Alibaba Qwen · General language
Qwen3-8B
Edge/consumer-GPU tier — runs quantised on 8-12GB VRAM. Output $0.70 non-thinking / $2.10 thinking. Smaller 4B/1.7B/0.6B siblings exist on Hugging Face but are not separately priced in Model Studio.
Open weights · Permissive (Apache, MIT, OpenMDW) · Data checked September 6, 2026 · Not a hands-on evaluation
Model ID qwen3-8b
- Parameters
- 8B dense
- Architecture
- Dense
- Context window
- 131,072 tokensMaximum input
- Max output
- 8,192 tokensPer response
- Input price
- $0.18 per 1M tokens
- Output price
- $0.70 per 1M tokens
- Cached input
- Not published
- Blended price
- $0.31 per 1M tokens3:1 input to output
- Knowledge cutoff
- 2025-03
- Released
- 2025-04
- Status
- ga
- Size band
- 4B to 15B
License and openness
Qwen3-8B is released under the Apache-2.0. This is a permissive license. It generally allows use, modification and redistribution, including commercial use, subject to attribution and notice requirements. License terms can change between versions; confirm the text published with the weights you download.
Capabilities
| Input modalities | text |
|---|---|
| Output modalities | text |
What it is for
Output $0.70 non-thinking / $2.10 thinking. Smaller 4B/1.7B/0.6B siblings exist on Hugging Face but are not separately priced in Model Studio.
At a three-to-one input-to-output ratio, Qwen3-8B costs $0.31 per million tokens blended. A workload of one million input and 330,000 output tokens per day would run about $12.33 per month at list price, before caching or batch discounts.
Cost at list price
| Input | $0.18 per 1M tokens |
|---|---|
| Output | $0.70 per 1M tokens |
| Cached input | Not published |
| Blended, 3:1 | $0.31 per 1M tokens |
Sources
- Source: Alibaba Qwen pricing ↗
- API docs ↗
- Full reference record for Qwen3-8B ↗
- Alibaba Qwen in the reference ↗
Sources checked September 6, 2026. Specifications and prices change without notice; confirm against the provider before you commit.
Other open-weight models from Alibaba Qwen
- Qwen3.8-2.4T-A95B · 2.4T total · 95B active
- Qwen3.8-27B · 27B dense
- Qwen3.6-35B-A3B · 35B total · 3B active
- Qwen3.6-27B · 27B dense
- Qwen3.5-397B-A17B · 397B total · 17B active
- Qwen3.5-122B-A10B · 122B total · 10B active
- Qwen3.5-35B-A3B · 35B total · 3B active
- Qwen3.5-27B · 27B dense
- Qwen3-Coder-Next · Not recorded
- Qwen3-Coder-480B-A35B-Instruct · 480B total · 35B active
- Qwen3-Coder-30B-A3B-Instruct · 30B total · 3B active
- Qwen3-Next-80B-A3B-Thinking · 80B total · 3B active