Alibaba Cloud

Image generation and editing with Pro and Turbo variants, up to ten reference images, transparent PNG output, and custom sizes up to 2560x2560.

Qwen image generation and editing with Base and Pro variants, multilingual typography, multi-image references, and controllable 1K or 2K output.

Unified image generation and editing model with class-leading complex Chinese/English text rendering, realistic textures, and multi-image fusion.

Real-time speech synthesis with 19 voices, delivery direction in plain language, inline emotion and sound tags, and audio streamed over SSE or WebSocket.

Audio generation from a written description, with narration, dialogue in up to three cloned voices, sound effects, ambience, and music in one file.

Tiered speech synthesis with over 1,000 voices, 16 languages, 20 Chinese dialects, natural-language delivery direction, and inline emotion tags.

Transcription tuned for voice messages and voice input over a socket, returning each utterance as one complete transcript when the speaker pauses.

Speech-to-text for short clips and long recordings, with sentence segments, word timestamps, and multilingual and Chinese dialect recognition.

Live transcription over a socket, streaming partial words while the speaker talks and a settled sentence at each pause, priced per token.

Duplex speech conversation over one socket, with 27 voices, native web search, tool calling, and separate text and audio token rates.

Upgraded Qwen3.8 Max snapshot with stronger coding, steadier multi-tool agent runs, and sharper chart and document vision across a 1M-token context.

Trillion-scale MoE flagship for coding, long-horizon agents, and professional work, with image and video understanding across a 1M-token context.

Qwen3.7 Max is a flagship text model for coding, productivity, long-running agents, deep thinking, tools, and 1M-token context.

Multimodal reasoner with 256K context, image and video input, function tools, structured JSON, and thinking on by default.

Qwen3.6 27B improves agentic coding, STEM reasoning, spatial vision, OCR, and text, image, and video understanding on 256K context.

Qwen3.6 35B A3B is a 256-expert mixture-of-experts reasoning model with 128K context, function tools, and strict structured JSON output.

Qwen3.5 4B is a low-cost multimodal reasoning model with 256K context, image and video input, function tools, and structured output.

Qwen3.5 122B-A10B is a multimodal reasoning model with 256K context, efficient sparse MoE inference, and text, image, and video input.

Qwen3.5 35B-A3B is an efficient native vision-language model with sparse MoE routing, deep thinking, and text, image, and video input.

Qwen3.5 27B is a dense multimodal reasoning model with fast responses, 256K context, and text, image, and video understanding.

Qwen3.5 9B is a compact multimodal reasoning model with 256K context, image and video input, function tools, and structured output.

Qwen3.5 397B-A17B is a flagship multimodal reasoning model for language, code, agents, GUI tasks, and image and video understanding.

Fast Qwen3.8 vision-language model for coding, agents, and visual understanding, with image and video input, five built-in tools, and a 1M token context.

Fast Qwen3.7 vision-language model for text, image, video, tool use, and agentic tasks, with implicit caching and a 1M token context.

Fast Qwen3.6 vision-language model for agentic coding, math reasoning, spatial understanding, OCR, and text, image, and video input.

Vision-language model with hybrid linear-attention plus sparse MoE, 1M context, and fast multimodal text/image/video inference.

Cost-effective Qwen3.7 vision-language model for text, image, video, coding, tool use, GUI understanding, and 1M-context workflows.

Vision-language model with major upgrades over 3.5: agentic and front-end coding, multimodal recognition, OCR, and object localization.

Multimodal model with hybrid architecture for efficient deep thinking and visual understanding across text, image, and video on a 1M context.

Speech and live video frames in, speech out over one socket, with 56 voices, tool calling during the conversation, and separate text and audio token rates.

Speech in, speech out, over one socket, with separate text and audio token rates and per-turn billing.

Speech in, speech out, over one socket, on the larger Omni tier, with separate text and audio token rates and per-turn billing.

Omni-modal reasoner that reads text, images, audio, and video and answers in text, with a 1M token context, thinking, and native web search.

Cost-efficient omni-modal model handling text, image, audio, and video, with up to 3 hours of audio and 1 hour of video across 90+ languages.

Flagship omni-modal model for text, image, audio, and video. 3h audio, 1h video, 90+ input and 30+ output languages, 55 voice timbres.

Simultaneous spoken translation over a WebSocket. Set the target language, then speak; the model replies in that language with text and audio.

Semantic document reranker. Sorts up to 500 candidates per query by relevance, supports 100+ languages, and accepts a custom sorting instruction.

All-in-one video generation up to 30 seconds with native audio, omni-modal references (images, video, audio, files, web links), and a fast Prime tier.

Multimodal video model supporting T2V, I2V, video editing, and reference-to-video, with high-fidelity output from text, image, or video inputs.

Multimodal video generation model for cinematic, multi-shot stories with native audio-visual sync (lip-sync, dialogue, music, SFX).

Alibaba’s Wan 2.5 video model with text-to-video and image-to-video, native audio, optional custom audio tracks, and 480p to 1080p output.

Alibaba’s Wan 2.2 video family with standard and flash tiers, first and last frame interpolation, and 480p to 1080p output at low cost.

Alibaba’s Wan 2.1 video model with turbo and plus tiers for text-to-video, image-to-video, and first and last frame clips at 480p or 720p.

Image generation and editing companion model: text-to-image, bounding-box edits, and cohesive image sets, with up to 4K output on Pro.

Alibaba’s Wan 2.5 image model with text-to-image and multi-reference editing of up to 3 images at about 1.7 megapixels.

Alibaba’s Wan 2.2 text-to-image model with plus and flash tiers and up to 1440x1440 output at low per-image pricing.

Alibaba’s Wan 2.1 text-to-image model with turbo and plus tiers and up to 1440x1440 output at low per-image pricing.

Text, image, and reference-to-video in one model. Cinematic motion, character consistency across up to 9 references, and synchronized native audio.

Video model offering Text-to-Video, Image-to-Video, Reference-to-Video, and Video Edit modes with high-fidelity, motion-smooth output.

Speed-optimised multimodal embedding, same shape as Vision-Plus, 3× cheaper image/video tokens.

Multimodal embedding producing independent vectors for text, image, and video inputs.

Multilingual text embedding with selectable output dimensions (64–2048). Up to 8,192 tokens per input.