> ## 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. # Chat image generation ## One endpoint, multiple use cases `POST /v1/chat/completions` covers **text-to-image** and **image-to-image** (plus multi-image / PDF / short-video references). They differ only in `messages` content — not separate APIs. | Use case | `messages[].content` | | - | - | | Text-to-image | Plain string, or only `type: text` | | Image-to-image | `text` + `image_url` (one or more) | | PDF reference (Banana 2.1) | `text` + `file` | | Short video (Banana 2.1) | `text` + `video_url` (**string**) | Gateway flow: Chat `messages` → download URL / decode data URL → Gemini `inlineData` → upstream `generateContent`. Remote PDF / video URLs are supported; they are **not** forwarded as `fileUri`. | Media | Content type | Value | | - | - | - | | Image | `image_url` | HTTPS URL or `data:image/...;base64,...` | | PDF | `file` | `filename` + `file_data` (HTTPS URL or `data:application/pdf;base64,...`) | | Video | `video_url` | **String** HTTPS URL or `data:video/mp4;base64,...` | ### PDF URL (complete) ```json theme={null} { "model": "gemini-nano-banana-2.1", "stream": false, "extra_body": { "google": { "image_config": { "aspect_ratio": "3:2", "image_size": "1K" } } }, "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Read the PDF. List labels, colors and shapes by page, then generate a reference-sheet image on a white background." }, { "type": "file", "file": { "filename": "reference.pdf", "file_data": "https://example.com/reference.pdf" } } ] } ] } ``` ### Video URL (complete) ```json theme={null} { "model": "gemini-nano-banana-2.1", "stream": false, "extra_body": { "google": { "image_config": { "aspect_ratio": "3:2", "image_size": "1K" } } }, "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Watch the video. List scene elements in order, then generate a reference-sheet image." }, { "type": "video_url", "video_url": "https://example.com/clip.mp4" } ] } ] } ``` ```bash theme={null} curl --fail-with-body --max-time 180 \ "https://api.omniall.ai/v1/chat/completions" \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ --data-binary @request.json ``` Notes: URLs must be publicly downloadable; default download limit is about 64MB per file; prefer short MP4 / small PDF. Pass `video_url` as a string, not `{ "url": "..." }`. ### Optional: Thinking Banana 2.1 supports thinking levels `minimal` / `medium` (default) / `high` via `extra_body.google.thinking_config` (snake\_case): ```json theme={null} "extra_body": { "google": { "image_config": { "aspect_ratio": "3:2", "image_size": "1K" }, "thinking_config": { "thinking_level": "high", "include_thoughts": false } } } ``` `include_thoughts` only controls whether thought text is returned; you can omit `thinking_config` for typical use. See [Overview · Thinking](/api-reference/image-gemini#optional-thinking-levels). ## OpenAPI ````yaml openapi/gemini-chat-image-en.yaml POST /v1/chat/completions openapi: 3.1.0 info: title: Omniall AI — Gemini Chat image generation version: 1.2.0 description: > Generate images with Gemini through a single OpenAI Chat Completions endpoint. **Path:** `POST https://api.omniall.ai/v1/chat/completions` Text-to-image, image-to-image, multi-image reference, and PDF / short-video reference are the **same API** with different `messages` payloads. Model examples: `gemini-nano-banana-2.1`, `gemini-3.1-flash-image-preview`, `gemini-3-pro-image-preview`. Use `extra_body.google.image_config` for `aspect_ratio` and `image_size` (`1K`/`2K`/`4K`). Optional Thinking (Banana 2.1): `extra_body.google.thinking_config.thinking_level` = `minimal` / `medium` (default) / `high`; `include_thoughts` only controls whether thought text is returned (snake_case). `messages[].content` part types: - plain string or `type: text` — prompt / edit instruction - `image_url` — reference image (HTTPS URL or data URL) - `file` — PDF (`file_data` HTTPS URL or `data:application/pdf;base64,...`; `filename` required) - `video_url` — short video (**string** HTTPS URL or `data:video/mp4;base64,...`) The gateway downloads remote URLs and converts them to Gemini `inlineData`. Auth: `Authorization: Bearer sk-...` servers: - url: https://api.omniall.ai security: [] paths: /v1/chat/completions: post: tags: - Gemini image summary: Chat image generation description: > Gemini image generation via OpenAI Chat Completions. Text-to-image and image-to-image share this endpoint. **Path:** `POST https://api.omniall.ai/v1/chat/completions` - **Text-to-image**: `content` as a plain string, or only `type: text` - **Image-to-image / multi-ref**: `content` array with `text` + one or more `image_url` - **PDF / short video** (Banana 2.1): add `type: file` / `type: video_url` Prefer non-streaming `stream: false`. Auth: `Authorization: Bearer sk-...` operationId: geminiChatImage parameters: - name: Authorization in: header required: true schema: type: string example: Bearer sk-... description: Bearer API key, e.g. `Bearer sk-...`. requestBody: required: true content: application/json: schema: type: object required: - model - messages description: Gemini Chat image request body (`POST /v1/chat/completions`). properties: model: type: string description: >- Gemini image model id. Examples: `gemini-nano-banana-2.1`, `gemini-3.1-flash-image-preview`. example: gemini-3.1-flash-image-preview messages: type: array description: >- Chat messages. Text-to-image is usually one `user` text; image-to-image adds media parts. items: type: object properties: role: type: string description: Use `user` for image generation. example: user content: oneOf: - type: string description: Plain-text prompt (text-to-image). - type: array description: >- Multimodal parts — `text`, `image_url`, `file` (PDF), `video_url`. items: type: object properties: type: type: string enum: - text - image_url - file - video_url text: type: string image_url: type: object properties: url: type: string description: >- HTTPS image URL or `data:image/...;base64,...`. required: - url file: type: object description: >- PDF / document part. Both `filename` and `file_data` are required. properties: filename: type: string example: reference.pdf file_data: type: string description: >- HTTPS PDF URL or `data:application/pdf;base64,...`. required: - filename - file_data video_url: type: string description: >- Video string — HTTPS URL or `data:video/mp4;base64,...`. required: - role - content stream: type: boolean description: >- Whether to stream. Prefer `false` for Chat image generation (one-shot complete response). default: false example: false extra_body: type: object description: Provider extensions under `extra_body.google`. properties: google: type: object properties: image_config: type: object description: >- Output aspect ratio and resolution. camelCase aliases also accepted. properties: aspect_ratio: type: string enum: - '1:1' - '2:3' - '3:2' - '3:4' - '4:3' - '4:5' - '5:4' - '9:16' - '16:9' - '21:9' example: '1:1' image_size: type: string enum: - 1K - 2K - 4K example: 2K thinking_config: type: object description: > Optional. Banana 2.1 Thinking (snake_case). `thinking_level`: `minimal` / `medium` (default) / `high`. properties: thinking_level: type: string enum: - minimal - medium - high example: high include_thoughts: type: boolean example: false examples: Text-to-image: summary: Text-to-image (plain text) value: model: gemini-3.1-flash-image-preview messages: - role: user content: >- An orange cat sleeping under cherry blossoms, Japanese illustration, soft light stream: false extra_body: google: image_config: aspect_ratio: '1:1' image_size: 2K Image-to-image: summary: Image-to-image (image URL) value: model: gemini-3.1-flash-image-preview messages: - role: user content: - type: text text: >- Generate three orthographic views of this object on one canvas, pure white background - type: image_url image_url: url: https://example.com/reference.jpg stream: false extra_body: google: image_config: aspect_ratio: '16:9' image_size: 2K Multi-image reference: summary: Multi-image reference value: model: gemini-3.1-flash-image-preview messages: - role: user content: - type: text text: >- Using the style and layout of the following images, generate a unified product poster - type: image_url image_url: url: https://example.com/ref-style.jpg - type: image_url image_url: url: https://example.com/ref-layout.jpg stream: false extra_body: google: image_config: aspect_ratio: '16:9' image_size: 2K PDF URL reference: summary: PDF URL reference (Banana 2.1) value: model: gemini-nano-banana-2.1 messages: - role: user content: - type: text text: >- Read the PDF. List labels, colors and shapes by page, then generate a reference-sheet image on a white background. - type: file file: filename: reference.pdf file_data: https://example.com/reference.pdf stream: false extra_body: google: image_config: aspect_ratio: '3:2' image_size: 1K Short video reference: summary: Video URL reference (Banana 2.1) value: model: gemini-nano-banana-2.1 messages: - role: user content: - type: text text: >- Watch the video. List scene elements in order, then generate a reference-sheet image. - type: video_url video_url: https://example.com/clip.mp4 stream: false extra_body: google: image_config: aspect_ratio: '3:2' image_size: 1K responses: '200': description: Chat Completions response (SSE when streaming). content: application/json: schema: type: object additionalProperties: true '400': description: Invalid request '401': description: Unauthorized '429': description: Rate limited '500': description: Upstream/gateway error ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.