Qwen3.8 27B
by IteraCompute · family qwen · listed Aug 2026RTVW
Dense 27B vision-language model for coding, agent tasks, and image and video understanding
Current rates USD per 1M tokens
Input$0.30
Output$2.50
Cache read$0.03
Cache write—
Against the market
On the record
- Model id
qwen/qwen3.8-27b- Context window
- 328K tokens
- Max output
- 66K 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
- iteracompute.com/docs.html
Back of the envelope
≈
Also listed at
- AMDfree in · free out
- Hetznerfree in · free out
- LLM Gateway$0.08 in · $0.35 out
- DevPass (LLM Gateway)$0.08 in · $0.35 out
- Cortecs$0.10 in · $0.40 out
- RunInfra$0.10 in · $0.40 out
- NanoGPT$0.15 in · $0.70 out
- Deep Infra$0.20 in · $2.50 out
- CrofAI$0.20 in · $1.50 out
- AKI.IO$0.30 in · $2.20 out
- OrcaRouter$0.33 in · $2.40 out
- Kosmik Compute$0.35 in · $2.20 out
- CoreWeave$0.40 in · $3.00 out
- Hugging Face$0.40 in · $3.00 out
- ai&$0.40 in · $3.00 out