Alibaba
Qwen 3.6 35B A3B
Qwen 3.6 35B A3B — multimodal MoE model on AkashML for agentic coding, reasoning, and long-context workflows.
qwen3-6-35b-a3bPricing
~95%- Input
- $0.004835 / 1,000,000 tokens
- Output
- $0.04835 / 1,000,000 tokens
- Cache read
- $0.000725 / 1,000,000 tokens
- Cache write
- $0.004835 / 1,000,000 tokens
Discount history
Model details
- Input
- text, image
- Output
- text
- Context window
- 262,144 tokens
- Maximum output
- 131,072 tokens
- Availability
- $215Uncapped capacity
- Updated
- 11/8/2026, 4:00:11 AM UTC
Capacity is reserved when your request is accepted.
Capabilities
ChatStreamingTool callingVisionReasoning
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p