Qwen3.5 9B
by routing.run · family qwen · listed Feb 2026RTW
Qwen instruction model for multilingual chat, reasoning, and tool use
Current rates USD per 1M tokens
Input$0.16
Output$0.48
Cache read—
Cache write—
Against the market
On the record
- Model id
qwen3.5-9b- Context window
- 262K tokens
- Max output
- 32K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-02-23
- Last updated
- 2026-02-23
- Provider docs
- docs.routing.run/api-reference/models
Back of the envelope
≈
Also listed at
- CrofAI$0.04 in · $0.15 out
- Kilo Gateway$0.05 in · $0.15 out
- NanoGPT$0.05 in · $0.15 out
- Mixlayer$0.10 in · $0.40 out
- LLM Gateway$0.10 in · $0.15 out
- Deep Infra$0.10 in · $0.15 out
- SiliconFlow$0.10 in · $0.15 out
- OpenRouter$0.10 in · $0.15 out
- OVHcloud AI Endpoints$0.12 in · $0.18 out
- Regolo AI$0.15 in · $0.60 out
- Hugging Face$0.17 in · $0.25 out
- Together AI$0.17 in · $0.25 out
- SiliconFlow (China)$0.22 in · $1.74 out
- Pioneer$0.30 in · $0.30 out