Qwen3 8B
by Alibaba (Qwen)Chat
Qwen instruction model for multilingual chat, reasoning, and tool use
- Context
- 131K tokens
- Max output
- 8,192 tokens
- Parameters
- 8.2B total
- Released
- 2025-04
- Weights
- Open
- Licence
- apache-2.0
alibaba/qwen3-8b · also seen as Qwen/Qwen3-8B, accounts/fireworks/models/qwen3-8b, qwen/qwen3-8b-fp8
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2025-04
- Weights
- Opennot gated
- License
- apache-2.0
- Input
- Text
- Output
- Text
- Context window
- 131,072 max across endpoints
- Max output
- 8,192
- Providers
- 8 + 2 gateways, not counted as providers
- Epoch Capabilities Index
- 136.2 ± 3.7 against price
- Direct price range
- $0.035–$0.200 in · $0.06–$0.70 out per 1M tokens · 6 of 8 providers have a comparable price
More details
- Last updated
- 2025-11-25
- Knowledge cutoff
- 2025-04
- Weights link
- Hugging Face · Qwen/Qwen3-8B
- Parameters
- 8.2B total
- Base model
- Qwen/Qwen3-8B-Base
- Developer country
- China
- Training compute
- 1.8×10²⁴ FLOP
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt cachingunknown
- Web searchunknown
- Computer useunknown
- System messages
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.06 in / $0.06 out per 1M tokens at SiliconFlow on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Qwen3 8B |
|---|---|---|---|---|---|
| Qwen3 4B InstructAlibaba (Qwen) | $0.20 | $0.20 | $0.20 | 262K | +0% |
| gemma-2-9bGoogle | $0.20 | $0.20 | $0.20 | 8.2K | +0% |
| Gemma 4 E4B ITGoogle | $0.20 | $0.20 | $0.20 | 131K | +0% |
| Ministral 14BMistral AI | $0.20 | $0.20 | $0.20 | 262K | +0% |
| Ministral 3 14BMistral AI | $0.20 | $0.20 | $0.20 | 262K | +0% |
| Mistral-7B-Instruct-v0.3Mistral AI | $0.20 | $0.20 | $0.20 | 65.5K | +0% |
| Agnes 1.5 LiteSapiens AI (Agnes AI) | $0.20 | $0.12 | $0.60 | 256K | +0% |
| GLM 4 9B 0414Z.ai (Zhipu AI) | $0.20 | $0.20 | $0.20 | 32K | +0% |
More from Alibaba (Qwen)
Newest Alibaba (Qwen) models in the catalogue. All Alibaba (Qwen) models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Qwen Image 2.1 Pro | 2026-10-16 | 65.5K | unpriced |
| Qwen 3.8 27B Fimi | 2026-10-05 | 262K | $0.10 via NanoGPT |
| Qwen 3.8 27B Kiwen | 2026-10-05 | 262K | $0.10 via NanoGPT |
| Qwen 3.8 27B Swift | 2026-10-05 | 262K | $0.10 via NanoGPT |
| Qwen 3.8 27B Kimiko | 2026-10-05 | 262K | $0.10 via NanoGPT |
| Qwen 3.8 27B Synthia | 2026-10-05 | 262K | $0.10 via NanoGPT |
| Qwen 3.8 27B Antislop | 2026-10-05 | 262K | $0.10 via NanoGPT |
| Qwen 3.8 27B DarkIdol | 2026-10-05 | 262K | $0.10 via NanoGPT |