All Models

Qwen 3.8 27B Obliterated

qwen Reasoning Tool Calling Attachments Open Weights Structured Output

Qwen 3.8 27B Obliterated is an open-weight multimodal model LoRA-tuned for fewer refusals across chat, coding, reasoning, tool use, and long-context work.

Providers 1
Released Jul 29, 2026
Input Modalities text, image
Output Modalities text
Tarsk Use coding

Available Providers (1)

Provider Model ID Input Cost Output Cost Context Max Output Docs
NanoGPT qwen/qwen3.8-27b-obliterated $0.25/MTok $1.50/MTok 262.1K 32.8K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output