Qwen3.6 27B
by Phala · family qwen · listed Apr 2026RTVW
Qwen vision-language model for visual reasoning, documents, and agent tasks
Current rates USD per 1M tokens
Input$0.32
Output$3.25
Cache read$0.03
Cache write—
Against the market
On the record
- Model id
qwen/qwen3.6-27b- Context window
- 262K tokens
- Max output
- 66K tokens
- Input modalities
- text, image, video
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-04-22
- Last updated
- 2026-04-22
Back of the envelope
≈
Also listed at
- QVACfree in · free out
- DevPass (LLM Gateway)$0.15 in · $1.35 out
- LLM Gateway$0.15 in · $1.35 out
- NanoGPT$0.203 in · $2.24 out
- SiliconFlow$0.30 in · $3.20 out
- Ambient$0.32 in · $3.20 out
- Abacus$0.32 in · $3.20 out
- OpenRouter$0.32 in · $3.20 out
- ai&$0.32 in · $3.20 out
- Deep Infra$0.32 in · $3.20 out
- Merge Gateway$0.413 in · $2.48 out
- Ofox$0.43 in · $2.57 out
- Cortecs$0.446 in · $3.01 out
- SiliconFlow (China)$0.45 in · $2.70 out
- Kilo Gateway$0.45 in · $2.70 out