Reasoning
Tools
Files
Vision
1M

Standard & Paid Price

Standard Price
MeterStandard Price
Input price$0.4000 / 1M tokens
Completion price$1.6000 / 1M tokens
Cache read price$0.0800 / 1M tokens
Cache creation price$0.5000 / 1M tokens
Dynamic pricing · 2 tiers
Billing details
Vendor list price comparison

Description

Alibaba Qwen3.7-Plus — multimodal hybrid agent model that perceives real-world scenes, reads screens and drives GUIs, generates code from visual references, and performs end-to-end navigation inside mobile apps. 1,000,000-token context window (991,808 max input, 983,616 in thinking mode), up to 131,072 output tokens, and a 262,144-token chain-of-thought budget. Accepts text, image, and video input and returns text; supports function calling, structured outputs, and context caching.

Capabilities

Input modalities
text, image, video
Output modalities
text
Tasks
chat, reasoning, vision, file-video-understanding

API endpoints

  • POST /v1/messages (anthropic)
  • POST /v1/chat/completions (openai)