Today's price · per 1M tokens
Input
$0.800
per 1M tokens
Output
$4.00
per 1M tokens
Blended
$1.60
blended $/1M — 3:1 weighted input:output
Price receipt
We read Groq's own pricing page on and found Qwen3.8-27B listed with a price on the same row — that read is where the number above comes from, recorded as a new model. We keep the page text we read; its content hash is 4c757d3402.
Overview
Qwen3.8-27B on Groq's LPU at $0.80/$4.00 per 1M tokens and about 450 tokens/sec, with a 131K context window. Groq lists it as a preview model and names it the direct successor to Qwen3.6-27B, which it shut down on 2026-09-14. Text and image in, text out, with thinking and instruct modes.
Deploy this open model on rented GPUs
Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.
Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.
Capabilities
struck through = not supportedSpecifications
- Provider
- Groq
- Context window
- 131K tokens
- Modality
- text, image
- Parameters
- 27B
- Open source
- Yes — open weights available
- Released
- Status
- Preview
- Last updated
- Tags
Availability verified: — listed on Groq's own page