# QwenCloud Docs > QwenCloud provides API access to Qwen large language models and multimodal AI. Capabilities include text generation, vision, image generation, video generation, speech-to-text, text-to-speech, speech-to-speech, embeddings, and reranking via OpenAI-compatible, Anthropic-compatible, and DashScope endpoints. ## Token Plan - [Token Plan](https://docs.qwencloud.com/token-plan/overview.md): Token Plan is an AI model subscription service from QwenCloud, using Credits as a unified billing unit across text, image, and video generation models. Available in Personal Edition and Team Edition. - [Token Plan Individual](https://docs.qwencloud.com/token-plan/personal/token-plan-personal-overview.md): Token Plan Individual is an AI model subscription service for individual developers with Credits-based billing across text, multimodal models and Harness tools, compatible with mainstream AI programming and agent tools. - [Quick start](https://docs.qwencloud.com/token-plan/personal/token-plan-personal-quickstart.md): Get started with Token Plan Individual in three steps. - [FAQ](https://docs.qwencloud.com/token-plan/personal/token-plan-personal-faq.md): Frequently asked questions about Token Plan Individual. - [Token Plan Team Edition](https://docs.qwencloud.com/token-plan/team/token-plan-team-overview.md): AI model subscription service for teams with Credits-based billing across text, image, and video generation models - [Quick start](https://docs.qwencloud.com/token-plan/team/token-plan-team-quickstart.md): Start using Token Plan (Team Edition) in three steps: subscribe, get your API key, and set up your AI tool. - [Team management](https://docs.qwencloud.com/token-plan/team/team-management.md): Add and manage team members, assign and revoke seats, configure SSO login, and monitor Credits usage in the Token Plan Management Console. - [FAQ](https://docs.qwencloud.com/token-plan/team/token-plan-team-faq.md): Fix Token Plan issues fast ## Best Practices - [Integrate Harness tools](https://docs.qwencloud.com/token-plan/best-practices/built-in-tools.md): Extend AI coding tools with built-in Harness tools in supported Qwen models - [Integrate multimodal generation models](https://docs.qwencloud.com/token-plan/best-practices/integrate-multimodal-gen.md): Integrate image generation, video generation, and speech synthesis models with Token Plan through tool extension mechanisms - [Add visual understanding capabilities](https://docs.qwencloud.com/token-plan/best-practices/add-vision-skill.md): Vision for coding models ## Getting Started - [Build with QwenCloud](https://docs.qwencloud.com/developer-guides/getting-started/introduction.md): AI models for text, vision, speech, and image & video generation. - [First API call](https://docs.qwencloud.com/developer-guides/getting-started/first-api-call.md): Get started in a few minutes - [Choose models](https://docs.qwencloud.com/developer-guides/getting-started/model-selection.md): Match your specific use case - [Pricing](https://docs.qwencloud.com/developer-guides/getting-started/pricing.md): Pay-as-you-go pricing for API usage - [Latest model: Qwen3.8-Flash](https://docs.qwencloud.com/developer-guides/getting-started/latest-model.md): Learn about the Qwen3.8-Flash model — its next-gen architecture, capabilities, specs, and how to get started ## Models - [Text generation models](https://docs.qwencloud.com/developer-guides/getting-started/text-generation-models.md): Choose a model for AI agents, chatbots, document processing, and more. - [Generate text](https://docs.qwencloud.com/developer-guides/text-generation/quickstart.md): Make your first text generation call - [Partial mode](https://docs.qwencloud.com/developer-guides/text-generation/partial-mode.md): Continue from a prefix - [Machine translation (Qwen-MT)](https://docs.qwencloud.com/developer-guides/text-generation/qwen-mt.md): 92 languages with terms - [Role playing (Qwen-Character)](https://docs.qwencloud.com/developer-guides/text-generation/role-playing.md): NPCs and virtual personas - [DeepSeek](https://docs.qwencloud.com/developer-guides/third-party-models/deepseek.md): Call DeepSeek models through the OpenAI-compatible API or DashScope SDK on QwenCloud. - [GLM](https://docs.qwencloud.com/developer-guides/third-party-models/glm.md): Call GLM models through the OpenAI-compatible API or DashScope SDK on QwenCloud. - [GLM-ZHIPU](https://docs.qwencloud.com/developer-guides/third-party-models/glm-zhipu.md): This document describes how to call the Z.AI GLM model inference service on QwenCloud. - [Kimi](https://docs.qwencloud.com/developer-guides/third-party-models/kimi.md): Call the Kimi K3 and Kimi K2.7 Code models through the OpenAI-compatible API or DashScope SDK on QwenCloud. - [Visual understanding models](https://docs.qwencloud.com/developer-guides/getting-started/vision-models.md): Choose a model for image analysis, video understanding, OCR, and more. - [Analyze images and videos](https://docs.qwencloud.com/developer-guides/multimodal/vision.md): Generate content from visual inputs - [Text extraction](https://docs.qwencloud.com/developer-guides/multimodal/ocr.md): OCR for docs and tables - [Image generation models](https://docs.qwencloud.com/developer-guides/getting-started/image-models.md): Choose a model for text-to-image generation, image editing, and more. - [Text-to-image](https://docs.qwencloud.com/developer-guides/image-generation/text-to-image.md): Generate images from text prompts. - [Image editing](https://docs.qwencloud.com/developer-guides/image-generation/image-editing.md): Modify images via text - [Image editing - Wan2.7/2.6/2.5](https://docs.qwencloud.com/developer-guides/image-generation/wan-image-editing.md): Edit images using text instructions with Wan2.7, 2.6, and 2.5 models. - [Video generation models](https://docs.qwencloud.com/developer-guides/getting-started/video-models.md): Choose a model for text-to-video, image-to-video, reference-to-video, video editing, and more. - [Wan3.0 Video Generation](https://docs.qwencloud.com/developer-guides/video-generation/wan30-video.md): The wan3.0 series is an All-in-One video generation model supporting text-to-video, image-to-video, multi-modal reference, video editing, and video extension. Up to 30 seconds per generation, 30fps, with native audio output. - [Text-to-video](https://docs.qwencloud.com/developer-guides/video-generation/text-to-video.md): Generate video from text - [Image-to-video: first frame](https://docs.qwencloud.com/developer-guides/video-generation/image-to-video.md): Animate from a single image - [Image-to-video: first and last frames](https://docs.qwencloud.com/developer-guides/video-generation/image-to-video-first-last.md): Animate between two frames - [Reference-to-video](https://docs.qwencloud.com/developer-guides/video-generation/reference-video.md): Replicate motion and look - [General video editing](https://docs.qwencloud.com/developer-guides/video-generation/video-editing.md): Repaint, extend, and edit - [HappyOyster User Guide](https://docs.qwencloud.com/developer-guides/getting-started/world-model/happyoyster-guide.md): HappyOyster world model user guide: capabilities, showcases, and prompt-writing for the Adventure, Directing, and Acting modes. - [Text-to-speech models](https://docs.qwencloud.com/developer-guides/speech/tts-models.md): Choose a model for speech synthesis, voice cloning, and voice design. - [Real-time speech synthesis](https://docs.qwencloud.com/developer-guides/speech/realtime-streaming.md): Stream text-to-speech conversion with low first-packet latency - [Non-real-time speech synthesis](https://docs.qwencloud.com/developer-guides/speech/tts.md): Non-realtime speech synthesis with Qwen3-TTS - [Voice cloning](https://docs.qwencloud.com/developer-guides/speech/voice-cloning.md): Clone a voice from audio samples for use with Qwen-Audio-TTS, CosyVoice, Qwen-TTS, or Qwen-Omni models. - [Voice design](https://docs.qwencloud.com/developer-guides/speech/voice-design.md): Create custom voices from text descriptions for use with CosyVoice or Qwen TTS models. - [SSML and LaTeX](https://docs.qwencloud.com/developer-guides/speech/ssml.md): Control speech rate, pauses, and pronunciation with SSML, or convert LaTeX formulas to natural speech - [Qwen-Audio-TTS voice list](https://docs.qwencloud.com/developer-guides/speech/voice-list/qwen-audio-tts.md): System and base voices for qwen-audio-3.0-tts-plus and qwen-audio-3.0-tts-flash - [CosyVoice voice list](https://docs.qwencloud.com/developer-guides/speech/voice-list/cosyvoice.md): System voice catalog - [Qwen-TTS voice list](https://docs.qwencloud.com/developer-guides/speech/voice-list/qwen-tts.md): Qwen-TTS voice reference for real-time and non-real-time speech synthesis - [Speech-to-text models](https://docs.qwencloud.com/developer-guides/speech/speech-to-text-models.md): Choose a model for live captions, file transcription, and more. - [Realtime speech recognition](https://docs.qwencloud.com/developer-guides/speech/asr-realtime.md): Live speech to text - [Audio file transcription](https://docs.qwencloud.com/developer-guides/speech/asr.md): Convert files to text - [Improve recognition accuracy](https://docs.qwencloud.com/developer-guides/speech/improve-recognition-accuracy.md): Improve speech recognition accuracy using custom hotwords and context enhancement. - [Speech-to-speech models](https://docs.qwencloud.com/developer-guides/speech/s2s-models.md): Choose a model for voice conversation, speech translation, or simultaneous interpretation. - [Realtime Audio Chat (Qwen-Audio-Realtime)](https://docs.qwencloud.com/developer-guides/speech/qwen-audio-realtime.md): Qwen-Audio is an end-to-end real-time voice interaction model for low-latency voice conversations. Use cases include voice assistants, intelligent customer service, and AI companions. - [Real-time audio and video translation](https://docs.qwencloud.com/developer-guides/speech/realtime-translation.md): Qwen real-time speech and audiovisual translation with 2.3-second latency - [Audio and video file translation](https://docs.qwencloud.com/developer-guides/speech/file-translation.md): 18-language translation - [Omni-modal models](https://docs.qwencloud.com/developer-guides/speech/omni-models.md): Choose a model for multimodal understanding, audio and video analysis, voice conversation, content moderation, or speech translation. - [Realtime audio and video understanding](https://docs.qwencloud.com/developer-guides/speech/realtime-multimodal-speech.md): Live audio and video chat - [Audio and video file understanding](https://docs.qwencloud.com/developer-guides/speech/multimodal-speech.md): Text + image/audio input - [Omni-modal voice list](https://docs.qwencloud.com/developer-guides/speech/omni-voice-list.md): Voices supported by Qwen3.5-Omni, Qwen3-Omni-Flash, Livetranslate, and other omni-modal models, with their voice parameter values. - [Embedding & reranking models](https://docs.qwencloud.com/developer-guides/getting-started/embedding-models.md): Choose a model for semantic search, RAG retrieval, cross-modal matching, and reranking. - [Text and multimodal embedding](https://docs.qwencloud.com/developer-guides/embeddings/embedding.md): Embedding models convert text, images, and video into numerical vectors for semantic search, recommendations, clustering, classification, and anomaly detection. - [Reranking](https://docs.qwencloud.com/developer-guides/embeddings/reranking.md): Improve search accuracy - [Function Calling](https://docs.qwencloud.com/developer-guides/tool-calling/function-calling.md): Connect models to external tools - [Web search](https://docs.qwencloud.com/developer-guides/tool-calling/web-search.md): Ground model responses in real-time web data - [Web extractor](https://docs.qwencloud.com/developer-guides/tool-calling/web-scraping.md): Fetch URLs for context - [Code interpreter](https://docs.qwencloud.com/developer-guides/tool-calling/code-interpreter.md): Run Python in a sandbox - [Image search](https://docs.qwencloud.com/developer-guides/tool-calling/image-search.md): Find images via Responses - [Connect to MCP servers](https://docs.qwencloud.com/developer-guides/tool-calling/mcp.md): Use external tools in chat - [PDF understanding](https://docs.qwencloud.com/developer-guides/tool-calling/pdf-understanding.md): PDF understanding enables the model to parse and comprehend PDF documents, extracting text and images for analysis. You can pass PDF files via URL or Base64 encoding. - [Structured output](https://docs.qwencloud.com/developer-guides/text-generation/structured-output.md): Make the model return valid JSON, and use JSON Schema to constrain the output structure precisely - [Thinking](https://docs.qwencloud.com/developer-guides/text-generation/thinking.md): Solve complex tasks with step-by-step thinking - [Batch API](https://docs.qwencloud.com/developer-guides/text-generation/batch.md): Process bulk requests asynchronously at 50% off ## Run and Scale - [Prime Mode](https://docs.qwencloud.com/developer-guides/run-and-scale/prime-mode.md): Prime Mode delivers higher TPS for latency-sensitive scenarios such as AI coding assistants, multi-step agent reasoning, and real-time conversations. - [Multi-turn conversations](https://docs.qwencloud.com/developer-guides/run-and-scale/multi-turn.md): Manage chat context - [Context cache](https://docs.qwencloud.com/developer-guides/run-and-scale/context-cache.md): Cut cost with prefix reuse - [Streaming output](https://docs.qwencloud.com/developer-guides/run-and-scale/streaming.md): Receive text output token by token as it is generated. - [Async task management](https://docs.qwencloud.com/developer-guides/run-and-scale/async-task-management.md): Two async patterns on QwenCloud: task-based for media generation, batch for high-volume text processing - [Connection reuse and pooling](https://docs.qwencloud.com/developer-guides/run-and-scale/connection-pooling.md): HTTP connection reuse and WebSocket connection pooling for high-concurrency workloads. ## Tutorials - [Accuracy tuning](https://docs.qwencloud.com/developer-guides/accuracy-tuning/overview.md): Maximize correctness and consistent behavior across text, image, video, speech, and vision models on QwenCloud - [Text-to-text](https://docs.qwencloud.com/developer-guides/accuracy-tuning/text-generation.md): Design effective prompts - [Text-to-image](https://docs.qwencloud.com/developer-guides/accuracy-tuning/image-generation.md): Better Wan image results - [Text-to-video](https://docs.qwencloud.com/developer-guides/accuracy-tuning/video-generation.md): Craft better video prompts - [Speech recognition best practices](https://docs.qwencloud.com/developer-guides/accuracy-tuning/speech-recognition.md): Optimize ASR quality through audio best practices, vocabulary customization, and post-processing correction. - [Explicit Cache Best Practices](https://docs.qwencloud.com/developer-guides/accuracy-tuning/explicit-cache-best-practice.md): Explicit cache guarantees deterministic cache hits for identical input content by adding cache markers to your requests, significantly reducing cost and latency. - [Latency optimization](https://docs.qwencloud.com/developer-guides/run-and-scale/latency-optimization.md): Faster response times across text, image, video, and speech models on QwenCloud - [Cost optimization](https://docs.qwencloud.com/developer-guides/run-and-scale/cost-optimization.md): Spend less on text, image, video, and speech API calls while maintaining output quality - [Safety](https://docs.qwencloud.com/developer-guides/run-and-scale/safety.md): Content moderation, input/output guardrails, and responsible AI practices across all modalities - [Realtime call with qwen3.8-omni-flash-realtime via WebRTC](https://docs.qwencloud.com/developer-guides/tutorials/realtime/webrtc-omni-realtime.md): Use qwen3.8-omni-flash-realtime model via WebRTC protocol for real-time calls - [Realtime call with qwen3.8-omni-flash-realtime via AOQ](https://docs.qwencloud.com/developer-guides/tutorials/realtime/aoq-omni-realtime.md): Use qwen3.8-omni-flash-realtime model via AOQ protocol for real-time calls - [Build push-to-talk voice conversations with qwen3.8-omni-flash-realtime over AOQ](https://docs.qwencloud.com/developer-guides/tutorials/realtime/aoq-omni-ptt.md): Use AOQ to connect to qwen3.8-omni-flash-realtime and let the client control turn boundaries for push-to-talk conversations and optional image questions. The client code uses iOS Swift. - [Real-time speech recognition with AOQ + fun-asr-realtime](https://docs.qwencloud.com/developer-guides/tutorials/realtime/aoq-fun-asr-realtime.md): Use AOQ to connect to fun-asr-realtime for streaming microphone audio and receiving real-time speech recognition results. Client code examples use Android Java; other AOQ-supported platforms share the same interface. - [Real-time voice conversation with AOQ + Qwen-Audio](https://docs.qwencloud.com/developer-guides/tutorials/realtime/aoq-audio-realtime.md): Use AOQ to connect to qwen-audio-3.1-realtime-plus and use server-side VAD to build low-latency real-time voice conversations. Client code examples use Android Java. - [Synthesize speech with qwen-audio-3.0-tts-flash over AOQ](https://docs.qwencloud.com/developer-guides/tutorials/realtime/aoq-tts-realtime.md): Use AOQ to connect to qwen-audio-3.0-tts-flash, send text in segments, and play synthesized speech in real time. The client code uses Android Java. ## Administration - [API keys](https://docs.qwencloud.com/developer-guides/administration/api-keys.md): Create and manage API keys - [Workspaces](https://docs.qwencloud.com/developer-guides/administration/workspace.md): Organize users and access - [Rate limits](https://docs.qwencloud.com/developer-guides/administration/rate-limits.md): Understand and manage API rate limits - [Dynamic rate limiting](https://docs.qwencloud.com/developer-guides/administration/dynamic-rate-limits.md): QwenCloud applies dynamic rate limiting to some models. The TPM rate limit value is adjusted monthly based on your historical consumption, and the actual available TPM is no lower than the rate limit value. ## Integrations - [OpenClaw](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/openclaw.md): Open-source AI assistant platform - [Hermes Agent](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/hermes-agent.md): Terminal AI coding assistant by Nous Research - [Claude Code](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/claude-code.md): Anthropic's terminal AI coding assistant - [OpenCode](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/opencode.md): Terminal AI coding assistant - [Cursor](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/cursor.md): AI-powered code editor - [Codex](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/codex.md): OpenAI's terminal AI coding assistant - [Qwen Code](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/qwen-code.md): Official terminal-based AI coding tool - [DeepSeek Harness](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/deepseek-harness.md): DeepSeek Harness is an open-source AI Agent framework by DeepSeek, supporting both Web UI and CLI modes. Connect it to QwenCloud using Pay-as-you-go, Token Plan Personal Edition, or Token Plan Team Edition. - [QwenPaw](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/qwenpaw.md): Open-source personal AI assistant from the AgentScope team - [Cherry Studio](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/cherry-studio.md): Open-source AI desktop client - [Chatbox](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/chatbox.md): Cross-platform AI chat client - [Cline](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/cline.md): VSCode AI coding extension - [Qoder](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/qoder.md): Agentic coding platform with IDE, CLI, and JetBrains plugin - [Qoder CN (formerly Lingma)](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/lingma.md): Alibaba Cloud intelligent coding assistant IDE - [Kilo CLI](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/kilo-cli.md): AI coding in terminal - [Postman](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/postman.md): API testing tool - [Dify](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/dify.md): Low-code LLM app platform - [More tools](https://docs.qwencloud.com/developer-guides/clients-and-developer-tools/other-tools.md): Connect any OpenAI or Anthropic compatible programming tool - [MLOps & observability](https://docs.qwencloud.com/developer-guides/integrations/mlops-observability.md): Production AI monitoring - [Monitoring alerts](https://docs.qwencloud.com/developer-guides/integrations/alerts.md): Configure alert rules for model API metrics ## Model Production - [Datasets overview](https://docs.qwencloud.com/developer-guides/datasets/overview.md): Manage training datasets for fine-tuning models on QwenCloud. - [Create a dataset](https://docs.qwencloud.com/developer-guides/datasets/create-dataset.md): Upload training data to QwenCloud for use in fine-tuning jobs. - [Manage datasets](https://docs.qwencloud.com/developer-guides/datasets/manage-datasets.md): Publish, edit, and delete datasets on the QwenCloud platform. - [Fine-tuning overview](https://docs.qwencloud.com/developer-guides/fine-tuning/overview.md): Improve model performance for your use case by fine-tuning Qwen models on QwenCloud with SFT and LoRA. - [Create a fine-tuning job](https://docs.qwencloud.com/developer-guides/fine-tuning/create-fine-tuning-job.md): Step-by-step guide to creating a fine-tuning job in the QwenCloud console. - [Manage fine-tuning jobs](https://docs.qwencloud.com/developer-guides/fine-tuning/manage-fine-tuning-jobs.md): Monitor, manage, and deploy fine-tuning jobs from the QwenCloud console. - [Hyperparameters reference](https://docs.qwencloud.com/developer-guides/fine-tuning/hyperparameters.md): Reference for all fine-tuning hyperparameters available in Expert mode on QwenCloud. - [Custom models overview](https://docs.qwencloud.com/developer-guides/custom-models/overview.md): View and manage models you have fine-tuned on QwenCloud. - [Model evaluation overview](https://docs.qwencloud.com/developer-guides/evaluation/overview.md): Evaluate model performance across multiple dimensions on QwenCloud, with LLM-based scoring and manual annotation. - [Evaluation dimensions](https://docs.qwencloud.com/developer-guides/evaluation/evaluation-dimensions.md): Create and manage evaluation dimensions on QwenCloud with LLM numeric scoring, LLM classification, and manual annotation. - [Evaluation tasks](https://docs.qwencloud.com/developer-guides/evaluation/evaluation-tasks.md): Create evaluation tasks on QwenCloud to quantify model output quality using custom dimensions and datasets. - [Deployment overview](https://docs.qwencloud.com/developer-guides/deployment/overview.md): Deploy custom models on QwenCloud to create dedicated inference services for production workloads. - [Manage deployments](https://docs.qwencloud.com/developer-guides/deployment/manage-deployments.md): Monitor, scale, and manage the lifecycle of your model deployments on QwenCloud. ## Security & Compliance - [Data security & privacy](https://docs.qwencloud.com/developer-guides/security-compliance/data-security.md): How QwenCloud secures your data - [Audit & access logs](https://docs.qwencloud.com/developer-guides/security-compliance/audit-logs.md): Track API usage for compliance ## Getting Started - [Get an API key](https://docs.qwencloud.com/api-reference/preparation/api-key.md): First step to using models - [Configure your API key](https://docs.qwencloud.com/api-reference/preparation/export-api-key-env.md): Avoid hardcoding secrets - [Install the SDK](https://docs.qwencloud.com/api-reference/preparation/install-sdk.md): Python and Java setup - [CLI Tool](https://docs.qwencloud.com/api-reference/preparation/cli.md): QwenCloud CLI for management and model invocation: manage the model catalog, accounts, usage, billing, subscriptions, and support tickets, and invoke text, image, video, and speech models - [Error messages](https://docs.qwencloud.com/api-reference/preparation/error-messages.md): API error code reference ## Chat Models - [OpenAI chat](https://docs.qwencloud.com/api-reference/chat/openai-chat.md): Compatible Chat API - [OpenAI responses](https://docs.qwencloud.com/api-reference/chat/openai-responses.md): Compatible Responses API - [Anthropic Messages API](https://docs.qwencloud.com/api-reference/chat/anthropic.md): Call Qwen models using Anthropic SDKs - [DashScope chat](https://docs.qwencloud.com/api-reference/chat/dashscope.md): Native SDK and HTTP API ## Specialized Models - [Decision Model API Reference](https://docs.qwencloud.com/api-reference/decision-model-api.md): Call POST /compatible-mode/v1/systemone to use the QwenCloud decision model (decision-model-preview), which returns classification, scoring, and yes/no decisions with full probability distributions and confidence in a single forward pass, without generating text. ## Image Generation API - [Qwen — OpenAI-compatible image generation](https://docs.qwencloud.com/api-reference/image-generation/qwen-text-to-image-openai.md): Call the Qwen image generation and editing models for text-to-image and image-to-image/editing through the OpenAI Images-compatible protocol - [Qwen synchronous](https://docs.qwencloud.com/api-reference/image-generation/qwen-text-to-image.md): Real-time image generation - [Qwen — Async image generation (3.0 and 2.1-pro)](https://docs.qwencloud.com/api-reference/image-generation/qwen-text-to-image-30-async.md): Asynchronous image generation for the qwen-image-3.0 series and qwen-image-2.1-pro - [Qwen — Generate an image](https://docs.qwencloud.com/api-reference/image-generation/qwen-text-to-image-async.md): Async image generation - [Qwen — Retrieve image result](https://docs.qwencloud.com/api-reference/image-generation/qwen-text-to-image-task-query.md): Check image task status - [Z-Image](https://docs.qwencloud.com/api-reference/image-generation/z-image.md): Fast lightweight generation - [Wan T2I synchronous](https://docs.qwencloud.com/api-reference/image-generation/wan-text-to-image-v2/synchronous.md): Real-time Wan text-to-image generation - [Wan v2 — Generate an image](https://docs.qwencloud.com/api-reference/image-generation/wan-text-to-image-v2/create-task.md): Async Wan image generation - [Wan v2 — Retrieve image result](https://docs.qwencloud.com/api-reference/image-generation/wan-text-to-image-v2/query-result.md): Check Wan image status - [Qwen](https://docs.qwencloud.com/api-reference/image-generation/qwen-image-editing.md): Edit images via text - [Wan 2.7 synchronous](https://docs.qwencloud.com/api-reference/image-generation/wan27-image-gen-edit/synchronous.md): Synchronous Wan 2.7 image generation and editing - [Wan 2.7 — Generate or edit an image](https://docs.qwencloud.com/api-reference/image-generation/wan27-image-gen-edit/create-task.md): Async Wan 2.7 image generation and editing - [Wan 2.7 — Retrieve image result](https://docs.qwencloud.com/api-reference/image-generation/wan27-image-gen-edit/query-result.md): Check Wan 2.7 image task status - [Wan 2.6 synchronous](https://docs.qwencloud.com/api-reference/image-generation/wan26-image-gen-edit/synchronous.md): Synchronous Wan 2.6 image generation and editing - [Wan 2.6 — Generate or edit an image](https://docs.qwencloud.com/api-reference/image-generation/wan26-image-gen-edit/create-task.md): Async Wan 2.6 image generation and editing - [Wan 2.6 — Retrieve image result](https://docs.qwencloud.com/api-reference/image-generation/wan26-image-gen-edit/query-result.md): Check Wan 2.6 image task status - [Wan 2.5 — Edit an image](https://docs.qwencloud.com/api-reference/image-generation/wan25-general-image-editing/create-task.md): Async Wan2.5 image edit - [Wan 2.5 — Retrieve editing result](https://docs.qwencloud.com/api-reference/image-generation/wan25-general-image-editing/query-result.md): Check Wan2.5 edit status ## Image Translation - [Qwen-MT-Image — Synchronous](https://docs.qwencloud.com/api-reference/image-translation/qwen-mt-image/synchronous.md): Call qwen-mt-image-2.0 image translation synchronously and receive the translated image URL directly - [Create image translation task](https://docs.qwencloud.com/api-reference/image-translation/qwen-mt-image/create-task.md): Submit a qwen-mt-image async image translation task - [Query task result](https://docs.qwencloud.com/api-reference/image-translation/qwen-mt-image/query-result.md): Query qwen-mt-image image translation task status and result ## Video Generation API - [wan3.0-video Video Generation](https://docs.qwencloud.com/api-reference/video-generation/wan30-video/create-task.md): wan3.0-video All-in-One video generation model. Supports text-to-video, first-frame/first+last-frame, all-in-one reference, audio, and more. - [wan3.0-video Query Task Result](https://docs.qwencloud.com/api-reference/video-generation/wan30-video/query-result.md): Query the status and result of a wan3.0-video video generation task. - [HappyHorse -- Generate a video from an image](https://docs.qwencloud.com/api-reference/video-generation/happyhorse-image-to-video/create-task.md): Submit HappyHorse image-to-video task (first frame) - [HappyHorse -- Retrieve image-to-video result](https://docs.qwencloud.com/api-reference/video-generation/happyhorse-image-to-video/query-result.md): Check HappyHorse image-to-video task status - [Wan 2.7 -- Generate a video from image](https://docs.qwencloud.com/api-reference/video-generation/wan27-image-to-video/create-task.md): Submit image-to-video task (wan2.7) - [Wan 2.7 -- Retrieve image-to-video result](https://docs.qwencloud.com/api-reference/video-generation/wan27-image-to-video/query-result.md): Check wan2.7 image-to-video task status - [Wan — Animate from first frame](https://docs.qwencloud.com/api-reference/video-generation/wan-image-to-video-first-frame/create-task.md): Submit image-to-video task - [Wan — Retrieve first-frame result](https://docs.qwencloud.com/api-reference/video-generation/wan-image-to-video-first-frame/query-result.md): Check video task status - [Wan — Animate from first & last frames](https://docs.qwencloud.com/api-reference/video-generation/wan-image-to-video-first-last-frames/create-task.md): Submit first+last frames - [Wan — Retrieve first-last-frame result](https://docs.qwencloud.com/api-reference/video-generation/wan-image-to-video-first-last-frames/query-result.md): Check video task status - [HappyHorse -- Generate a video from reference images](https://docs.qwencloud.com/api-reference/video-generation/happyhorse-reference-to-video/create-task.md): Submit HappyHorse reference-to-video task - [HappyHorse -- Retrieve reference-to-video result](https://docs.qwencloud.com/api-reference/video-generation/happyhorse-reference-to-video/query-result.md): Check HappyHorse reference-to-video task status - [Wan 2.7 -- Generate from reference](https://docs.qwencloud.com/api-reference/video-generation/wan27-reference-to-video/create-task.md): Submit a Wan 2.7 reference-to-video task - [Wan 2.7 -- Retrieve reference-to-video result](https://docs.qwencloud.com/api-reference/video-generation/wan27-reference-to-video/query-result.md): Check Wan 2.7 video task status - [Wan 2.6 — Generate from reference](https://docs.qwencloud.com/api-reference/video-generation/wan-reference-to-video/create-task.md): Submit reference video - [Wan 2.6 — Retrieve reference-to-video result](https://docs.qwencloud.com/api-reference/video-generation/wan-reference-to-video/query-result.md): Check video task status - [HappyHorse -- Generate a video from text](https://docs.qwencloud.com/api-reference/video-generation/happyhorse-text-to-video/create-task.md): Submit HappyHorse text-to-video task - [HappyHorse -- Retrieve text-to-video result](https://docs.qwencloud.com/api-reference/video-generation/happyhorse-text-to-video/query-result.md): Check HappyHorse text-to-video task status - [Wan 2.7 -- Generate a video from text](https://docs.qwencloud.com/api-reference/video-generation/wan27-text-to-video/create-task.md): Submit text-to-video task (wan2.7) - [Wan 2.7 -- Retrieve text-to-video result](https://docs.qwencloud.com/api-reference/video-generation/wan27-text-to-video/query-result.md): Check wan2.7 video task status - [Wan 2.6 and earlier — Generate a video from text](https://docs.qwencloud.com/api-reference/video-generation/wan-text-to-video/create-task.md): Submit text-to-video task (wan2.6 and earlier) - [Wan 2.6 and earlier — Retrieve text-to-video result](https://docs.qwencloud.com/api-reference/video-generation/wan-text-to-video/query-result.md): Check video task status (wan2.6 and earlier) - [HappyHorse -- Edit a video](https://docs.qwencloud.com/api-reference/video-generation/happyhorse-video-editing/create-task.md): Submit HappyHorse video editing task - [HappyHorse -- Retrieve video editing result](https://docs.qwencloud.com/api-reference/video-generation/happyhorse-video-editing/query-result.md): Check HappyHorse video editing task status - [Wan 2.7 -- Edit a video](https://docs.qwencloud.com/api-reference/video-generation/wan27-video-editing/create-task.md): Submit video editing task (wan2.7) - [Wan 2.7 -- Retrieve video editing result](https://docs.qwencloud.com/api-reference/video-generation/wan27-video-editing/query-result.md): Check wan2.7 video editing task status - [Wan — Edit a video](https://docs.qwencloud.com/api-reference/video-generation/wan-general-video-editing/create-task.md): Submit video edit task - [Wan — Retrieve video editing result](https://docs.qwencloud.com/api-reference/video-generation/wan-general-video-editing/query-result.md): Check video edit status - [Wan — Animate an image](https://docs.qwencloud.com/api-reference/video-generation/wan-image-to-animation/create-task.md): Submit animation task - [Wan — Retrieve animation result](https://docs.qwencloud.com/api-reference/video-generation/wan-image-to-animation/query-result.md): Check animation status - [Wan — Swap video character](https://docs.qwencloud.com/api-reference/video-generation/wan-video-character-swap/create-task.md): Submit face swap task - [Wan — Retrieve character swap result](https://docs.qwencloud.com/api-reference/video-generation/wan-video-character-swap/query-result.md): Check face swap status ## World Models API - [World models](https://docs.qwencloud.com/api-reference/world-model/world-model.md): World model capabilities and usage guides. - [HappyOyster](https://docs.qwencloud.com/api-reference/world-model/happyoyster.md): Documentation index for the HappyOyster world model: overview, quick start, client SDKs, and Open API reference. - [Overview](https://docs.qwencloud.com/api-reference/world-model/happyoyster-overview.md): HappyOyster is a real-time interactive open-world model. From a single natural-language prompt and a first-frame image, it generates a digital world you can perform, explore, and interact with in real time, delivered as a joinable live video stream. Well-suited to interactive drama, film previsualization, AI companions, and playable worlds. - [Quick Start](https://docs.qwencloud.com/api-reference/world-model/happyoyster-quick-start.md): Complete the end-to-end HappyOyster integration: authentication, server-side Open API, client SDK, and Demo. - [Get Authentication Credentials](https://docs.qwencloud.com/api-reference/world-model/happyoyster-auth-setup.md): Obtain the authentication credentials required by the HappyOyster server and client: API Host, primary API Key, temporary API Key, and ticket. - [Integration Flow](https://docs.qwencloud.com/api-reference/world-model/happyoyster-integration-flow.md): Your server prepares worlds and exports artifacts through the HappyOyster Open APIs; the client SDK handles the RTC connection and real-time interaction. - [Download SDKs and Demos](https://docs.qwencloud.com/api-reference/world-model/happyoyster-sdk-and-demo.md): Download the HappyOyster client SDKs and server-side demo reference implementations. - [Client SDK](https://docs.qwencloud.com/api-reference/world-model/happyoyster-client-sdk.md): Documentation index for the HappyOyster client SDKs, covering integration guides and API references for Android, iOS, and Web. - [Android SDK](https://docs.qwencloud.com/api-reference/world-model/happyoyster-android-sdk.md): Documentation index for the HappyOyster Android SDK: integration guide, API reference, and Playground guide. - [HappyOyster Android SDK Integration Guide](https://docs.qwencloud.com/api-reference/world-model/happyoyster-android-sdk-integration-guide.md): By integrating the HappyOyster Android SDK, your App can enter worlds generated by AI in real time, delivering a real-time interactive video experience in three modes: Adventure (world exploration), Directing (real-time directing), and Acting (role-play). - [HappyOyster Android SDK API Reference](https://docs.qwencloud.com/api-reference/world-model/happyoyster-android-sdk-api-reference.md): The entry point for the HappyOyster Android SDK is the singleton object HappyOyster . Except for initialize , updateToken , attachVideo , and sendCommand , all business methods are suspend functions that throw SDKError on failure. Covers the three modes adventure / directing / acting, the required model config, and aspectRatio. - [HappyOyster-Android Playground Getting Started Guide](https://docs.qwencloud.com/api-reference/world-model/happyoyster-android-playground-guide.md): This guide helps international partners install Happy Oyster Android Playground, sign in, and walk through a complete product experience. - [iOS SDK](https://docs.qwencloud.com/api-reference/world-model/happyoyster-ios-sdk.md): Documentation index for the HappyOyster iOS SDK: integration guide and API reference. - [HappyOyster iOS SDK Integration Guide](https://docs.qwencloud.com/api-reference/world-model/happyoyster-ios-sdk-integration-guide.md): This is the shortest onboarding path for iOS integrators: from initialization, to getting the picture on screen, to sending control instructions, to ending the experience. For the complete method signatures, fields, and error codes, refer to the iOS SDK API Reference. - [HappyOyster iOS SDK API Reference](https://docs.qwencloud.com/api-reference/world-model/happyoyster-ios-sdk-api-reference.md): The HappyOyster iOS SDK entry point is the process-level singleton HappyOysterEngine.shared . Business methods are all async throws , throwing OysterSDKError on failure. A single experience is carried by an OysterTravel handle, spanning three modes — adventure, directing, and acting — on both UIKit and SwiftUI. - [Web SDK](https://docs.qwencloud.com/api-reference/world-model/happyoyster-web-sdk.md): Documentation index for the HappyOyster Web SDK: integration guide and API reference. - [HappyOyster Web SDK Integration Guide](https://docs.qwencloud.com/api-reference/world-model/happyoyster-web-sdk-integration-guide.md): This document is intended for frontend / full-stack developers and explains how to integrate the HappyOyster Web SDK reliably in production across its adventure, directing, and acting modes. - [HappyOyster Web SDK API Reference](https://docs.qwencloud.com/api-reference/world-model/happyoyster-web-sdk-api-reference.md): HappyOysterEngine configures the Open Platform host and model, updates the QwenCloud temporary API Key token, and creates Travel sessions. Travel is the session object returned by createTravel(); the session is entered and started only after calling travel.start(). Supports the adventure, directing, and acting modes. - [HappyOyster Adventure Open API Reference](https://docs.qwencloud.com/api-reference/world-model/happyoyster-adventure-openapi-reference.md) - [HappyOyster-Adventure-Create World API Reference](https://docs.qwencloud.com/api-reference/world-model/adventure/create-world.md): Create a world exploration World. Create a World from a natural-language prompt and a required first-frame image; the API immediately returns an encrypted World ID, the World builds asynchronously in the background, and the client polls the build progress until it completes. - [HappyOyster-Adventure-Query World Build Status API Reference](https://docs.qwencloud.com/api-reference/world-model/adventure/query-world-build-status.md): Query the build progress of an Adventure World. The API returns the encrypted World ID, build status, and first-frame URL; the client polls until the World enters ready. - [HappyOyster-Adventure-Get Travel Credential API Reference](https://docs.qwencloud.com/api-reference/world-model/adventure/get-travel-credential.md): A third-party server uses the primary API Key to exchange for a short-lived, single-use ticket, then securely delivers it to the client. This endpoint only validates World ownership, status, and quota; it does not create a Travel. - [HappyOyster-Adventure-Enter Travel API Reference](https://docs.qwencloud.com/api-reference/world-model/adventure/enter-travel.md): The client uses the ticket to create an actual Travel and obtain the RTC join configuration and the Adventure capability version. maxExperienceTimeSec takes effect only in the Adventure model. - [HappyOyster-Adventure-Query Travel Status API Reference](https://docs.qwencloud.com/api-reference/world-model/adventure/query-travel-status.md): Query the Adventure Travel lifecycle, server-side streaming status, and the current world's action pool; you can also report the client's pull-stream or playback heartbeat at the same time. - [HappyOyster-Adventure-End Travel API Reference](https://docs.qwencloud.com/api-reference/world-model/adventure/end-travel.md): Actively end an Adventure Travel. After a normal end it enters completed; on a no-stream timeout end it enters failed and no replay artifacts are generated. The server also ends it automatically when maxExperienceTimeSec is reached. - [HappyOyster-Adventure-Query World Detail API Reference](https://docs.qwencloud.com/api-reference/world-model/adventure/query-world-detail.md): Query the full metadata and echoable creation parameters of a single Adventure World. For build-progress polling, use the Query World Build Status endpoint. - [HappyOyster-Adventure-Query World List API Reference](https://docs.qwencloud.com/api-reference/world-model/adventure/query-world-list.md): Paginate through the Adventure Worlds under the current primary account. The endpoint is automatically isolated by model and never returns Directing or Acting Worlds. - [HappyOyster-Adventure-Delete World API Reference](https://docs.qwencloud.com/api-reference/world-model/adventure/delete-world.md): Delete an Adventure World under the current primary account. When the World no longer exists under the same account, it returns deleted=false idempotently. - [HappyOyster-Adventure-Query Travel List API Reference](https://docs.qwencloud.com/api-reference/world-model/adventure/query-travel-list.md): Paginate through the Adventure Travels under the current primary account, with optional filtering by status or associated World. - [HappyOyster-Adventure-Query Travel Artifacts API Reference](https://docs.qwencloud.com/api-reference/world-model/adventure/query-travel-artifacts.md): Query the recorded original and the three composited variants of a completed Adventure Travel. For external delivery, withInstructionAndWatermark is recommended. - [HappyOyster Directing Open API Reference](https://docs.qwencloud.com/api-reference/world-model/happyoyster-directing-openapi-reference.md) - [HappyOyster-Directing-Create World API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/create-world.md): Create a real-time directing World. Supports standard mode (natural-language prompt) and script mode (structured ScriptList); the API immediately returns an encrypted World ID, the World builds asynchronously in the background, and the client polls the build progress until it completes. - [HappyOyster-Directing-Query World Build Status API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/query-world-build-status.md): Query the build progress of a Directing World. The API returns the encrypted World ID, build status, and first-frame URL; the client polls until the World enters ready. - [HappyOyster-Directing-Get Travel Credential API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/get-travel-credential.md): A third-party server uses the primary API Key to exchange for a short-lived, single-use ticket, then securely delivers it to the client. This endpoint only validates World ownership, status, and quota; it does not create a Travel. - [HappyOyster-Directing-Enter Travel (Client) API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/enter-travel.md): The client uses the ticket to create an actual Travel and obtain the RTC join configuration and the Directing capability version. creationModel determines the control interfaces the Travel can call. - [HappyOyster-Directing-Query Travel Status API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/query-travel-status.md): Query the Directing Travel lifecycle, server-side streaming status, executed text instructions, and chapter information; you can also report the client's pull-stream or playback heartbeat at the same time. - [HappyOyster-Directing-Rewind Travel API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/rewind-travel.md): Rewind a Travel to a specified video timestamp and resume running from the actual landing point. The Travel must first enter the paused state. - [HappyOyster-Directing-Pause Travel API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/pause-travel.md): Request to pause a running Directing Travel. After the pause completes, you can call resume or rewind. - [HappyOyster-Directing-Resume Travel API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/resume-travel.md): Resume a paused Directing Travel so that it re-enters the running state. - [HappyOyster-Directing-End Travel API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/end-travel.md): End a Directing Travel. After a normal end the status changes to completed and it enters artifact processing; on a no-stream timeout end it changes to failed and no replay artifacts are generated. - [HappyOyster-Directing-Send Process Instruction API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/instruct-travel.md): Send a single text instruction to a standard-mode Travel to drive subsequent frame generation. Only creationModel=simple is supported; a scriptlist Travel should use full script update. - [HappyOyster-Directing-Update Script API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/update-script.md): Submit the complete set of 45 turns in a script-mode Travel to fully replace the current Travel's acts. Only creationModel=scriptlist is supported. - [HappyOyster-Directing-Query World Detail API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/query-world-detail.md): Query the current status, creation parameters, and returnable ScriptList information of a single Directing World. For build-progress polling, use the Query World Build Status endpoint. - [HappyOyster-Directing-Query World List API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/query-world-list.md): Paginate through the Directing Worlds under the current primary account. The endpoint is automatically isolated by model and never returns Acting or Adventure Worlds. - [HappyOyster-Directing-Delete World API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/delete-world.md): Delete a Directing World under the current primary account. When the World no longer exists under the same account, it returns deleted=false idempotently. - [HappyOyster-Directing-Query Travel List API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/query-travel-list.md): Paginate through the Directing Travels under the current primary account, with optional filtering by status or associated World. - [HappyOyster-Directing-Query Travel Artifacts API Reference](https://docs.qwencloud.com/api-reference/world-model/directing/query-travel-artifacts.md): Query the recorded original and the three composited variants of a completed Directing Travel. An available original is the precondition for returning an artifacts response; for external delivery, withInstructionAndWatermark is recommended. - [HappyOyster Acting Open API Reference](https://docs.qwencloud.com/api-reference/world-model/happyoyster-acting-openapi-reference.md) - [HappyOyster-Acting-Create World API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/create-world.md): Create a role-play World. Create a World from a natural-language prompt and a required first-frame image; the API immediately returns an encrypted World ID (encryptedWorldId), the World builds asynchronously in the background, and the client polls the build progress until it completes. - [HappyOyster-Acting-Query World Build Status API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/query-world-build-status.md): Query the build progress of an Acting World. The API returns the encrypted World ID, build status, and first-frame URL; the client polls until the World enters ready. - [HappyOyster-Acting-Get Travel Credential API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/get-travel-credential.md): A third-party server uses the primary API Key to exchange for a short-lived, single-use ticket, then securely delivers it to the client. This endpoint only validates World ownership, status, and quota; it does not create a Travel. - [HappyOyster-Acting-Enter Travel API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/enter-travel.md): The client uses the ticket to create an actual Travel and obtain the RTC join configuration, the Acting capability version, and the player aspect ratio. A successful call creates the Travel. - [HappyOyster-Acting-Query Travel Status API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/query-travel-status.md): Query the Acting Travel lifecycle, server-side streaming status, sent text instructions, and chapter information; you can also report the client's pull-stream or playback heartbeat at the same time. - [HappyOyster-Acting-Pause Travel API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/pause-travel.md): Request to pause a running Acting Travel. After the pause, video generation stops and you can continue via the Resume Travel endpoint. - [HappyOyster-Acting-Resume Travel API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/resume-travel.md): Resume a paused Acting Travel so that it re-enters the running state. - [HappyOyster-Acting-Send Process Instruction API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/instruct-travel.md): Send a single text instruction to an Acting Travel to drive subsequent role-play and frame generation. Callable when the Travel is running or paused. - [HappyOyster-Acting-End Travel API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/end-travel.md): Actively end an Acting Travel. After a normal end it enters completed and starts processing artifacts; on a no-stream timeout end it enters failed and no replay artifacts are generated. - [HappyOyster-Acting-Query World Detail API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/query-world-detail.md): Query the full metadata and echoable creation parameters of a single Acting World. For build-progress polling, use the Query World Build Status endpoint. - [HappyOyster-Acting-Query World List API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/query-world-list.md): Paginate through the Acting Worlds under the current primary account. The endpoint is automatically isolated by model and never returns Directing or Adventure Worlds. - [HappyOyster-Acting-Delete World API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/delete-world.md): Delete an Acting World under the current primary account. When the World no longer exists under the same account, it returns deleted=false idempotently. - [HappyOyster-Acting-Query Travel List API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/query-travel-list.md): Paginate through the Acting Travels under the current primary account, with optional filtering by status or associated World. - [HappyOyster-Acting-Query Travel Artifacts API Reference](https://docs.qwencloud.com/api-reference/world-model/acting/query-travel-artifacts.md): Query the recorded original and the three composited variants of a completed Acting Travel. For external delivery, withInstructionAndWatermark is recommended. - [HappyOyster Error Codes](https://docs.qwencloud.com/api-reference/world-model/happyoyster-error-code.md): HappyOyster Open API response structure and error codes, including business codes, typical scenarios, and handling suggestions. ## Speech-to-Text - [Fun-ASR WebSocket API](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-realtime/websocket-api.md): WebSocket connection, headers, and interaction flow for Fun-ASR real-time speech recognition - [Qwen-Audio-3.x-ASR-Flash-Streaming/Fun-ASR-Realtime real-time speech recognition client events](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-realtime/client-events.md): WebSocket client event reference for Qwen-Audio-3.x-ASR-Flash-Streaming/Fun-ASR-Realtime real-time speech recognition - [Qwen-Audio-3.0-ASR-Flash-Streaming/Fun-ASR-Realtime server events](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-realtime/server-events.md): WebSocket server event reference for Qwen-Audio-3.0-ASR-Flash-Streaming/Fun-ASR-Realtime real-time speech recognition - [Qwen-Audio-3.x-ASR-Flash-Streaming/Fun-ASR-Realtime Python SDK](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-realtime/python-sdk.md): This topic describes the parameters and interfaces of the Python SDK for the Qwen-Audio-3.x-ASR-Flash-Streaming/Fun-ASR-Realtime real-time speech recognition model. - [Qwen-Audio-3.x-ASR-Flash-Streaming/Fun-ASR-Realtime Java SDK](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-realtime/java-sdk.md): Real-time ASR Java SDK for Qwen-Audio-3.x-ASR-Flash-Streaming/Fun-ASR-Realtime - [Qwen-Audio-3.x-ASR-Flash-Streaming/Fun-ASR-Realtime Android SDK](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-realtime/android-sdk.md): This guide shows you how to use the Android SDK for Qwen-Audio-3.x-ASR-Flash-Streaming and Fun-ASR-Realtime real-time speech recognition to convert speech to text. - [Qwen-Audio-3.0-ASR-Flash-Streaming/Fun-ASR-Realtime iOS SDK](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-realtime/ios-sdk.md): This guide shows you how to use the Qwen-Audio-3.0-ASR-Flash-Streaming/Fun-ASR-Realtime real-time speech recognition iOS SDK to transcribe speech into text. - [Qwen-Audio-3.0-ASR-Flash-Streaming/Fun-ASR-Realtime HarmonyOS SDK](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-realtime/harmonyos-sdk.md): Learn about HarmonyOS SDK integration, request parameters, APIs, callbacks, and sample code for real-time speech recognition. - [Qwen-Audio-3.x-ASR-Flash-Filetrans/Fun-ASR recording Python SDK](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-recording/python-sdk.md): File transcription Python - [Qwen-Audio-3.0-ASR-Flash-Filetrans/Fun-ASR HTTP API for non-real-time speech recognition](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-recording/restful-api.md): File transcription REST - [Qwen-Audio-3.x-ASR-Flash-Filetrans/Fun-ASR recording Java SDK](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-recording/java-sdk.md): File transcription Java SDK for Qwen-Audio-3.x-ASR-Flash-Filetrans/Fun-ASR - [Qwen-Audio-3.0-ASR-Flash-Filetrans/Fun-ASR recording Android SDK](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-recording/android-sdk.md): File transcription Android SDK for Qwen-Audio-3.0-ASR-Flash-Filetrans/Fun-ASR - [Qwen-Audio-3.0-ASR-Flash-Filetrans/Fun-ASR recording iOS SDK](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-recording/ios-sdk.md): File transcription iOS SDK for Qwen-Audio-3.0-ASR-Flash-Filetrans/Fun-ASR - [Qwen-Audio-3.0-ASR-Flash-Filetrans/Fun-ASR recording HarmonyOS SDK](https://docs.qwencloud.com/api-reference/speech-recognition/fun-asr-recording/harmonyos-sdk.md): File transcription HarmonyOS SDK for Qwen-Audio-3.0-ASR-Flash-Filetrans/Fun-ASR - [Qwen-ASR-Realtime WebSocket API](https://docs.qwencloud.com/api-reference/speech-recognition/qwen-asr-realtime/websocket-api.md): WebSocket connection, headers, and interaction flows for Qwen-ASR-Realtime - [Qwen-ASR client events](https://docs.qwencloud.com/api-reference/speech-recognition/qwen-asr-realtime/client-events.md): WebSocket client reference - [Qwen-ASR server events](https://docs.qwencloud.com/api-reference/speech-recognition/qwen-asr-realtime/server-events.md): WebSocket server reference - [Qwen-ASR realtime Python SDK](https://docs.qwencloud.com/api-reference/speech-recognition/qwen-asr-realtime/python-sdk.md): Qwen ASR Python streaming - [Qwen-ASR realtime Java SDK](https://docs.qwencloud.com/api-reference/speech-recognition/qwen-asr-realtime/java-sdk.md): Qwen ASR Java integration - [OpenAI compatible ASR](https://docs.qwencloud.com/api-reference/speech-recognition/qwen-asr/openai.md): Audio via Chat API - [DashScope synchronous](https://docs.qwencloud.com/api-reference/speech-recognition/qwen-asr/dashscope.md): Sync audio recognition - [Qwen-ASR — Transcribe audio](https://docs.qwencloud.com/api-reference/speech-recognition/qwen-asr/dashscope-async.md): Submit async transcription - [Qwen-ASR — Retrieve transcription](https://docs.qwencloud.com/api-reference/speech-recognition/qwen-asr/query-result.md): Check transcription status - [Custom hotwords HTTP API](https://docs.qwencloud.com/api-reference/speech-recognition/custom-hotwords/http-api.md): Manage custom vocabularies through HTTP APIs, including creating, listing, getting, updating, and deleting vocabularies. - [Custom hotwords Python SDK](https://docs.qwencloud.com/api-reference/speech-recognition/custom-hotwords/python-sdk.md): Use the Python SDK to create, list, query, update, and delete custom vocabularies for speech recognition. - [Custom hotwords Java SDK](https://docs.qwencloud.com/api-reference/speech-recognition/custom-hotwords/java-sdk.md): Use the Java SDK to create, query, update, and delete custom vocabularies for speech recognition. ## Text-to-speech - [Qwen-Audio-TTS/CosyVoice Java SDK](https://docs.qwencloud.com/api-reference/speech-synthesis/cosyvoice/java-sdk.md): Qwen-Audio-TTS/CosyVoice Java reference - [Qwen-Audio-TTS/CosyVoice Python SDK](https://docs.qwencloud.com/api-reference/speech-synthesis/cosyvoice/python-sdk.md): Qwen-Audio-TTS/CosyVoice Python reference - [CosyVoice WebSocket API](https://docs.qwencloud.com/api-reference/speech-synthesis/cosyvoice/websocket-api.md): CosyVoice WebSocket API - [Qwen-Audio-TTS/CosyVoice client events](https://docs.qwencloud.com/api-reference/speech-synthesis/cosyvoice/client-events.md): Qwen-Audio-TTS/CosyVoice real-time speech synthesis WebSocket client event reference - [CosyVoice server-side events](https://docs.qwencloud.com/api-reference/speech-synthesis/cosyvoice/server-events.md): CosyVoice real-time speech synthesis WebSocket server event reference - [Qwen-Audio-TTS/CosyVoice Android SDK](https://docs.qwencloud.com/api-reference/speech-synthesis/cosyvoice/android-sdk.md): Convert text to expressive, high-quality speech in your Android app with the Qwen-Audio-TTS/CosyVoice text-to-speech (TTS) SDK. - [Qwen-Audio-TTS/CosyVoice iOS SDK](https://docs.qwencloud.com/api-reference/speech-synthesis/cosyvoice/ios-sdk.md): Use the Qwen-Audio-TTS/CosyVoice iOS SDK to turn text into high-quality, expressive speech in your iOS apps. - [Qwen-Audio-TTS/CosyVoice HarmonyOS SDK](https://docs.qwencloud.com/api-reference/speech-synthesis/cosyvoice/harmonyos-sdk.md): Learn about HarmonyOS SDK integration, parameters, APIs, callbacks, and sample code for Qwen-Audio-TTS/CosyVoice real-time speech synthesis. - [Qwen-TTS client events](https://docs.qwencloud.com/api-reference/speech-synthesis/qwen-tts-realtime/client-events.md): Client events are JSON messages sent over a WebSocket connection to control the Qwen-TTS Realtime API session -- configure voice settings, stream text for synthesis, and signal completion. - [Qwen-TTS server events](https://docs.qwencloud.com/api-reference/speech-synthesis/qwen-tts-realtime/server-events.md): WebSocket server reference - [Qwen-TTS realtime Python SDK](https://docs.qwencloud.com/api-reference/speech-synthesis/qwen-tts-realtime/python-sdk.md): Real-time TTS Python SDK - [Qwen-TTS realtime Java SDK](https://docs.qwencloud.com/api-reference/speech-synthesis/qwen-tts-realtime/java-sdk.md): Real-time TTS Java SDK - [Speech synthesis](https://docs.qwencloud.com/api-reference/speech-synthesis/qwen-tts.md): Qwen-TTS API reference - [Create a cloned voice](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-cloning/cosyvoice/create-voice.md): Clone a voice from audio for Qwen-Audio-TTS or CosyVoice TTS models. Returns a `voice_id` that you can use in [Qwen-Audio-TTS](/developer-guides/speech/tts-models) or [CosyVoice synthesis calls](/api-reference/speech-synthesis/cosyvoice/python-sdk). - [List cloned voices](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-cloning/cosyvoice/list-voices.md): Returns a list of Qwen-Audio-TTS or CosyVoice cloned voices with optional prefix filtering and pagination. - [Query a cloned voice](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-cloning/cosyvoice/query-voice.md): Returns details about a specific Qwen-Audio-TTS or CosyVoice cloned voice, including its status, creation time, and the original audio URL. - [Update a cloned voice](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-cloning/cosyvoice/update-voice.md): Replace the audio of an existing Qwen-Audio-TTS or CosyVoice cloned voice. The voice ID remains the same. - [Delete a cloned voice](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-cloning/cosyvoice/delete-voice.md): Deletes a Qwen-Audio-TTS or CosyVoice cloned voice and releases its quota. - [Create a cloned voice](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-cloning/qwen/create-voice.md): Clone a voice from audio for Qwen TTS or Qwen-Omni-Realtime models. Returns a `voice` name that you can use in [Qwen TTS](/api-reference/speech-synthesis/qwen-tts), [Realtime streaming TTS](/api-reference/speech-synthesis/qwen-tts-realtime/client-events), or [Realtime Multimodal API](/api-reference/real-time-multimodal/client-events) calls. - [List cloned voices](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-cloning/qwen/list-voices.md): Returns a paginated list of Qwen cloned voices under your account. - [Delete a cloned voice](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-cloning/qwen/delete-voice.md): Deletes a Qwen cloned voice and releases its quota. - [Python SDK](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-cloning/cosyvoice-sdk/python-sdk.md): Qwen-Audio-TTS/CosyVoice voice cloning Python SDK reference (VoiceEnrollmentService). - [Java SDK](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-cloning/cosyvoice-sdk/java-sdk.md): Qwen-Audio-TTS/CosyVoice voice cloning Java SDK reference (VoiceEnrollmentService). - [Create a designed voice](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-design/cosyvoice/create-voice.md): Design a voice from a text description for CosyVoice TTS models. Returns a `voice_id` and Base64-encoded preview audio. - [List designed voices](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-design/cosyvoice/list-voices.md): Returns a list of CosyVoice designed voices with optional prefix filtering and pagination. Uses the same `voice-enrollment` model as voice cloning — use the `prefix` filter to narrow results (designed voices follow the pattern `{target_model}-vd-{prefix}-{unique_id}`). - [Query a designed voice](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-design/cosyvoice/query-voice.md): Returns details about a specific CosyVoice designed voice, including its status, voice prompt, and preview text. - [Delete a designed voice](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-design/cosyvoice/delete-voice.md): Deletes a CosyVoice designed voice and releases its quota. - [Create a voice](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-design/qwen/create-voice.md): Create a custom voice from a text description and return preview audio. - [List designed voices](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-design/qwen/list-voices.md): Returns a paginated list of voices under your account. - [Query a voice](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-design/qwen/query-voice.md): Returns details about a specific voice. - [Delete a voice](https://docs.qwencloud.com/api-reference/speech-synthesis/voice-design/qwen/delete-voice.md): Deletes a voice and releases its quota. ## Speech-to-Speech - [Qwen-Omni client events](https://docs.qwencloud.com/api-reference/real-time-multimodal/client-events.md): WebSocket client reference - [Qwen-Omni server events](https://docs.qwencloud.com/api-reference/real-time-multimodal/server-events.md): WebSocket server reference - [Qwen-Omni Python SDK](https://docs.qwencloud.com/api-reference/real-time-multimodal/realtime-python-sdk.md): Qwen-Omni-Realtime Python SDK - [Qwen-Omni Java SDK](https://docs.qwencloud.com/api-reference/real-time-multimodal/realtime-java-sdk.md): Qwen-Omni-Realtime Java SDK - [Real-time multimodal interaction flow](https://docs.qwencloud.com/api-reference/real-time-multimodal/interaction-process.md): The real-time multimodal interaction flow between the server and the client. - [Qwen-Audio-Realtime WebSocket API](https://docs.qwencloud.com/api-reference/qwen-audio-realtime/websocket-api.md): Qwen-Audio-Realtime WebSocket connection protocol, request headers, core concepts, and interaction flows - [Qwen-Audio-Realtime Client Events](https://docs.qwencloud.com/api-reference/qwen-audio-realtime/client-events.md): Qwen-Audio-Realtime API client event reference - [Qwen-Audio-Realtime Server Events](https://docs.qwencloud.com/api-reference/qwen-audio-realtime/server-events.md): Qwen-Audio-Realtime API server event reference - [Qwen-Audio-3.0-Realtime real-time voice conversation Android SDK](https://docs.qwencloud.com/api-reference/qwen-audio-realtime/android-sdk.md): Use the Android SDK for Qwen-Audio-3.0-Realtime to build real-time voice conversations with audio input and audio or text output. - [Qwen-Audio-3.0-Realtime real-time voice conversation iOS SDK](https://docs.qwencloud.com/api-reference/qwen-audio-realtime/ios-sdk.md): Use the iOS SDK for Qwen-Audio-3.0-Realtime to build real-time voice conversations with audio input and audio or text output. - [Qwen-Audio-3.0-Realtime real-time voice conversation HarmonyOS SDK](https://docs.qwencloud.com/api-reference/qwen-audio-realtime/harmonyos-sdk.md): Use the HarmonyOS SDK for Qwen-Audio-3.0-Realtime to build real-time voice conversations with audio input and audio or text output. - [LiveTranslate client events](https://docs.qwencloud.com/api-reference/speech-translation/livetranslate-realtime/client-events.md): WebSocket client reference for the Qwen real-time speech and audiovisual translation API, including event types, parameters, and examples. - [LiveTranslate server events](https://docs.qwencloud.com/api-reference/speech-translation/livetranslate-realtime/server-events.md): WebSocket server reference for the Qwen real-time speech and audiovisual translation API, including event types, parameters, and examples. - [LiveTranslate Python SDK](https://docs.qwencloud.com/api-reference/speech-translation/livetranslate-realtime/python-sdk.md): LiveTranslate Python SDK - [LiveTranslate Java SDK](https://docs.qwencloud.com/api-reference/speech-translation/livetranslate-realtime/java-sdk.md): LiveTranslate Java SDK - [Audio and video translation](https://docs.qwencloud.com/api-reference/speech-translation/audio-video-translation-api.md): LiveTranslate API reference ## Realtime API - [Realtime API overview](https://docs.qwencloud.com/api-reference/realtime-api/overview.md): The Realtime API provides multiple transport protocols, each optimized for different requirements such as performance, latency, weak-network resilience, and integration cost - [SDK download](https://docs.qwencloud.com/api-reference/realtime-api/sdk-download.md): Download AOQ SDK and WebSocket SDK - [Token authentication](https://docs.qwencloud.com/api-reference/realtime-api/token-auth.md): Learn how the Realtime API authenticates connections with tokens, including how to get an API key and how to authenticate over the WebSocket, WebRTC, and AOQ protocols - [Connect to a model](https://docs.qwencloud.com/api-reference/realtime-api/connect-model.md): Connect to Realtime API models and applications over the AOQ, WebRTC, and WebSocket protocols. Covers the connection flow, sequence diagrams, and code examples for each protocol - [SDK overview](https://docs.qwencloud.com/api-reference/realtime-api/aoq-sdk-intro.md): AOQ SDK platform support and architecture overview - [Android SDK](https://docs.qwencloud.com/api-reference/realtime-api/android-sdk.md): AOQ Android SDK API reference - [iOS SDK](https://docs.qwencloud.com/api-reference/realtime-api/ios-sdk.md): AOQ iOS SDK API reference - [HarmonyOS SDK](https://docs.qwencloud.com/api-reference/realtime-api/harmonyos-sdk.md): AOQ HarmonyOS SDK API reference - [Windows SDK](https://docs.qwencloud.com/api-reference/realtime-api/windows-sdk.md): AOQ Windows SDK C++ API reference - [macOS SDK](https://docs.qwencloud.com/api-reference/realtime-api/macos-sdk.md): AOQ macOS SDK Objective-C API reference - [Electron SDK](https://docs.qwencloud.com/api-reference/realtime-api/electron-sdk.md): AOQ Client SDK Electron API reference - [Linux Python SDK](https://docs.qwencloud.com/api-reference/realtime-api/linux-python-sdk.md): AOQ Client SDK Linux Python API reference - [Linux C++ SDK](https://docs.qwencloud.com/api-reference/realtime-api/linux-cpp-sdk.md): AOQ Client SDK Linux C++ API reference - [Connection management](https://docs.qwencloud.com/api-reference/realtime-api/connection-management.md): AOQ SDK connection state diagram, migration rules, and API - [Media stream control](https://docs.qwencloud.com/api-reference/realtime-api/media-stream-control.md): AOQ SDK media stream send/stop control - [Audio features](https://docs.qwencloud.com/api-reference/realtime-api/audio-features.md): AOQ SDK audio capture, playback, and codec configuration - [Custom audio playback](https://docs.qwencloud.com/api-reference/realtime-api/custom-audio-playback.md): Play audio returned by AOQ using an external player - [Custom audio capture](https://docs.qwencloud.com/api-reference/realtime-api/custom-audio-capture.md): Use an external audio source instead of the device microphone - [Video features](https://docs.qwencloud.com/api-reference/realtime-api/video-features.md): AOQ SDK video capture, preview, and encoding configuration - [Custom video input](https://docs.qwencloud.com/api-reference/realtime-api/custom-video-input.md): Use an external video source instead of the device camera ## Text Embeddings - [OpenAI compatible embedding](https://docs.qwencloud.com/api-reference/text-embedding/openai-embedding.md): OpenAI-compatible embedding - [DashScope embedding](https://docs.qwencloud.com/api-reference/text-embedding/dashscope-embedding.md): DashScope embedding API ## Multimodal Embeddings - [DashScope multimodal embedding](https://docs.qwencloud.com/api-reference/multimodal-embedding/dashscope-multimodal-embedding.md): Multimodal embedding API ## Reranking - [OpenAI compatible reranking](https://docs.qwencloud.com/api-reference/rerank/openai-rerank.md): OpenAI-compatible reranking API - [DashScope reranking](https://docs.qwencloud.com/api-reference/rerank/dashscope-rerank.md): DashScope reranking API ## Platform API - [Conversations](https://docs.qwencloud.com/api-reference/platform-api/conversations.md): Auto-managed chat history - [Create conversation](https://docs.qwencloud.com/api-reference/platform-api/conversations/create-conversation.md): Create a conversation with optional initial message items. - [Retrieve conversation](https://docs.qwencloud.com/api-reference/platform-api/conversations/retrieve-conversation.md): Retrieve a conversation by its ID. - [Update conversation](https://docs.qwencloud.com/api-reference/platform-api/conversations/update-conversation.md): Update a conversation's metadata. This completely replaces existing metadata. - [Delete conversation](https://docs.qwencloud.com/api-reference/platform-api/conversations/delete-conversation.md): Delete a conversation. Message items are not deleted. - [Create items](https://docs.qwencloud.com/api-reference/platform-api/conversations/create-items.md): Add message items to a conversation. - [List items](https://docs.qwencloud.com/api-reference/platform-api/conversations/list-items.md): List message items in a conversation. - [Retrieve item](https://docs.qwencloud.com/api-reference/platform-api/conversations/retrieve-item.md): Retrieve a message item by its ID. - [Delete item](https://docs.qwencloud.com/api-reference/platform-api/conversations/delete-item.md): Delete a message item from a conversation. - [File](https://docs.qwencloud.com/api-reference/platform-api/file.md): File management API - [Upload file](https://docs.qwencloud.com/api-reference/platform-api/file/upload-file.md): Upload a file for document analysis or batch processing. You can store up to 10,000 files and 100 GB total. Files never expire. - [Retrieve file](https://docs.qwencloud.com/api-reference/platform-api/file/retrieve-file.md): Retrieve file details by file ID. - [List files](https://docs.qwencloud.com/api-reference/platform-api/file/list-files.md): List all files in your account (uploaded files and batch results), with filtering by purpose, creation time, and pagination. - [Delete file](https://docs.qwencloud.com/api-reference/platform-api/file/delete-file.md): Delete a file by its ID. - [Create batch](https://docs.qwencloud.com/api-reference/platform-api/batch/create-batch.md): Create a batch job that processes all requests in the uploaded input file asynchronously. - [Retrieve batch](https://docs.qwencloud.com/api-reference/platform-api/batch/retrieve-batch.md): Check the status of a batch job and retrieve output file IDs when the job completes. - [List batches](https://docs.qwencloud.com/api-reference/platform-api/batch/list-batches.md): List batch jobs for your account. Results are sorted by creation time in descending order. Only tasks from the last 30 days are available. - [Cancel batch](https://docs.qwencloud.com/api-reference/platform-api/batch/cancel-batch.md): Cancel an in-progress or queued batch job. The status changes to `cancelling` while currently executing requests complete, then to `cancelled`. Completed requests before cancellation are still billed. ## Toolkit & Framework - [OpenAI compatibility](https://docs.qwencloud.com/api-reference/toolkitframework/openai-compatible/overview.md): Migrate from OpenAI by changing three parameters: base_url, api_key, and model. ## More - [Generate a temporary API key](https://docs.qwencloud.com/api-reference/more/generate-a-temporary-api-key.md): Short-lived access tokens - [Manage asynchronous tasks](https://docs.qwencloud.com/api-reference/more/manage-asynchronous-tasks.md): Track and control async jobs ## Billing - [Billing overview](https://docs.qwencloud.com/resources/billing-overview.md): View bills, manage payments, and track spending - [Free quota](https://docs.qwencloud.com/resources/free-quota.md): New user free quota - [Use and manage coupons](https://docs.qwencloud.com/resources/coupons.md): View, use, and manage your coupons - [Billing and cost management](https://docs.qwencloud.com/resources/bill-query.md): Analyze and manage costs - [Overdue payment protection](https://docs.qwencloud.com/resources/overdue-payment-protection.md): Understand grace periods for overdue payments ## FAQ - [Account & access](https://docs.qwencloud.com/resources/faq-account.md): Keys, permissions, access - [Billing & pricing](https://docs.qwencloud.com/resources/faq-billing.md): Payments and costs Q&A - [Text generation FAQ](https://docs.qwencloud.com/resources/faq-text-generation.md): Common questions about streaming, context management, context caching, structured output, thinking mode, function calling, and batch. - [Images & videos FAQ](https://docs.qwencloud.com/resources/faq-images-videos.md): Common questions about image and video generation — billing, API errors, model differences, input requirements, and output URLs. - [Audio & speech FAQ](https://docs.qwencloud.com/resources/faq-audio-speech.md): CosyVoice TTS, Qwen-Omni Realtime, and Fun-ASR — common questions about synthesis, real-time conversation, and speech recognition. - [Embedding & reranking FAQ](https://docs.qwencloud.com/resources/faq-embedding-reranking.md): Common questions about text embeddings, multimodal embeddings, and reranking — model selection, dimensions, batch limits, and use cases. ## Changelog - [Model releases](https://docs.qwencloud.com/changelog/models.md): New launches and updates - [Platform updates](https://docs.qwencloud.com/changelog/platform.md): Features and improvements - [Legal updates](https://docs.qwencloud.com/changelog/legal-updates.md) ## OpenAPI Specs - [openapi-anthropic](https://docs.qwencloud.com/openapi-anthropic.json): Call Qwen models through the Anthropic-compatible Messages API. Supports thinking, tool use, streaming, image/video understanding, and context caching. Authentication: pass your API key via the `x-api-key` header or the `Authorization: Bearer` header. - [openapi-dashscope](https://docs.qwencloud.com/openapi-dashscope.json): Call Qwen models using the DashScope native HTTP API. Supports text and multimodal models, streaming, tool calls, and structured output. - [openapi-openai-chat](https://docs.qwencloud.com/openapi-openai-chat.json): Call Qwen models using the OpenAI-compatible Chat API. Supports text and multimodal models, streaming, tool calls, and structured output. - [openapi-openai-responses](https://docs.qwencloud.com/openapi-openai-responses.json): Call Qwen models using the OpenAI-compatible Responses API. Supports built-in tools, multi-turn context management, and thinking mode. - [openapi-decision-model](https://docs.qwencloud.com/openapi-decision-model.json): Call POST /compatible-mode/v1/systemone to use the QwenCloud decision model (decision-model-preview), which performs classification, yes-or-no decisions, and scoring in a single forward pass, returning probability distributions and confidence, without generating text. Suitable for high-frequency structured decisions such as ticket routing, content moderation, agent routing, and result verification. - [openapi-qwen-image-edit](https://docs.qwencloud.com/openapi-qwen-image-edit.json): Qwen-Image editing API. Supports single-image editing, multi-image fusion, style transfer, text editing, element manipulation, and more. - [openapi-qwen-image](https://docs.qwencloud.com/openapi-qwen-image.json): Qwen-Image text-to-image generation API. Supports synchronous calls for all models and asynchronous calls for legacy models. - [openapi-qwen-image-openai](https://docs.qwencloud.com/openapi-qwen-image-openai.json): Call the Qwen image generation and editing models through the OpenAI Images-compatible protocol for text-to-image (T2I) and image-to-image/editing (I2I). - [openapi-wan-t2i-v2](https://docs.qwencloud.com/openapi-wan-t2i-v2.json): Generate images from text prompts using the Wan text-to-image model family. Supports various artistic styles and realistic photographic effects to meet diverse creative needs. This API uses an asynchronous task pattern: submit a task with POST, then poll for results with GET. - [openapi-wan25-image-edit](https://docs.qwencloud.com/openapi-wan25-image-edit.json): Wan2.5 general image editing API. Edits images using text prompts, preserving subject consistency. Supports single-image editing and multi-image fusion with up to three reference images. - [openapi-wan26-image](https://docs.qwencloud.com/openapi-wan26-image.json): Wan2.6 image generation and editing API. Supports multi-image input, image editing, and interleaved text-image output. - [openapi-wan27-image](https://docs.qwencloud.com/openapi-wan27-image.json): Wan2.7 image generation and editing API. Supports text-to-image, multi-image editing, interactive editing with bounding boxes, and image set generation. - [openapi-z-image](https://docs.qwencloud.com/openapi-z-image.json): Z-Image text-to-image generation API. - [openapi-image-translation](https://docs.qwencloud.com/openapi-image-translation.json): Qwen-MT-Image accurately translates text in images while preserving the original layout. It supports domain hints, sensitive word filtering, and terminology intervention. `qwen-mt-image-2.0` supports both synchronous and asynchronous modes. See [Synchronous calls](/api-reference/image-translation/qwen-mt-image/synchronous) for the sync API. Asynchronous workflow: 1. **Create task**: POST to submit a task and receive a task_id. 2. **Query result**: Poll by task_id until the task completes and returns the image URL. - [openapi-image](https://docs.qwencloud.com/openapi-image.json): DashScope Image APIs for image generation, editing, specialized image tasks, and multimodal embeddings. - [openapi-batch](https://docs.qwencloud.com/openapi-batch.json): Submit batch inference jobs via file upload at 50% of real-time API cost. OpenAI-compatible. - [openapi-conversations](https://docs.qwencloud.com/openapi-conversations.json): Auto-managed chat history for multi-turn context across devices and sessions. - [openapi-file](https://docs.qwencloud.com/openapi-file.json): Upload and manage files for document analysis or batch processing. - [openapi-reranking](https://docs.qwencloud.com/openapi-reranking.json): Rerank retrieved documents by semantic relevance to improve search accuracy in RAG and retrieval systems. - [openapi-qwen-asr](https://docs.qwencloud.com/openapi-qwen-asr.json): API reference for Qwen-ASR audio file recognition. Supports OpenAI-compatible, DashScope synchronous, and DashScope asynchronous protocols. - [openapi-qwen-tts](https://docs.qwencloud.com/openapi-qwen-tts.json): API reference for the Qwen speech synthesis model (Qwen-TTS, Qwen3-TTS-Flash, Qwen3-TTS-Instruct-Flash). Supports streaming and non-streaming output. - [openapi-voice-cloning-cosyvoice](https://docs.qwencloud.com/openapi-voice-cloning-cosyvoice.json) - [openapi-voice-cloning-cosyvoice-delete](https://docs.qwencloud.com/openapi-voice-cloning-cosyvoice-delete.json) - [openapi-voice-cloning-cosyvoice-list](https://docs.qwencloud.com/openapi-voice-cloning-cosyvoice-list.json) - [openapi-voice-cloning-cosyvoice-query](https://docs.qwencloud.com/openapi-voice-cloning-cosyvoice-query.json) - [openapi-voice-cloning-cosyvoice-update](https://docs.qwencloud.com/openapi-voice-cloning-cosyvoice-update.json) - [openapi-voice-cloning-qwen](https://docs.qwencloud.com/openapi-voice-cloning-qwen.json) - [openapi-voice-cloning-qwen-delete](https://docs.qwencloud.com/openapi-voice-cloning-qwen-delete.json) - [openapi-voice-cloning-qwen-list](https://docs.qwencloud.com/openapi-voice-cloning-qwen-list.json) - [openapi-voice-design-cosyvoice](https://docs.qwencloud.com/openapi-voice-design-cosyvoice.json) - [openapi-voice-design-cosyvoice-delete](https://docs.qwencloud.com/openapi-voice-design-cosyvoice-delete.json) - [openapi-voice-design-cosyvoice-list](https://docs.qwencloud.com/openapi-voice-design-cosyvoice-list.json) - [openapi-voice-design-cosyvoice-query](https://docs.qwencloud.com/openapi-voice-design-cosyvoice-query.json) - [openapi-voice-design](https://docs.qwencloud.com/openapi-voice-design.json): Create and manage custom voices from text descriptions for use with Qwen TTS models. - [openapi-voice-design-delete](https://docs.qwencloud.com/openapi-voice-design-delete.json) - [openapi-voice-design-list](https://docs.qwencloud.com/openapi-voice-design-list.json) - [openapi-voice-design-query](https://docs.qwencloud.com/openapi-voice-design-query.json) - [openapi-text-embedding](https://docs.qwencloud.com/openapi-text-embedding.json): API reference for text embedding models. Supports OpenAI-compatible and DashScope protocols. - [openapi-happyhorse-image-to-video](https://docs.qwencloud.com/openapi-happyhorse-image-to-video.json): Generate videos from an image using the HappyHorse model. Submit a task asynchronously, then poll `GET /tasks/{task_id}` for the result. - [openapi-happyhorse-ref-to-video](https://docs.qwencloud.com/openapi-happyhorse-ref-to-video.json): The HappyHorse reference-to-video model lets you provide multiple reference images and a text prompt to generate a video that combines subjects from the images into a scene based on the prompt. Submit a task asynchronously, then poll `GET /tasks/{task_id}` for the result. - [openapi-happyhorse-text-to-video](https://docs.qwencloud.com/openapi-happyhorse-text-to-video.json): Generate videos from text using the HappyHorse model. Submit a task asynchronously, then poll `GET /tasks/{task_id}` for the result. - [openapi-happyhorse-video-editing](https://docs.qwencloud.com/openapi-happyhorse-video-editing.json): Edit videos using the HappyHorse model with text instructions and optional reference images. Submit a task asynchronously, then poll `GET /tasks/{task_id}` for the result. - [openapi-wan-video-editing](https://docs.qwencloud.com/openapi-wan-video-editing.json): Wan unified video editing API. Supports multimodal input (text, image, video) with five core capabilities: multi-image reference, video repainting, local editing, video extension, and frame expansion. - [openapi-wan-image-to-animation](https://docs.qwencloud.com/openapi-wan-image-to-animation.json): Animate a character image by transferring actions and expressions from a reference video using the wan2.2-animate-move model. - [openapi-wan-i2v-first-frame](https://docs.qwencloud.com/openapi-wan-i2v-first-frame.json): Generate videos from a first-frame image and text prompt using Wan image-to-video models. Supports audio synchronization, multi-shot narrative, and multiple resolution tiers. - [openapi-wan-i2v-first-last](https://docs.qwencloud.com/openapi-wan-i2v-first-last.json): Generate a smoothly transitioning video from a first frame image, a last frame image, and a text prompt using the Wan kf2v model. - [openapi-wan-ref-to-video](https://docs.qwencloud.com/openapi-wan-ref-to-video.json): Wan reference-to-video API. Generates performance videos from reference images or videos with multimodal input (text, image, video). Supports single or multi-character interactions, multi-shot narrative, and audio-video sync. - [openapi-wan-text-to-video](https://docs.qwencloud.com/openapi-wan-text-to-video.json): Wan text-to-video generation API. Supports multimodal input (text, images, audio) and generates videos up to 15 seconds at 1080P resolution. Uses asynchronous task submission — submit a task, then poll for results. - [openapi-wan-character-swap](https://docs.qwencloud.com/openapi-wan-character-swap.json): Wan video character swap API. Replaces the main character in a video with a character from an image, preserving the scene, lighting, and tone of the original video. Uses asynchronous task processing. - [openapi-wan27-image-to-video](https://docs.qwencloud.com/openapi-wan27-image-to-video.json): The Wan 2.7 image-to-video model now supports multi-modal input — including images, audio, and video — and performs three main tasks: video generation from the first frame, video generation from the first and last frames, and video continuation. Submit a task asynchronously, then poll `GET /tasks/{task_id}` for the result. - [openapi-wan27-ref-to-video](https://docs.qwencloud.com/openapi-wan27-ref-to-video.json): Wan 2.7 reference-to-video API. Generates performance videos from reference images or videos with multimodal input (text, image, video). Uses the new protocol with media array input, resolution+ratio parameters, and enhanced response metadata. - [openapi-wan27-text-to-video](https://docs.qwencloud.com/openapi-wan27-text-to-video.json): Generate videos from text using the Wan 2.7 model. Submit a task asynchronously, then poll `GET /tasks/{task_id}` for the result. - [openapi-wan27-video-editing](https://docs.qwencloud.com/openapi-wan27-video-editing.json): Edit videos using the Wan 2.7 model. Supports multimodal inputs such as text, images, and videos for video editing. Submit a task asynchronously, then poll `GET /tasks/{task_id}` for the result. - [openapi-wan30-video](https://docs.qwencloud.com/openapi-wan30-video.json): Wan 3.0 is an All-in-One video generation model that supports text-to-video, image-to-video (first-frame / first+last-frame), reference-to-video, and file-to-video, generating videos up to 30 seconds. Submit a task asynchronously, then poll `GET /tasks/{task_id}` for the result. - [openapi-happyoyster-acting](https://docs.qwencloud.com/openapi-happyoyster-acting.json): HappyOyster role-play (Acting) mode Open API. Create and manage Worlds, exchange travel credentials, enter a room on the client, send text process instructions, pause/resume/end Travels, and query history and artifacts. The server calls management endpoints with the primary API Key; the client experiences the real-time RTC channel via a temporary API Key and ticket. Defaults to 9:16 portrait streaming (16:9 landscape is also supported); rewind is not supported. - [openapi-happyoyster-adventure](https://docs.qwencloud.com/openapi-happyoyster-adventure.json): HappyOyster world-exploration (Adventure) mode Open API. Create and manage Worlds, exchange travel credentials, and query history and artifacts. Server-side calls use the primary API Key over standard HTTPS REST. Clients experience the World in real time over the RTC channel using a temporary API Key and a ticket. - [openapi-happyoyster-directing](https://docs.qwencloud.com/openapi-happyoyster-directing.json): HappyOyster real-time directing (Directing) mode Open API. Create and manage Worlds, exchange experience credentials, enter rooms, send process instructions and script updates, pause/resume/rewind/end Travels, and query history and artifacts. The server side is called with the primary API Key over standard HTTPS REST. The client experiences the content in real time over an RTC channel using a temporary API Key and ticket.