All Models

Qwen3.8 2.4T A95B

qwen Reasoning Tool Calling Open Weights Structured Output

Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows

Providers 9
Released Aug 12, 2026
Input Modalities text, image
Output Modalities text
Tarsk Use coding

Benchmarks

57.7
Intelligence Index
71.9
Coding Index

Available Providers (9)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Requesty qwen3.8-2.4T-A95B $1.80/MTok $5.40/MTok 262.1K 262.1K
Deep Infra Qwen/Qwen3.8-2.4T-A95B $2/MTok $6/MTok 262.1K 131.1K
OpenRouter qwen/qwen3.8-2.4t-a95b $2/MTok $6/MTok 1.0M 262.1K
Vercel AI Gateway alibaba/qwen3.8-2.4t-a95b $2/MTok $6/MTok 262.1K 131.1K
Eden AI qwen/qwen3.8-2.4t-a95b $2/MTok $6/MTok 1M 131.1K
Kilo Gateway qwen/qwen3.8-2.4t-a95b $2/MTok $6/MTok 1M 262.1K
Cortecs qwen3.8-2.4t-a95b $2.50/MTok $6/MTok 262.1K 262.1K
Hugging Face Qwen/Qwen3.8-2.4T-A95B $2.50/MTok $6.25/MTok 262.1K 131.1K
Merge Gateway qwen/qwen3.8-2.4t-a95b $2.50/MTok $6.25/MTok 262.1K 1.0M

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output