Qwen3.8 27B
by Wafer · family qwen · listed Aug 2026RTVW
Dense 27B vision-language model for coding, agent tasks, and image understanding
Current rates USD per 1M tokens
Input$0.06
Output$2.30
Cache read$0.05
Cache write—
Against the market
On the record
- Model id
Qwen3.8-27B- Context window
- 262K tokens
- Max output
- 33K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-08-14
- Last updated
- 2026-08-14
- Provider docs
- docs.wafer.ai/serverless/models
Back of the envelope
≈
Also listed at
- AMDfree in · free out
- Hetznerfree in · free out
- IteraComputefree in · free out
- CedarLLM$0.03 in · $1.15 out
- Adaption$0.039 in · $1.25 out
- NEAR AI Cloud$0.04 in · $1.35 out
- engy$0.045 in · $0.32 out
- Vercel AI Gateway$0.06 in · $2.20 out
- DevPass (LLM Gateway)$0.08 in · $0.35 out
- Liquid Inference$0.08 in · $0.525 out
- LLM Gateway$0.08 in · $0.35 out
- Entrim$0.10 in · $0.40 out
- Cortecs$0.10 in · $0.40 out
- RunInfra$0.10 in · $0.40 out
- Powerspring$0.104 in · $0.417 out