All Models

Qwen3.8 Flash Next

qwen Reasoning Tool Calling Attachments Open Weights Structured Output

Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding

Providers 2
Released Aug 27, 2026
Input Modalities text, image
Output Modalities text
Tarsk Use coding

Benchmarks

55.8
Intelligence Index
73.1
Coding Index

Available Providers (2)

Provider Model ID Input Cost Output Cost Context Max Output Docs
AMD Qwen3.8-Flash-Next $0.15/MTok $0.47/MTok 262.1K 131.1K
Cortecs qwen3.8-flash-next $0.20/MTok $0.50/MTok 262.1K 64K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output