# DataEyesAI ## Docs - Documentation > Getting Started [Overview](https://doc.dataeyes.vip/doc-9565764.md): - Documentation > Getting Started [Console (Getting Started)](https://doc.dataeyes.vip/doc-9565765.md): - Documentation > Getting Started [API Key](https://doc.dataeyes.vip/doc-9565766.md): - Documentation > Getting Started [Base URL](https://doc.dataeyes.vip/doc-9565767.md): - Documentation > Developer Tool Integration [OpenClaw](https://doc.dataeyes.vip/doc-9565768.md): - Documentation > Developer Tool Integration [Claude Code](https://doc.dataeyes.vip/doc-9565769.md): - Documentation > Developer Tool Integration [Codex](https://doc.dataeyes.vip/doc-9565770.md): - Documentation > Developer Tool Integration [Gemini CLI](https://doc.dataeyes.vip/doc-9565771.md): - Documentation > Developer Tool Integration [Grok CLI](https://doc.dataeyes.vip/doc-9565772.md): - Documentation > Developer Tool Integration [Other Tools](https://doc.dataeyes.vip/doc-9565773.md): - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Completions [ChatGPT automatic completion ](https://doc.dataeyes.vip/doc-9565774.md): - Documentation > AI Models API > Midjourney format [Midjourney API Reference](https://doc.dataeyes.vip/doc-9565775.md): - Documentation > AI Models API > Video Model > Grok Video Generation [00-Overview](https://doc.dataeyes.vip/doc-9565776.md): - Documentation > AI Models API > Video Model > Grok Video Generation [01-Text-to-Video](https://doc.dataeyes.vip/doc-9565777.md): - Documentation > AI Models API > Video Model > Grok Video Generation [02-Image-to-Video](https://doc.dataeyes.vip/doc-9565778.md): - Documentation > AI Models API > Video Model > Grok Video Generation [03-Reference-to-Video](https://doc.dataeyes.vip/doc-9565779.md): - Documentation > AI Models API > Video Model > Grok Video Generation [04-Video-Editing](https://doc.dataeyes.vip/doc-9565780.md): - Documentation > AI Models API > Video Model > Grok Video Generation [05-Video-Extension](https://doc.dataeyes.vip/doc-9565781.md): - Documentation > AI Models API > Video Model > Seedance Video Generation [00-Overview](https://doc.dataeyes.vip/doc-9565782.md): - Documentation > AI Models API > Video Model > Seedance Video Generation [01-Create-Video-Generation-Task](https://doc.dataeyes.vip/doc-9565783.md): - Documentation > AI Models API > Video Model > Seedance Video Generation [02-Query-Video-Generation-Task](https://doc.dataeyes.vip/doc-9565784.md): - Documentation > AI Models API > Video Model > Seedance Video Generation [03-Query-Video-Generation-Task-List](https://doc.dataeyes.vip/doc-9565785.md): - Documentation > AI Models API > Video Model > Seedance Video Generation [04-Cancel-or-Delete-Task](https://doc.dataeyes.vip/doc-9565786.md): - Documentation > AI Models API > Video Model > Seedance Video Generation [Seedance Private Asset Library API Documentation](https://doc.dataeyes.vip/doc-9565787.md): - Documentation > AI Models API > Video Model > MiniMax-H3 Video Generation [00-Overview](https://doc.dataeyes.vip/doc-9565788.md): - Documentation > AI Models API > Video Model > MiniMax-H3 Video Generation [01-Create-Video-Generation](https://doc.dataeyes.vip/doc-9565789.md): - Documentation > AI Models API > Video Model > MiniMax-H3 Video Generation [02-Create-Video-Regeneration](https://doc.dataeyes.vip/doc-9565790.md): - Documentation > AI Models API > Video Model > MiniMax-H3 Video Generation [03-Create-H3-Context-IR](https://doc.dataeyes.vip/doc-9565791.md): - Documentation > AI Models API > Video Model > MiniMax-H3 Video Generation [04-Query-Task](https://doc.dataeyes.vip/doc-9565792.md): - Documentation > AI Models API > Video Model > MiniMax-H3 Video Generation [05-List-Tasks](https://doc.dataeyes.vip/doc-9565793.md): - Documentation > AI Models API > Video Model > MiniMax-H3 Video Generation [06-Cancel-or-Delete-Task](https://doc.dataeyes.vip/doc-9565794.md): - Documentation > AI Models API > Video Model > Hailuo Video Generation [00-Overview](https://doc.dataeyes.vip/doc-9565795.md): - Documentation > AI Models API > Video Model > Hailuo Video Generation [01-Text-to-Video-T2V](https://doc.dataeyes.vip/doc-9565796.md): - Documentation > AI Models API > Video Model > Hailuo Video Generation [02-Image-to-Video-I2V](https://doc.dataeyes.vip/doc-9565797.md): - Documentation > AI Models API > Video Model > Hailuo Video Generation [03-First-Last-Frame-FL2V](https://doc.dataeyes.vip/doc-9565798.md): - Documentation > AI Models API > Video Model > Hailuo Video Generation [04-Subject-Reference-S2V](https://doc.dataeyes.vip/doc-9565799.md): - Documentation > AI Models API > Video Model > Hailuo Video Generation [05-Query-Task-Status](https://doc.dataeyes.vip/doc-9565800.md): - Documentation > AI Models API > Video Model > Hailuo Video Generation [06-Video-Download](https://doc.dataeyes.vip/doc-9565801.md): - Documentation > AI Models API > Video Model > Hailuo Video Generation [99-Appendix-Camera-Movement-and-Webhooks](https://doc.dataeyes.vip/doc-9565802.md): - Documentation > AI Models API > Video Model > Jimeng Video Generation [00-Overview](https://doc.dataeyes.vip/doc-9565803.md): - Documentation > AI Models API > Video Model > Jimeng Video Generation [01-3.0-Pro-Video-Generation](https://doc.dataeyes.vip/doc-9565804.md): - Documentation > AI Models API > Video Model > Jimeng Video Generation [02-720P-Text-to-Video](https://doc.dataeyes.vip/doc-9565805.md): - Documentation > AI Models API > Video Model > Jimeng Video Generation [03-720P-Image-to-Video-First-Frame](https://doc.dataeyes.vip/doc-9565806.md): - Documentation > AI Models API > Video Model > Jimeng Video Generation [04-720P-Image-to-Video-Start-End-Frame](https://doc.dataeyes.vip/doc-9565807.md): - Documentation > AI Models API > Video Model > Jimeng Video Generation [05-720P-Image-to-Video-Camera](https://doc.dataeyes.vip/doc-9565808.md): - Documentation > AI Models API > Video Model > Jimeng Video Generation [06-1080P-Text-to-Video](https://doc.dataeyes.vip/doc-9565809.md): - Documentation > AI Models API > Video Model > Jimeng Video Generation [07-1080P-Image-to-Video-First-Frame](https://doc.dataeyes.vip/doc-9565810.md): - Documentation > AI Models API > Video Model > Jimeng Video Generation [08-1080P-Image-to-Video-Start-End-Frame](https://doc.dataeyes.vip/doc-9565811.md): - Documentation > AI Models API > Video Model > Jimeng Video Generation [09-Error-Codes](https://doc.dataeyes.vip/doc-9565812.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [00-Overview](https://doc.dataeyes.vip/doc-9565813.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [01-Text-to-Video](https://doc.dataeyes.vip/doc-9565814.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [02-Image-to-Video](https://doc.dataeyes.vip/doc-9565815.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [03-Omni-Video](https://doc.dataeyes.vip/doc-9565816.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [04-Multi-Image-to-Video](https://doc.dataeyes.vip/doc-9565817.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [05-Motion-Control](https://doc.dataeyes.vip/doc-9565818.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [06-Multi-Elements](https://doc.dataeyes.vip/doc-9565819.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [07-Video-Extension](https://doc.dataeyes.vip/doc-9565820.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [08-Lip-Sync](https://doc.dataeyes.vip/doc-9565821.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [09-Avatar](https://doc.dataeyes.vip/doc-9565822.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [10-Text-to-Audio](https://doc.dataeyes.vip/doc-9565823.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [11-Video-to-Audio](https://doc.dataeyes.vip/doc-9565824.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [12-TTS](https://doc.dataeyes.vip/doc-9565825.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [13-Custom-Voices](https://doc.dataeyes.vip/doc-9565826.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [14-Image-Recognition](https://doc.dataeyes.vip/doc-9565827.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [15-Element-Management](https://doc.dataeyes.vip/doc-9565828.md): - Documentation > AI Models API > Video Model > Kling AI Video Generation [16-Video-Effects](https://doc.dataeyes.vip/doc-9565829.md): - Documentation > AI Models API > Video Model > Vidu Video Generation [00-Overview](https://doc.dataeyes.vip/doc-9565830.md): - Documentation > AI Models API > Video Model > Vidu Video Generation [01-Text-to-Video](https://doc.dataeyes.vip/doc-9565831.md): - Documentation > AI Models API > Video Model > Vidu Video Generation [02-Image-to-Video](https://doc.dataeyes.vip/doc-9565832.md): - Documentation > AI Models API > Video Model > Vidu Video Generation [03-Reference-to-Video](https://doc.dataeyes.vip/doc-9565833.md): - Documentation > AI Models API > Video Model > Vidu Video Generation [04-Start-End-Frame](https://doc.dataeyes.vip/doc-9565834.md): - Documentation > AI Models API > Video Model > Vidu Video Generation [05-Multi-Frame](https://doc.dataeyes.vip/doc-9565835.md): - Documentation > AI Models API > Video Model > Vidu Video Generation [06-Scene-Template](https://doc.dataeyes.vip/doc-9565836.md): - Documentation > AI Models API > Video Model > Vidu Video Generation [07-Template-Story](https://doc.dataeyes.vip/doc-9565837.md): - Documentation > AI Models API > Video Model > Vidu Video Generation [08-Query-Tasks](https://doc.dataeyes.vip/doc-9565838.md): - Documentation > AI Models API > Video Model > HappyHorse [HappyHorse Text-to-Video](https://doc.dataeyes.vip/doc-9565839.md): - Documentation > AI Models API > Video Model > HappyHorse [HappyHorse Image-to-Video (First Frame)](https://doc.dataeyes.vip/doc-9565840.md): - Documentation > AI Models API > Video Model > HappyHorse [HappyHorse Reference-to-Video](https://doc.dataeyes.vip/doc-9565841.md): - Documentation > AI Models API > Video Model > HappyHorse [HappyHorse Video Editing](https://doc.dataeyes.vip/doc-9565842.md): - Documentation > AI Models API > Video Model > Wan Video Generation [00-Overview.md](https://doc.dataeyes.vip/doc-9565843.md): - Documentation > AI Models API > Video Model > Wan Video Generation [01-Text-to-Video](https://doc.dataeyes.vip/doc-9565844.md): - Documentation > AI Models API > Video Model > Wan Video Generation [02-Image-to-Video](https://doc.dataeyes.vip/doc-9565845.md): - Documentation > AI Models API > Video Model > Wan Video Generation [03-Reference-to-Video](https://doc.dataeyes.vip/doc-9565846.md): - Documentation > AI Models API > Video Model > Wan Video Generation [04-Video-Editing](https://doc.dataeyes.vip/doc-9565847.md): - Documentation > AI Models API > Video Model > Wan Video Generation [05-First-Last-Frame-to-Video](https://doc.dataeyes.vip/doc-9565848.md): - Documentation > AI Models API > Video Model > Wan Video Generation [06-Motion-Transfer-and-Character-Swap](https://doc.dataeyes.vip/doc-9565849.md): - Documentation > AI Models API > Video Model > Wan Video Generation [07-Digital-Human-Video](https://doc.dataeyes.vip/doc-9565850.md): - Documentation > AI Models API > Video Model > Wan Video Generation [08-VACE-Video-Editing](https://doc.dataeyes.vip/doc-9565851.md): - Documentation > AI Models API > Video Model > Wan Video Generation [09-Query-Task](https://doc.dataeyes.vip/doc-9565852.md): - Documentation > AI Models API > Audio API [Audio API](https://doc.dataeyes.vip/doc-9565853.md): - Documentation > AI Models API > Audio API [Gemini TTS API](https://doc.dataeyes.vip/doc-9565854.md): - Documentation > AI Models API > Audio API [Google DeepMind Lyria API](https://doc.dataeyes.vip/doc-9565855.md): - Documentation > AI Models API > Audio API [Elevenlabs Speech to Text API Reference](https://doc.dataeyes.vip/doc-9565856.md): - Documentation > Search / Reader Product > Web Search API​​ > Modal Card API > Weather [All City ID](https://doc.dataeyes.vip/doc-9565857.md): - Documentation > Advanced & System API [Data Updates](https://doc.dataeyes.vip/doc-9565858.md): - Documentation > Advanced & System API > System interface [API Key & Quota Query API](https://doc.dataeyes.vip/doc-9565859.md): - Documentation > Advanced & System API > System interface [API Key Management API](https://doc.dataeyes.vip/doc-9565860.md): - Documentation > Advanced & System API > API Reference​​ [Error Codes](https://doc.dataeyes.vip/doc-9565861.md): - Documentation > Advanced & System API > API Reference​​ [HTTP Notes](https://doc.dataeyes.vip/doc-9565862.md): - Terms & Policies [DataEyesAI API Terms of Service](https://doc.dataeyes.vip/doc-9565863.md): - Terms & Policies [DataEyesAI Legal Notice and Privacy Policy](https://doc.dataeyes.vip/doc-9565864.md): - Terms & Policies [DataEyesAI Paid Services Agreement](https://doc.dataeyes.vip/doc-9565865.md): - Terms & Policies [Automatic Renewal Service Rules](https://doc.dataeyes.vip/doc-9565866.md): ## API Docs - Documentation > AI Models API > OpenAI format (supports major original models) > Chat (Response) [Create Network Search](https://doc.dataeyes.vip/api-526172079.md): https://platform.openai.com/docs/api-reference/responses/create - Documentation > AI Models API > OpenAI format (supports major original models) > Chat (Response) [Create Model Response GPT-5 Enable Thinking](https://doc.dataeyes.vip/api-526172080.md): https://platform.openai.com/docs/api-reference/responses/create - Documentation > AI Models API > OpenAI format (supports major original models) > Chat (Response) [Create Function Call](https://doc.dataeyes.vip/api-526172081.md): https://platform.openai.com/docs/api-reference/responses/create - Documentation > AI Models API > OpenAI format (supports major original models) > Chat (Response) [Create Model Response](https://doc.dataeyes.vip/api-526172082.md): https://platform.openai.com/docs/api-reference/responses/create - Documentation > AI Models API > OpenAI format (supports major original models) > Chat (Response) [Create Model Response (Streaming Return)](https://doc.dataeyes.vip/api-526172083.md): https://platform.openai.com/docs/api-reference/responses/create - Documentation > AI Models API > OpenAI format (supports major original models) > Chat (Response) [Create Model Response (Control Thinking Length)](https://doc.dataeyes.vip/api-526172084.md): https://platform.openai.com/docs/api-reference/responses/create - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Audio [Audio to text gpt-4o-transcribe](https://doc.dataeyes.vip/api-526172085.md): Official documentation: https://platform.openai.com/docs/guides/speech-to-text - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Audio [GPT-4o-audio](https://doc.dataeyes.vip/api-526172086.md): Official documentation: https://platform.openai.com/docs/api-reference/chat/create - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Audio [Audio to text whisper-1](https://doc.dataeyes.vip/api-526172087.md): Official documentation: https://platform.openai.com/docs/guides/speech-to-text - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Audio [Audio to text gpt-4o-transcribe](https://doc.dataeyes.vip/api-526172088.md): Official documentation: https://platform.openai.com/docs/guides/speech-to-text - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Audio [Create voice gpt-4o-mini-tts](https://doc.dataeyes.vip/api-526172089.md): Official documentation: https://platform.openai.com/docs/guides/text-to-speech - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Chat [Create chat-based image recognition (non-streaming)](https://doc.dataeyes.vip/api-526172090.md): Given a prompt, the model will return one or more predicted completions and can also provide the probabilities of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Chat [Create chat-based image recognition (streaming)](https://doc.dataeyes.vip/api-526172091.md): Given a prompt, the model will return one or more predicted completions and can also provide the probabilities of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Chat [Create chat-based image recognition (streaming) best64](https://doc.dataeyes.vip/api-526172092.md): Given a prompt, the model will return one or more predicted completions and can also provide the probabilities of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Chat [Official N test](https://doc.dataeyes.vip/api-526172093.md): Given a prompt, the model will return one or more predicted completions and can also return the probability of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Chat [Create structured output](https://doc.dataeyes.vip/api-526172094.md): Given a prompt, the model will return one or more predicted completions and can also provide the probabilities of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Chat [Control the effort level of the inference model](https://doc.dataeyes.vip/api-526172095.md): Given a prompt, the model will return one or more predicted completions and can also provide the probabilities of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Chat [Create chat function call](https://doc.dataeyes.vip/api-526172096.md): Given a prompt, the model will return one or more predicted completions and can also provide the probabilities of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Chat [deepseek-ocr recognition](https://doc.dataeyes.vip/api-526172097.md): Given a prompt, the model will return one or more predicted completions and can also provide the probabilities of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Chat [Create chat completion (non-stream)](https://doc.dataeyes.vip/api-526172098.md): Given a prompt, the model will return one or more predicted completions and can also provide the probabilities of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > ChatGPT Interface > Completions [Create completion](https://doc.dataeyes.vip/api-526172099.md): Given a prompt, the model will return one or more predicted completions and can also provide the probabilities of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > Image [Edit image](https://doc.dataeyes.vip/api-526172100.md): Edit images - Documentation > AI Models API > OpenAI format (supports major original models) > Image [Create chat completion (streaming)](https://doc.dataeyes.vip/api-526172101.md): Given a prompt, the model will return one or more predicted completions and can also provide the probabilities of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > Image [Create chat completion (qwen-mt-turbo)](https://doc.dataeyes.vip/api-526172102.md): Given a prompt, the model will return one or more predicted completions and can also provide the probabilities of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > Image [Create chat completion with deepseek v3.1 level of reasoning (streaming)](https://doc.dataeyes.vip/api-526172103.md): - Documentation > AI Models API > OpenAI format (supports major original models) > Audio [Speech recognition](https://doc.dataeyes.vip/api-526172104.md): Supports speech recognition and is compatible with whisper-1, gpt-4o-transcribe, and gpt-4o-mini-transcribe. - Documentation > AI Models API > OpenAI format (supports major original models) > Audio [Speech synthesis](https://doc.dataeyes.vip/api-526172105.md): Supports OpenAI's official tts models: tts-1, tts-1-hd, or gpt-4o-mini-tts - Documentation > AI Models API > OpenAI format (supports major original models) > Audio [Official Function Calling invocation](https://doc.dataeyes.vip/api-526172106.md): Given a prompt, the model will return one or more predicted completions and can also provide the probability of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > Audio [Create chat-generated images (non-streaming)](https://doc.dataeyes.vip/api-526172107.md): Given a prompt, the model will return one or more predicted completions and can also provide the probability of alternative tokens at each position. - Documentation > AI Models API > OpenAI format (supports major original models) > Embedding [Text embeddings](https://doc.dataeyes.vip/api-526172108.md): Obtain vector representations for the given input text, which can be easily used by machine learning models and algorithms. - Documentation > AI Models API > Anthropic format [Chat](https://doc.dataeyes.vip/api-526172109.md): Basic text conversation, only supports Claude series models - Documentation > AI Models API > Anthropic format [Chat(prompt cache)](https://doc.dataeyes.vip/api-526172110.md): By setting the parameter: "cache_control": {"type": "ephemeral"}, prompt cache mode can be supported - Documentation > AI Models API > Anthropic format [Streaming response](https://doc.dataeyes.vip/api-526172111.md): Text conversation with streaming response. - Documentation > AI Models API > Anthropic format [Chat (deep reasoning)](https://doc.dataeyes.vip/api-526172112.md): Claude models that support thinking mode are required, such as: claude-sonnet-4-20250514-thinking - Documentation > AI Models API > Anthropic format [Tool invocation (function call)](https://doc.dataeyes.vip/api-526172113.md): Invoke functions - Documentation > AI Models API > Anthropic format [Analyze image](https://doc.dataeyes.vip/api-526172114.md): - Documentation > AI Models API > Google Gemini interface > Native format [Text-to-image + control over aspect ratio + clarity](https://doc.dataeyes.vip/api-526172115.md): Use Google's image generation models: gemini-2.5-flash-image (Banana), gemini-3-pro-image-preview (BananaPro) to support clarity control as follows: - Documentation > AI Models API > Google Gemini interface > Native format [Generate image](https://doc.dataeyes.vip/api-526172116.md): Use Google's image generation model: gemini-2.5-flash-image-preview - Documentation > AI Models API > Google Gemini interface > Native format [Text generation](https://doc.dataeyes.vip/api-526172117.md): Official documentation: https://ai.google.dev/gemini-api/docs/text-generation?hl=en#multi-turn-conversations - Documentation > AI Models API > Google Gemini interface > Native format [Text generation - stream](https://doc.dataeyes.vip/api-526172118.md): Official documentation: https://ai.google.dev/gemini-api/docs/text-generation?hl=en#multi-turn-conversations - Documentation > AI Models API > Google Gemini interface > Native format [Text generation + reasoning - stream](https://doc.dataeyes.vip/api-526172119.md): Official documentation：https://ai.google.dev/gemini-api/docs/text-generation?hl=zh-cn#multi-turn-conversations - Documentation > AI Models API > Google Gemini interface > Native format [Image generation](https://doc.dataeyes.vip/api-526172120.md): - Documentation > AI Models API > Google Gemini interface > Native format [Formatted output](https://doc.dataeyes.vip/api-526172121.md): - Documentation > AI Models API > Google Gemini interface > Native format [Function call](https://doc.dataeyes.vip/api-526172122.md): - Documentation > AI Models API > Google Gemini interface > Native format [Document understanding](https://doc.dataeyes.vip/api-526172123.md): Official documentation: https://ai.google.dev/gemini-api/docs/document-processing?hl=en - Documentation > AI Models API > Google Gemini interface > Native format [URL context [native format]](https://doc.dataeyes.vip/api-526172124.md): Official documentation: https://ai.google.dev/gemini-api/docs/document-processing?hl=zh-cn - Documentation > AI Models API > Google Gemini interface > Native format [Code execution](https://doc.dataeyes.vip/api-526172125.md): Official documentation: https://ai.google.dev/gemini-api/docs/document-processing?hl=zh-cn - Documentation > AI Models API > Google Gemini interface > Native format [Video understanding](https://doc.dataeyes.vip/api-526172126.md): Official documentation: https://ai.google.dev/gemini-api/docs/video-understanding?hl=zh-cn - Documentation > AI Models API > Google Gemini interface > Native format [URL context](https://doc.dataeyes.vip/api-526172127.md): Official documentation: https://ai.google.dev/gemini-api/docs/url-context?hl=en - Documentation > AI Models API > Google Gemini interface > Native format [Video understanding - url [native format]](https://doc.dataeyes.vip/api-526172128.md): Official documentation: https://ai.google.dev/gemini-api/docs/video-understanding?hl=zh-cn - Documentation > AI Models API > Google Gemini interface > Native format [Imagen 4](https://doc.dataeyes.vip/api-526172129.md): Official documentation: https://ai.google.dev/gemini-api/docs/image-generation?hl=zh-cn - Documentation > AI Models API > Google Gemini interface > Native format [Audio understanding](https://doc.dataeyes.vip/api-526172130.md): Official documentation: https://ai.google.dev/gemini-api/docs/url-context?hl=zh-cn - Documentation > AI Models API > Google Gemini interface > Native format [Embeddings](https://doc.dataeyes.vip/api-526172131.md): Official documentation: https://ai.google.dev/gemini-api/docs/text-generation?hl=zh-cn#multi-turn-conversations - Documentation > AI Models API > Google Gemini interface > Native format [Chat](https://doc.dataeyes.vip/api-526172132.md): Please replace the model name in {model-name} in the interface. - Documentation > AI Models API > Google Gemini interface > Native format [Edit image](https://doc.dataeyes.vip/api-526172133.md): - Documentation > AI Models API > Google Gemini interface > Image-to-image Base64 request method [Multi-image fusion slice generation with gemini-3-pro-image-preview, controlling aspect ratio and clarity](https://doc.dataeyes.vip/api-526172134.md): Official documentation: https://ai.google.dev/gemini-api/docs/image-generation?hl=zh-cn#gemini-image-editing - Documentation > AI Models API > Google Gemini interface > Image-to-image Base64 request method [Image editing](https://doc.dataeyes.vip/api-526172135.md): Official documentation: https://ai.google.dev/gemini-api/docs/image-generation?hl=zh-cn#gemini-image-editing - Documentation > AI Models API > Google Gemini interface > Image-to-image Base64 request method [Single image gemini-3-pro-image-preview, controlling aspect ratio and clarity.](https://doc.dataeyes.vip/api-526172136.md): Official documentation: https://ai.google.dev/gemini-api/docs/image-generation?hl=zh-cn#gemini-image-editing - Documentation > AI Models API > Google Gemini interface > Image-to-image Base64 request method [Image generation（ gemini-2.5-flash-image）](https://doc.dataeyes.vip/api-526172137.md): Official documentation: https://ai.google.dev/gemini-api/docs/image-generation?hl=zh-cn#gemini-image-editing - Documentation > AI Models API > Google Gemini interface > Image-to-image Base64 request method [Image generation gemini-2.5-flash-image, controlling aspect ratio.](https://doc.dataeyes.vip/api-526172138.md): - Documentation > AI Models API > Google Gemini interface > Image-to-image Base64 request method [Image understanding](https://doc.dataeyes.vip/api-526172139.md): Official documentation: https://ai.google.dev/gemini-api/docs/image-understanding?hl=zh-cn - Documentation > AI Models API > Google Gemini interface > Image-to-image URL request returns URL request format OpenAI [Single image generation with gemini-3-pro-image-preview, controlling aspect ratio and clarity.](https://doc.dataeyes.vip/api-526172140.md): Official documentation: https://ai.google.dev/gemini-api/docs/image-generation?hl=zh-cn#gemini-image-editing - Documentation > AI Models API > Google Gemini interface > Image-to-image URL request returns URL request format OpenAI [Multi-image fusion slice generation with gemini-3-pro-image-preview, controlling aspect ratio and clarity.](https://doc.dataeyes.vip/api-526172141.md): Official documentation: https://ai.google.dev/gemini-api/docs/image-generation?hl=zh-cn#gemini-image-editing - Documentation > AI Models API > Google Gemini interface > Image-to-image URL request returns URL request format OpenAI [Image understanding](https://doc.dataeyes.vip/api-526172142.md): Official documentation: https://ai.google.dev/gemini-api/docs/image-understanding?hl=zh-cn - Documentation > AI Models API > NanoBanana > OpenAI request [Edit image](https://doc.dataeyes.vip/api-526172143.md): Create edited or extended images based on the given original image and prompts. - Documentation > AI Models API > NanoBanana > OpenAI request [OpenAI image format](https://doc.dataeyes.vip/api-526172144.md): Enter the model name for model, for example: nano-banana. - Documentation > AI Models API > NanoBanana > Gemini request [Generate image](https://doc.dataeyes.vip/api-526172145.md): Use Google's image generation model: nano-banana - Documentation > AI Models API > NanoBanana > Gemini request [Edit image](https://doc.dataeyes.vip/api-526172146.md): Use Google's image model: nano-banana - Documentation > AI Models API > Midjourney format [Task query interface](https://doc.dataeyes.vip/api-526172147.md): Query task information by task ID. (You can poll this interface to check the progress of the task, or use a callback interface to obtain it.) - Documentation > AI Models API > Midjourney format [Upload image](https://doc.dataeyes.vip/api-526172148.md): Official documentation: https://docs.midjourney.com/hc/en-us/articles/33329380893325-Managing-Image-Uploads - Documentation > AI Models API > Midjourney format [Get seed (Seed)](https://doc.dataeyes.vip/api-526172149.md): - Documentation > AI Models API > Midjourney format [Submit Imagine task](https://doc.dataeyes.vip/api-526172150.md): Official documentation: https://docs.midjourney.com/hc/en-us/articles/32023408776205-Prompt-Basics - Documentation > AI Models API > Midjourney format [Query tasks based on ID list](https://doc.dataeyes.vip/api-526172151.md): - Documentation > AI Models API > Midjourney format [FaceSwap](https://doc.dataeyes.vip/api-526172152.md): Submit a FaceSwap task to perform face swapping. - Documentation > AI Models API > Midjourney format [Execute Action operation](https://doc.dataeyes.vip/api-526172153.md): Official documentation: https://docs.midjourney.com/hc/en-us/articles/32804058614669-Upscalers - Documentation > AI Models API > Midjourney format [/mj/submit/blend](https://doc.dataeyes.vip/api-526172154.md): Official documentation: https://docs.midjourney.com/hc/en-us/articles/32635189884557-Blend-Images-on-Discord - Documentation > AI Models API > Midjourney format [Submit Describe task](https://doc.dataeyes.vip/api-526172155.md): Official documentation: https://docs.midjourney.com/hc/en-us/articles/32497889043981-Describe - Documentation > AI Models API > Midjourney format [Submit Modal](https://doc.dataeyes.vip/api-526172156.md): - Documentation > AI Models API > Midjourney format [Refresh link](https://doc.dataeyes.vip/api-526172157.md): You can use this interface to refresh image links and obtain new links. - Documentation > AI Models API > Midjourney format [Edit image ](https://doc.dataeyes.vip/api-526172158.md): Use the edit interface to modify externally provided images. You can perform partial repainting or directly alter the image. - Documentation > AI Models API > Midjourney format [Query task status by task ID](https://doc.dataeyes.vip/api-526172159.md): - Documentation > AI Models API > Midjourney format [Get the seed of the task image](https://doc.dataeyes.vip/api-526172160.md): - Documentation > AI Models API > Doubao - Painting [doubao-seededit-3-0-i2i-250628](https://doc.dataeyes.vip/api-526172161.md): Given prompts and/or input images, the model will generate new images. - Documentation > AI Models API > Doubao - Painting [doubao-seedream-4-0-250828 - text-to-image](https://doc.dataeyes.vip/api-526172162.md): - Documentation > AI Models API > Doubao - Painting [doubao-seedream-4-0-250828 - image-to-image](https://doc.dataeyes.vip/api-526172163.md): Given prompts and/or input images, the model will generate new images. - Documentation > AI Models API > Doubao - Painting [doubao-seedream-4-0-250828 - multi-image generation](https://doc.dataeyes.vip/api-526172164.md): Given a prompt and/or input image, the model will generate a new image. - Documentation > AI Models API > Rerank Reordering Model [Rerank](https://doc.dataeyes.vip/api-526172165.md): Given a prompt, the model will return one or more predicted completions, and can also provide the probability of alternative tokens at each position. - Documentation > AI Models API > Audio API > Text-to-Music Suno > Task Submission [Generate Song (Inspiration Mode)](https://doc.dataeyes.vip/api-526172166.md): - Documentation > AI Models API > Audio API > Text-to-Music Suno > Task Submission [Generate Song (Custom Mode)](https://doc.dataeyes.vip/api-526172167.md): - Documentation > AI Models API > Audio API > Text-to-Music Suno > Task Submission [Generate Song (Continuation Mode)](https://doc.dataeyes.vip/api-526172168.md): - Documentation > AI Models API > Audio API > Text-to-Music Suno > Task Submission [Generate Song (Singer Style)](https://doc.dataeyes.vip/api-526172169.md): Integration Steps - Documentation > AI Models API > Audio API > Text-to-Music Suno > Task Submission [Generate Song (Secondary Creation from Uploaded Song)](https://doc.dataeyes.vip/api-526172170.md): - Documentation > AI Models API > Audio API > Text-to-Music Suno > Task Submission [Generate Song (Song Stitching)](https://doc.dataeyes.vip/api-526172171.md): - Documentation > AI Models API > Audio API > Text-to-Music Suno > Task Submission [Generate Lyrics](https://doc.dataeyes.vip/api-526172172.md): - Documentation > AI Models API > Audio API > Text-to-Music Suno > Task Submission [Song Stitching](https://doc.dataeyes.vip/api-526172173.md): - Documentation > AI Models API > Audio API > Text-to-Music Suno > Query Interface [Batch Retrieve Tasks](https://doc.dataeyes.vip/api-526172174.md): - Documentation > AI Models API > Audio API > Text-to-Music Suno > Query Interface [Query Single Task](https://doc.dataeyes.vip/api-526172175.md): - Documentation > Search / Reader Product > Web Reader API​​ [Web Reader API](https://doc.dataeyes.vip/api-526172176.md): - Documentation > Search / Reader Product > Web Reader API​​ [Web Reader API（HK）](https://doc.dataeyes.vip/api-526172177.md): Belonging to the overseas environment - Hong Kong node: using overseas authorization; - Documentation > Search / Reader Product > Web Search API​​ > Modal Card API > Weather [Weather Query API](https://doc.dataeyes.vip/api-526172181.md): - Documentation > Search / Reader Product > Web Search API​​ [Web Search API](https://doc.dataeyes.vip/api-526172178.md): - Documentation > Search / Reader Product > Web Search API​​ [Video Search api](https://doc.dataeyes.vip/api-526172179.md): - Documentation > Search / Reader Product > Web Search API​​ [Trending Search API](https://doc.dataeyes.vip/api-526172180.md): - Documentation > Search / Reader Product > Document OCR Parsing API [fiel upload](https://doc.dataeyes.vip/api-526172182.md): Document Parsing Interface, supports parsing document content through URL or file upload, and returns the text in Markdown format. - Documentation > Search / Reader Product > Document OCR Parsing API [URL Parsing](https://doc.dataeyes.vip/api-526172183.md): Document Parsing Interface, supports parsing document content through URL or file upload, and returns the text in Markdown format. - Documentation > Advanced & System API > List models [Models](https://doc.dataeyes.vip/api-526172184.md):