qwen3.6-plus
Qwen3.6-Plus was released on April 2, 2026. It was the first model of the Qianwen 3.6 series and was officially called “the model with the strongest programming capabilities in China” at the time. It has achieved a significant jump in agent programming capabilities based on Qwen3.5, scoring 78.8 on SWE-bench Verified and 61.6 on Terminal-Bench 2.0. Its performance surpasses domestic models such as GLM-5 and Kimi-K2.5 with two to three times the number of parameters, and is close to the level of the Claude series. The model supports 1 million Token context windows by default, deeply integrates reasoning, memory and execution capabilities, and demonstrates stable engineering implementation capabilities in code repair, terminal automation and long-term planning tasks. This version is open for calls through the Alibaba Cloud Bailian API and is positioned as an "atmosphere programming" infrastructure for developers.
- Context
- 1000000 tokens
- Max output
- 65536 tokens
- Input
- llm image video
- Output
- llm
Pricing
Input: $0.5 / 1M tokens
Output: $3 / 1M tokens
Cached input: $0.05 / 1M tokens
Cache write: $0.625 / 1M tokens
Endpoints
- openai