# OctopusX API

## Docs

- [Authentication Methods](https://doc.octopusx.ai/en/account/authentication.md): Explains Bearer Token, native-compatible authentication headers, login session state, and OAuth browser flows.
- [Account Balance and Usage](https://doc.octopusx.ai/en/account/billing.md): Query the remaining quota at the API Key level, as well as OpenAI-compatible subscription and usage information.
- [Account Management Overview](https://doc.octopusx.ai/en/account/overview.md): Summary of authentication headers, OAuth state flow, token usage, and OpenAI-compatible balance query interfaces.
- [Doubao Seedream Image Generation API](https://doc.octopusx.ai/en/images/doubao-seedream/generation.md): Use `POST /v1/images/generations` to call the Doubao Seedream series image generation endpoint.
- [Gemini Image Generation API](https://doc.octopusx.ai/en/images/gemini-image/generation.md): Use `POST /v1beta/models/{model}:generateContent` to call the Gemini image generation API, covering `gemini-3-pro-image-preview`, `gemini-2.5-flash-image-preview`, and `gemini-3.1-flash-image-preview` in a unified way.
- [OpenAI Images Compatible Image Editing](https://doc.octopusx.ai/en/images/gpt-image-1/edit.md): Use `POST /v1/images/edits` or `POST /v1/edits` to perform editing, inpainting, and image-to-image generation based on existing images.
- [OpenAI Images Compatible Image Generation](https://doc.octopusx.ai/en/images/gpt-image-1/generation.md): Use `POST /v1/images/generations` to call the unified image generation entry point, and select compatible models such as `gpt-image-1`, `dall-e-3`, and `dall-e-2` via `model`.
- [OpenAI Images Compatibility Overview](https://doc.octopusx.ai/en/images/gpt-image-1/overview.md): Organizes the unified image generation and editing APIs for `gpt-image-1`, `dall-e-3`, `dall-e-2`, and more through a compatibility entrypoint.
- [gpt-image-2-pro Image Generation API](https://doc.octopusx.ai/en/images/gpt-image-2-pro/generation.md): Use `POST /v1/images/generations` to call the high-resolution image generation entry for `gpt-image-2-pro`.
- [gpt-image-2 Image Generation API](https://doc.octopusx.ai/en/images/gpt-image-2/generation.md): Use `POST /v1/images/generations` to call the unified image generation entry for `gpt-image-2`.
- [Jimeng Image Editing](https://doc.octopusx.ai/en/images/jimeng/edit.md): Use `POST /v1/images/edits` to generate a new image by editing based on a reference image.
- [Jimeng Image Generation](https://doc.octopusx.ai/en/images/jimeng/generation.md): Use `POST /v1/images/generations` to call the Jimeng model for image generation.
- [Jimeng Official Format Image Generation](https://doc.octopusx.ai/en/images/jimeng/official-generation.md): Generate images using the official Jimeng format interface via `POST /jm`.
- [Jimeng Official Format Query Task](https://doc.octopusx.ai/en/images/jimeng/official-query.md): Use `POST /jm` to query the status and result of Jimeng official format tasks.
- [Jimeng Image Overview](https://doc.octopusx.ai/en/images/jimeng/overview.md): Jimeng Image provides two integration methods: an OpenAI-compatible interface and an official format, supporting both image generation and image editing.
- [Midjourney Overview](https://doc.octopusx.ai/en/images/midjourney/overview.md): A summary of Midjourney task submission, task querying, image proxying, and common return codes.
- [Midjourney Task Query](https://doc.octopusx.ai/en/images/midjourney/query.md): Query Midjourney single tasks, batch tasks, and task image seed.
- [Midjourney Task Submission](https://doc.octopusx.ai/en/images/midjourney/submit.md): Submit Midjourney imagine, blend, modal, describe, shorten, swap face, video, and Discord image upload tasks.
- [Image Model Support Matrix](https://doc.octopusx.ai/en/images/model-matrix.md): Summarizes the model families, entry routes, image-to-image capabilities, size, and aspect ratio constraints currently supported by image-related interfaces.
- [Image Series Overview](https://doc.octopusx.ai/en/images/overview.md): Summarizes image capability entry points grouped by model, including Gemini, GPT Image, Jimeng Image, Doubao Seedream, OpenAI Images compatible routes, and Midjourney routes.
- [Poly Exploration API Documentation](https://doc.octopusx.ai/en/index.md): A unified API platform for developers, providing capabilities such as text, image, video, audio, file upload, task processing, and account management, helping developers quickly build AI applications and automated workflows.
- [Task Management Overview](https://doc.octopusx.ai/en/tasks/overview.md): Summary of the query entry points for video tasks and Suno tasks.
- [General Chat Completions API (Default Non-Streaming)](https://doc.octopusx.ai/en/texts/chat-completions-non-stream.md): Use the OpenAI Chat Completions-compatible format to initiate a conversation and return the full result in one response.
- [Chat Completions API (Default Streaming)](https://doc.octopusx.ai/en/texts/chat-completions-stream.md): Start a conversation using the OpenAI Chat Completions-compatible format and return model output via SSE streaming.
- [Claude Messages API](https://doc.octopusx.ai/en/texts/claude-messages.md): Call Claude models using Anthropic Messages native format.
- [Text Completion API](https://doc.octopusx.ai/en/texts/completions.md): Generate text using the OpenAI Legacy Completions compatible format.
- [Gemini Native Format](https://doc.octopusx.ai/en/texts/gemini-native.md): Use Google Gemini native paths and request bodies to call generateContent, streamGenerateContent, and model queries.
- [Text Model Support Matrix](https://doc.octopusx.ai/en/texts/model-matrix.md): Summarizes the protocol styles, typical model families, capability coverage, and recommended entry points currently supported by the text model APIs.
- [Model List](https://doc.octopusx.ai/en/texts/models.md): Query the models available to the current API Key, compatible with OpenAI, Claude, and Gemini styles.
- [OpenAI Multimodal Responses API](https://doc.octopusx.ai/en/texts/openai-responses.md): Create responses using the OpenAI Responses API format, with support for multimodal input, tool calling, streaming output, and context compression.
- [Overview of Text Series](https://doc.octopusx.ai/en/texts/overview.md): The text series covers OpenAI-compatible text interfaces, Claude native message interface, Gemini native interface, OpenAI Responses, multimodal input, model list, and Realtime.
- [Realtime API](https://doc.octopusx.ai/en/texts/realtime.md): Use the OpenAI Realtime-compatible WebSocket route for real-time interactions.
- [Upload Image](https://doc.octopusx.ai/en/uploads/image-upload.md): Call `/api/upload/presign` to generate a pre-signed upload URL, then pass the returned `public_url` to interfaces that accept public asset URLs.
- [Upload Management Overview](https://doc.octopusx.ai/en/uploads/overview.md): A summary of object storage presigned upload APIs and how they integrate with image and video tasks.
- [Overview of Domestic Video Models](https://doc.octopusx.ai/en/videos/aigc/overview.md): A summary of the integration methods, model naming, parameter specifications, and query workflows for domestic video model series.
- [Video Extend](https://doc.octopusx.ai/en/videos/grok/extend.md): Use `POST /v1/videos/{video_id}/extend` to extend a segment based on an existing Grok video task.
- [Video Extensions](https://doc.octopusx.ai/en/videos/grok/extensions.md): Use `POST /v1/videos/extensions` to extend a segment of a specified Grok video task.
- [Grok Video Generation](https://doc.octopusx.ai/en/videos/grok/generation.md): Use `POST /v1/videos` to invoke the Grok video series models and submit asynchronous generation tasks.
- [Grok Video Overview](https://doc.octopusx.ai/en/videos/grok/overview.md): A model-series-organized overview of Grok's OpenAI format and unified video interfaces.
- [Grok Task Query](https://doc.octopusx.ai/en/videos/grok/query.md): Query Grok video task progress, results, and error information using `GET /v1/videos/{task_id}`.
- [Video Remix](https://doc.octopusx.ai/en/videos/grok/remix.md): Submit a remix based on an existing Grok video task using `POST /v1/videos/{video_id}/remix`.
- [Video Extend](https://doc.octopusx.ai/en/videos/grok/unified-extend.md): Use `POST /v1/video/extend` to extend segments of an existing Grok task via the unified video format.
- [Video Extensions](https://doc.octopusx.ai/en/videos/grok/unified-extensions.md): Use `POST /v1/videos/extensions` to perform segment extension for Grok tasks under the unified video pipeline.
- [Create Video](https://doc.octopusx.ai/en/videos/grok/unified-generation.md): Use `POST /v1/video/create` to submit Grok asynchronous generation tasks through a unified video format.
- [Query Task](https://doc.octopusx.ai/en/videos/grok/unified-query.md): Use `GET /v1/video/query` to query Grok unified video task status and results.
- [Video Remix](https://doc.octopusx.ai/en/videos/grok/unified-remix.md): Use `POST /v1/video/remix` to submit remix requests for existing Grok tasks through the unified video format.
- [Doubao Video Generation](https://doc.octopusx.ai/en/videos/jimeng/doubao-generation.md): Use `POST /v1/videos` to call the Doubao model and submit asynchronous video tasks.
- [Doubao Task Status Query](https://doc.octopusx.ai/en/videos/jimeng/doubao-query.md): Use `GET /v1/videos/{task_id}` to query Doubao video task status and results.
- [Jimeng Video Generation](https://doc.octopusx.ai/en/videos/jimeng/generation.md): Use `POST /v1/videos` to call the Jimeng model and submit asynchronous video tasks.
- [Jimeng Video Overview](https://doc.octopusx.ai/en/videos/jimeng/overview.md): Organizes Jimeng Video's three integration methods by model series: OpenAI format, unified video, and Doubao channel.
- [Jimeng Task Status Query](https://doc.octopusx.ai/en/videos/jimeng/query.md): Use `GET /v1/videos/{task_id}` to query Jimeng video task status and results.
- [Create Video](https://doc.octopusx.ai/en/videos/jimeng/unified-generation.md): Use `POST /v1/video/create` to submit Jimeng asynchronous generation tasks through the unified video format.
- [Query Task](https://doc.octopusx.ai/en/videos/jimeng/unified-query.md): Use `GET /v1/video/query` to query the status and result of a Jimeng unified video task.
- [Kling Video Generation](https://doc.octopusx.ai/en/videos/kling/generation.md): Use `POST /v1/videos` to call the Kling model and submit asynchronous video tasks.
- [Kling Video Overview](https://doc.octopusx.ai/en/videos/kling/overview.md): Organize Kling's OpenAI-format interfaces by model series.
- [Kling Task Status Query](https://doc.octopusx.ai/en/videos/kling/query.md): Use `GET /v1/videos/{task_id}` to query Kling video task status and results.
- [Video Model Support Matrix](https://doc.octopusx.ai/en/videos/model-matrix.md): A summary of the recommended entry points, generation modes, reference image passing methods, and duration limits for the current video model series.
- [Video Series Overview](https://doc.octopusx.ai/en/videos/overview.md): A summary of video API documentation organized by model series.
- [Create Asset Group](https://doc.octopusx.ai/en/videos/seedance-2/asset-create-group.md): Create a Seedance asset group using `POST /v1/seedance/asset/CreateAssetGroup`.
- [Upload Assets](https://doc.octopusx.ai/en/videos/seedance-2/asset-create-media.md): Use `POST /v1/seedance/asset/CreateAsset` to import public assets into the Seedance asset library.
- [Query Asset](https://doc.octopusx.ai/en/videos/seedance-2/asset-get.md): Query Seedance asset import status and details using `POST /v1/seedance/asset/GetAsset`.
- [Create Video](https://doc.octopusx.ai/en/videos/seedance-2/generation.md): Submit a Seedance 2.0 multimodal video generation task using `POST /v1/video/generations`.
- [Seedance-2 Overview](https://doc.octopusx.ai/en/videos/seedance-2/overview.md): Summarizes the Seedance 2.0 asset management and video generation APIs.
- [Query Task](https://doc.octopusx.ai/en/videos/seedance-2/query.md): Use `GET /v1/video/generations/{task_id}` to query the status and result of a Seedance 2.0 video generation task.
- [Sora Video Generation](https://doc.octopusx.ai/en/videos/sora/generation.md): Use `POST /v1/videos` to call the Sora model and submit asynchronous video tasks.
- [Sora Video Overview](https://doc.octopusx.ai/en/videos/sora/overview.md): Organize Sora's OpenAI format and unified video interface by model series.
- [Sora Task Query](https://doc.octopusx.ai/en/videos/sora/query.md): Use `GET /v1/videos/{task_id}` to query Sora video task status and results.
- [Create Video](https://doc.octopusx.ai/en/videos/sora/unified-generation.md): Use `POST /v1/video/create` to submit Sora asynchronous generation tasks via the unified video format.
- [Query Task](https://doc.octopusx.ai/en/videos/sora/unified-query.md): Use `GET /v1/video/query` to query the status and result of a Sora unified video task.
- [Veo Video Generation](https://doc.octopusx.ai/en/videos/veo/generation.md): Use `POST /v1/videos` to call the Veo model and submit asynchronous video tasks.
- [Veo Video Overview](https://doc.octopusx.ai/en/videos/veo/overview.md): OpenAI format and unified video interface for Veo, organized by model series.
- [Veo Task Query](https://doc.octopusx.ai/en/videos/veo/query.md): Use `GET /v1/videos/{task_id}` to query Veo video task status and results.
- [Video Remix](https://doc.octopusx.ai/en/videos/veo/remix.md): Submit a remix extension based on an existing Veo video task using `POST /v1/videos/{video_id}/remix`.
- [Create Video](https://doc.octopusx.ai/en/videos/veo/unified-generation.md): Use `POST /v1/video/create` to submit Veo asynchronous generation tasks through a unified video format.
- [Query Task](https://doc.octopusx.ai/en/videos/veo/unified-query.md): Use `GET /v1/video/query` to query the status and result of Veo unified video tasks.
- [Vidu Image-to-Video](https://doc.octopusx.ai/en/videos/vidu/img2video.md): Submit a first-frame image video generation task using `POST /vidu/ent/v2/img2video`.
- [Vidu Video Overview](https://doc.octopusx.ai/en/videos/vidu/overview.md): Official Vidu format, OpenAI format, and unified video interface organized by model series.
- [Vidu Task Query](https://doc.octopusx.ai/en/videos/vidu/query.md): Use `GET /vidu/ent/v2/task/{task_id}/creations` to query Vidu task status and results.
- [Vidu Reference-to-Video](https://doc.octopusx.ai/en/videos/vidu/reference2video.md): Use `POST /vidu/ent/v2/reference2video` to submit a subject-reference video generation task.
- [Vidu Start and End Frame Video Generation](https://doc.octopusx.ai/en/videos/vidu/start-end2video.md): Use `POST /vidu/ent/v2/start-end2video` to submit a start-and-end-frame video generation task.
- [Vidu Text-to-Video](https://doc.octopusx.ai/en/videos/vidu/text2video.md): Use `POST /vidu/ent/v2/text2video` to submit a pure-text video generation task.
- [Create Video](https://doc.octopusx.ai/en/videos/vidu/unified-generation.md): Use `POST /v1/video/create` to submit Vidu asynchronous generation tasks through the unified video format.
- [Query Task](https://doc.octopusx.ai/en/videos/vidu/unified-query.md): Use `GET /v1/video/query` to query the status and result of a Vidu unified video task.
- [Vidu Video Generation](https://doc.octopusx.ai/en/videos/vidu/vidu-generation.md): Use `POST /v1/videos` to call the Vidu model and submit asynchronous video tasks.
- [Vidu Task Status Query](https://doc.octopusx.ai/en/videos/vidu/vidu-query.md): Use `GET /v1/videos/{task_id}` to query Vidu video task status and results.