> ## 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. # Generate an image > Generate one or more images from a text prompt. Beyond the standard fields, each model accepts its own **model-specific** sizing and quality parameters such as `resolution`, `aspect_ratio`, `width`/`height`, and `quality`. Send the ones your chosen model supports. Call `GET /v1/models` to see each model's supported parameters; pricing is shown on deepshi.ai and every response returns the actual `usage.cost`. Set `stream: true` for Server-Sent Events on slow, high-resolution generations. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/images/generations 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/images/generations: post: tags: - Images summary: Generate an image description: >- Generate one or more images from a text prompt. Beyond the standard fields, each model accepts its own **model-specific** sizing and quality parameters such as `resolution`, `aspect_ratio`, `width`/`height`, and `quality`. Send the ones your chosen model supports. Call `GET /v1/models` to see each model's supported parameters; pricing is shown on deepshi.ai and every response returns the actual `usage.cost`. Set `stream: true` for Server-Sent Events on slow, high-resolution generations. operationId: createImage requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ImageGenerationRequest' responses: '200': description: >- The generated image(s). When `stream: true`, the response is a Server-Sent Events stream (`text/event-stream`): periodic keepalive comments followed by a terminal `image_generation.completed` event carrying the final image (see the `ImageStreamEvent` schema). content: application/json: schema: $ref: '#/components/schemas/ImageResponse' text/event-stream: schema: $ref: '#/components/schemas/ImageStreamEvent' '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '402': $ref: '#/components/responses/InsufficientQuota' '403': $ref: '#/components/responses/Forbidden' '429': $ref: '#/components/responses/RateLimited' '500': $ref: '#/components/responses/InternalError' components: schemas: ImageGenerationRequest: type: object description: >- Image generation request. `model` and `prompt` are required. The remaining fields are optional; a model safely ignores any field it does not support. Model-specific sizing/quality fields (`width`/`height`, `aspect_ratio`, `resolution`, `quality`, `image_size`) apply only to the models that declare them — see `GET /v1/models`. Additional model-specific parameters not listed here may also be sent and are forwarded to the model. required: - model - prompt additionalProperties: true properties: model: type: string description: The image model id to use. See `GET /v1/models`. example: nano-banana-pro prompt: type: string description: Text description of the image to generate. example: a serene canal in Venice at sunset 'n': type: integer description: Number of images to generate (1–4). minimum: 1 maximum: 4 default: 1 response_format: type: string description: >- How images are returned. `url` returns an inline base64 `data:` URI, not a hosted link. enum: - b64_json - url default: b64_json output_format: type: string description: Encoding of the returned image. Not all models honor every format. enum: - png - jpeg - webp stream: type: boolean description: >- Stream the result as Server-Sent Events. Use it for slow, high-resolution generations that would otherwise time out. default: false seed: type: integer description: Seed for reproducible output. Omit for a random seed. width: type: integer description: >- Model-specific. Output width in pixels, for pixel-dimension models (e.g. `flux-2-pro`). height: type: integer description: Model-specific. Output height in pixels, for pixel-dimension models. aspect_ratio: type: string description: >- Model-specific. Aspect ratio for aspect-ratio and resolution-tier models. example: '16:9' resolution: type: string description: >- Model-specific. Resolution tier for resolution-tier models (e.g. `nano-banana-2`, `nano-banana-pro`, `grok-imagine-quality`). Determines the billed price for those models. example: 2K quality: type: string description: >- Model-specific. Quality tier for the GPT Image models (`gpt-image-1.5`, `gpt-image-2`). Higher tiers cost more, and the price depends on the image size and quality you pick. Omit to use the model's default tier. enum: - low - medium - high image_size: type: string description: >- Model-specific. Named output size for preset-size models (e.g. `seedream-4.5`). example: auto_2K ImageResponse: type: object properties: created: type: integer format: int64 description: Unix timestamp when the request was created. model: type: string description: The image model id you requested. size: type: string description: The actual output dimensions, as `WIDTHxHEIGHT`. data: type: array items: $ref: '#/components/schemas/ImageData' description: The generated image(s). usage: $ref: '#/components/schemas/Usage' ImageStreamEvent: type: object description: >- One Server-Sent Event from a streamed image request (`stream: true`). The stream sends keepalive comments, then a terminal `image_generation.completed` event carrying the final image and usage. Note the flat shape: `b64_json` is top-level here, not nested under `data[]` as in the non-streamed `ImageResponse`. properties: type: type: string description: Event type. example: image_generation.completed b64_json: type: string description: Base64-encoded image, present on the completed event. size: type: string description: Output dimensions of the image. example: 1024x1024 usage: $ref: '#/components/schemas/Usage' ImageData: type: object required: - index properties: b64_json: type: string nullable: true description: >- Base64-encoded image. Present when `response_format` is `b64_json` (the default). url: type: string nullable: true description: >- Inline `data:` URI for the image. Present when `response_format` is `url`. revised_prompt: type: string nullable: true description: The prompt actually used, if the model revised it. index: type: integer description: Position of this image in the batch. Usage: type: object description: Token usage and the billed cost for the request. properties: prompt_tokens: type: integer description: Total input tokens (includes any cached tokens). prompt_tokens_details: type: object properties: cached_tokens: type: integer cached_read_tokens: type: integer description: >- Tokens served from the prompt cache, billed at the cache-read rate. image_tokens: type: integer completion_tokens: type: integer description: >- Output tokens generated (includes reasoning tokens for reasoning models). completion_tokens_details: type: object properties: reasoning_tokens: type: integer image_tokens: type: integer total_tokens: type: integer cost: $ref: '#/components/schemas/Cost' 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. Cost: type: object description: >- Deepshi extension: the exact USD amount this request deducted from your balance. Standard OpenAI SDKs ignore it. properties: total_cost: type: number description: USD cost deducted from your balance for this request. example: 0.000135 responses: BadRequest: description: Malformed request, or a model id that doesn't exist in the catalog. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: The model does not exist or you do not have access to it. type: invalid_request_error code: model_not_found param: null 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 InsufficientQuota: description: The account is out of credits. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: You have insufficient credits to complete this request. type: insufficient_quota code: insufficient_quota param: null Forbidden: description: The key is revoked, or not permitted to use the requested model. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: The model does not exist or you do not have access to it. type: invalid_request_error code: model_not_found param: null RateLimited: description: Too many requests. Back off and retry. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: Rate limit reached. Please retry after a short delay. type: rate_limit_error code: rate_limit_exceeded 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 `.' ````