Alibaba
Qwen 3.6 27B
Qwen 3.6 27B — native vision-language dense model with strong agentic coding, STEM reasoning, video understanding, and OCR.
qwen3.6-27bPricing
~94%- Input
- $0.0182 / 1,000,000 tokens
- Output
- $0.1512 / 1,000,000 tokens
- Cache read
- $0.00273 / 1,000,000 tokens
- Cache write
- $0.0182 / 1,000,000 tokens
Discount history
Model details
- Input
- text, image
- Output
- text
- Context window
- 256,000 tokens
- Maximum output
- 32,768 tokens
- Availability
- $4.7KUncapped capacity
- Updated
- 11/8/2026, 3:58:06 AM UTC
Capacity is reserved when your request is accepted.
Capabilities
ChatStreamingTool callingVisionReasoning
Supported parameters
max_tokenstemperaturetop_pfrequency_penaltypresence_penaltyrepetition_penaltymin_plogit_biaslogprobstop_logprobsstoptoolstool_choiceresponse_formatseedstructured_outputsinclude_reasoningreasoning