Qwen 3.8 27B

NEW

Alibaba Qwen 3.8 27B dense vision-language model on Cerebras (~1,850 tok/s). Vision (base64 PNG/JPEG, max 10 images), function calling, reasoning (on by default at high, off via effort). 131K context (65K free tier), 40K max output.

131K context·$0.99 in·$1.49 out·Aug 2026 release·Vision, Reasoning, Tools / functions

Available on

Cerebras

Providers

Where Qwen 3.8 27B runs in Big-AGI, with each service's own model ID and USD-per-1M-token rates. The summary above prefers the creator's claim; rates below are each service's own.

ServiceModel IDContextInputOutputCache read

Cerebras

qwen-3.8-27b

131K

$0.99

$1.49

$0.99

Specs as reported by each service · usage over the last 2 days · refreshed hourly