# GlobalAI OPC

## Docs

- [SD2 Manxue: Batch Query Asset Moderation Review Status](https://docs.xingchaoyiqing.com/api-reference/assets/sd2-manxue-asset-status.md): Batch query moderation review status for SD2 Manxue assets by asset ID. Poll until status is Active before using assets in generation tasks.
- [SD2 Manxue: Submit Image, Video, or Audio for Review](https://docs.xingchaoyiqing.com/api-reference/assets/sd2-manxue-asset-upload.md): Batch submit image, video, and audio URLs for SD2 Manxue review. At least one array must be non-empty. Returns an assetId per submitted item.
- [Seedance 2.0: Permanently Delete an Asset by Asset ID](https://docs.xingchaoyiqing.com/api-reference/assets/seedance2-asset-delete.md): Permanently delete a Seedance 2.0 asset by ID. Deletion is irreversible — verify the asset is no longer needed before calling this endpoint.
- [Seedance 2.0: Get Asset Name, Status, Type, and URL](https://docs.xingchaoyiqing.com/api-reference/assets/seedance2-asset-detail.md): Retrieve details and current status for a Seedance 2.0 asset by ID. Poll until status is Active before referencing it in generation tasks.
- [Seedance 2.0: Upload an Asset to the Media Library](https://docs.xingchaoyiqing.com/api-reference/assets/seedance2-asset-upload.md): Upload an image, video, audio, or document asset to the Seedance 2.0 library and receive an assetId to reference in generation tasks.
- [GPT Image 2: Create an Async Image Generation Task](https://docs.xingchaoyiqing.com/api-reference/image/gpt-image2-create.md): POST /kyyReactApiServer/v1/image2/images — Generate images with GPT Image 2 using quality tiers, flexible sizing, and up to 16 reference images.
- [GPT Image 2: Query Image Generation Task and Result](https://docs.xingchaoyiqing.com/api-reference/image/gpt-image2-query.md): GET /kyyReactApiServer/v1/result/{id} — Poll a GPT Image 2 task for status and result. Returns image_url on completion. URLs expire in 24 hours.
- [Nano Banana: Create an Async Image Generation Task](https://docs.xingchaoyiqing.com/api-reference/image/nano-banana-create.md): POST /kyyReactApiServer/v1/banana/images — Submit an async Nano Banana image generation task. Supports up to 4K resolution and 6 reference images.
- [Nano Banana: Query Image Generation Task and Result](https://docs.xingchaoyiqing.com/api-reference/image/nano-banana-query.md): GET /kyyReactApiServer/v1/result/{id} — Poll a Nano Banana image task for status and result. Returns image_url on completion. URLs expire in 24 hours.
- [GlobalAI OPC API Reference: Endpoints and Integration](https://docs.xingchaoyiqing.com/api-reference/introduction.md): Complete API reference for GlobalAI OPC's text, image, and video generation endpoints. Supports OpenAI, Claude, and Gemini protocol compatibility.
- [Claude Messages API for AI Chat and Text Generation](https://docs.xingchaoyiqing.com/api-reference/text/claude-messages.md): POST /gw_llm_power/v1/messages — Send messages using the Anthropic Claude protocol. Supports Claude and GPT models with native Claude request format.
- [Gemini Native generateContent API — API Reference](https://docs.xingchaoyiqing.com/api-reference/text/gemini-native.md): POST /gw_llm_power/v1/models/{model}:generateContent — Use Gemini models natively with Google's protocol. Supports image and video analysis.
- [OpenAI Chat Completions API for GPT and Claude Models](https://docs.xingchaoyiqing.com/api-reference/text/openai-chat.md): POST /gw_llm_power/v1/chat/completions — Send chat messages and receive AI responses. Supports GPT, Claude, and Gemini models via the OpenAI protocol.
- [Grok: Create Video Generation Task (4 Models, Text + Image)](https://docs.xingchaoyiqing.com/api-reference/video/grok-create.md): POST /v1/grok/videos — Submit Grok video tasks with 4 model variants. Supports 6–30s duration, up to 7 reference images, and text-to-video mode.
- [Grok: Query Video Generation Task Status and Result](https://docs.xingchaoyiqing.com/api-reference/video/grok-query.md): GET /v1/result/{id} — Poll for Grok video generation status. Returns video_url on completion. Supports all four Grok model variants.
- [SD2 Manxue: Create Video Generation Task (720p to 4K)](https://docs.xingchaoyiqing.com/api-reference/video/sd2-manxue-create.md): POST /v1/sd2_manxue/videos — Generate 4–15s videos from 720p to 4K with SD2 Manxue. Supports text, first/last frame, and image, video, audio reference.
- [SD2 Manxue: Query Video Generation Task Status and Result](https://docs.xingchaoyiqing.com/api-reference/video/sd2-manxue-query.md): GET /v1/result/{id} — Poll for SD2 Manxue video generation status. Returns video_url and actualDuration on completion. Result links are temporary.
- [Seedance 1.5 Video Generation — Create Task API Reference](https://docs.xingchaoyiqing.com/api-reference/video/seedance-create.md): POST /v1/seedance/videos — Generate Seedance 1.5 videos via a content array. Supports text-to-video, first/last frame, and reference image input modes.
- [Seedance 1.5 Video Generation — Query Task and Status](https://docs.xingchaoyiqing.com/api-reference/video/seedance-query.md): GET /v1/result/{id} — Poll for Seedance 1.5 video status. Returns video_url on completion. Status can also be cancelled. Results expire after 1 day.
- [Seedance 2.0 Video Generation — Create Task API Reference](https://docs.xingchaoyiqing.com/api-reference/video/seedance2-create.md): POST /v1/kyyvideo2/videos — Create a Seedance 2.0 video task. Pro models need no reference video; standard models require one. Supports multi-modal inputs.
- [Seedance 2.0 Video Generation — Query Task and Status](https://docs.xingchaoyiqing.com/api-reference/video/seedance2-query.md): GET /v1/result/{id} — Poll for Seedance 2.0 video task status. Returns video_url and totalTokens when completed. Download the MP4 within 1 day.
- [Sora Video Generation — Create Task API Reference Guide](https://docs.xingchaoyiqing.com/api-reference/video/sora-create.md): POST /v1/sora/videos — Generate 4, 8, or 12-second videos with OpenAI Sora. Set model, aspect ratio, duration, and optionally attach a reference image.
- [Sora Video Generation — Query Task Status and Result](https://docs.xingchaoyiqing.com/api-reference/video/sora-query.md): GET /v1/result/{id} — Poll for Sora video task status. Returns video_url when completed. Download the MP4 within 1 day before the link expires.
- [StarVideos O3: Create Video Task (Text, Image, Frame Modes)](https://docs.xingchaoyiqing.com/api-reference/video/starvideos-create.md): POST /v1/starvideos/videos — Generate 3–15s videos with starvideos_o3. Supports text, multi-image reference, first/last frame, and video reference.
- [StarVideos O3: Query Video Generation Task Status and Result](https://docs.xingchaoyiqing.com/api-reference/video/starvideos-query.md): GET /v1/result/{id} — Poll for StarVideos O3 video generation status. Returns video_url and actualDuration when the task completes.
- [VEO Video Generation — Create a Task API Reference](https://docs.xingchaoyiqing.com/api-reference/video/veo-create.md): POST /v1/veo/videos — Generate 8-second videos with Google VEO. Supports 720p, 1080p, and 4K using reference images or first/last frame pin mode.
- [VEO Video Generation — Query Task Status and Result](https://docs.xingchaoyiqing.com/api-reference/video/veo-query.md): GET /v1/result/{id} — Poll for VEO video task status. Returns video_url when completed. All VEO outputs are fixed 8-second MP4; download within 24 hours.
- [Videos API: Create Video Generation Task (Standard and Fast)](https://docs.xingchaoyiqing.com/api-reference/video/videos-create.md): POST /v1/videos/videos — Generate 4–15s 720p videos with the Videos or Videos Fast model. Supports text, first/last frame, and multi-modal reference.
- [Videos API: Query Video Generation Task Status and Result](https://docs.xingchaoyiqing.com/api-reference/video/videos-query.md): GET /v1/result/{id} — Poll for Videos model generation status. Returns video_url and actualDuration on completion. Poll every 30–60 seconds.
- [Vidu: Create Video Generation Task (Text, Image, Frames)](https://docs.xingchaoyiqing.com/api-reference/video/vidu-create.md): POST /v1/vidu/videos — Generate 1–16s videos at 540p–1080p. Supports text-to-video, image-to-video, and first/last frame guidance.
- [Vidu: Query Video Generation Task Status and Result](https://docs.xingchaoyiqing.com/api-reference/video/vidu-query.md): GET /v1/result/{id} — Poll for Vidu video generation status. Returns video_url and totalTokens on completion. Generated URLs are valid for 24 hours.
- [Upload and Manage Media Assets for Video Generation](https://docs.xingchaoyiqing.com/guides/asset-management.md): Upload, track, and manage media assets (images, videos, audio) used as references in Seedance 2.0 and SD2 Manxue video generation tasks.
- [Understanding Async Task Processing in GlobalAI OPC](https://docs.xingchaoyiqing.com/guides/async-tasks.md): Video and image generation in GlobalAI OPC uses async task processing. Submit a task, receive an ID, then poll for results until completion.
- [GlobalAI OPC API Authentication: Keys and Best Practices](https://docs.xingchaoyiqing.com/guides/authentication.md): All GlobalAI OPC endpoints require a Bearer token in the Authorization header. Learn how to set your API key securely and handle common auth errors.
- [GlobalAI OPC API Changelog: Updates and Release Notes](https://docs.xingchaoyiqing.com/guides/changelog.md): Track new models, API updates, and feature additions in GlobalAI OPC. Stay up to date with the latest capabilities and breaking changes.
- [GlobalAI OPC: Text, Image, and Video Generation APIs](https://docs.xingchaoyiqing.com/guides/introduction.md): GlobalAI OPC provides video, image, and text AI generation APIs through a unified OpenAI-compatible gateway supporting Sora, VEO, Claude, GPT, and more.
- [All AI Models Available Through GlobalAI OPC Gateway](https://docs.xingchaoyiqing.com/guides/models-overview.md): Compare all video, image, and text AI models available through GlobalAI OPC, including Sora, VEO, Seedance, Vidu, Grok, GPT, Claude, and Gemini.
- [GlobalAI OPC Quickstart: Your First API Call in Minutes](https://docs.xingchaoyiqing.com/guides/quickstart.md): Make your first text, image, and video generation API calls with GlobalAI OPC. Covers obtaining an API key, choosing a model, and polling for results.