Qwen3 8B
by Hugging Face · family qwen · listed Apr 2025RTW
Dense 8B Qwen3 model with switchable thinking for chat, reasoning, and tool use
Current rates USD per 1M tokens
Input$0.07
Output$0.18
Cache read—
Cache write—
Against the market
On the record
- Model id
Qwen/Qwen3-8B- Context window
- 41K tokens
- Max output
- 33K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2025-04-29
- Last updated
- 2025-04-29
- Provider docs
- huggingface.co/docs/inference-providers
Back of the envelope
≈
Also listed at
- SiliconFlow (China)free in · free out
- SiliconFlow$0.06 in · $0.06 out
- Alibaba (China)$0.072 in · $0.287 out
- Alibaba$0.18 in · $0.70 out
- Thinking Machines$0.195 in · $0.60 out
- NanoGPT$0.47 in · $0.47 out