionalProperties: true type: object title: ImageDataItem description: |- Single image entry inside the OpenAI-shaped ``data: [...]`` array. Providers return either ``url`` (most non-OpenAI providers) or ``b64_json`` (gpt-image-*); ``revised_prompt`` is OpenAI-specific. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError securitySchemes: AuthBearer: type: http scheme: bearer ````