Qwen3.5 27B Thinking
Qwen vision-language model for visual reasoning, documents, and agent tasks
Model facts
- Context window
- 26K tokens
- Maximum output
- 66K tokens
- Cheapest paid input
- $0.27 per 1M tokens
- Cheapest paid output
- $2.16 per 1M tokens
- Open weights
- yes
- Providers
- 1
Capabilities and modalities
reasoning, tool calling, attachments, temperature control, open weights, text, image, video.
Observed price history
- 2026-08-24: $0.27 input / $2.16 output per 1M tokens
API providers
- NanoGPT — model id qwen3.5-27b:thinking; $0.27 input / $2.16 output per 1M tokens; provider documentation