Qwen3 32B
by Alibaba (Qwen)Chat
Qwen instruction model for multilingual chat, reasoning, and tool use
- Context
- 131K tokens
- Max output
- 16,384 tokens
- Parameters
- 32.8B total
- Released
- 2025-04
- Weights
- Open
- Licence
- apache-2.0
alibaba/qwen3-32b · also seen as qwen.qwen3-32b-v1:0, Qwen/Qwen3-32B, qwen/qwen3-32b-fp8, alibaba/qwen-3-32b, +6 more
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
- 16,384
- Providers
- 25 + 14 gateways, not counted as providers
- Epoch Capabilities Index
- 138.5 ± 2.8 against price
- Direct price range
- $0.08–$0.90 in · $0.23–$2.80 out per 1M tokens · 14 of 25 providers have a comparable price
More details
- Last updated
- 2026-04-16
- Knowledge cutoff
- 2025-04
- Weights link
- Hugging Face · Qwen/Qwen3-32B
- Parameters
- 32.8B total
- Developer country
- China
- Training compute
- 7.1×10²⁴ FLOP
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel tools
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt caching
- 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 $0.08 in / $0.23 out per 1M tokens at OVHcloud AI Endpoints 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 32B |
|---|---|---|---|---|---|
| Llama 3.2 11B Instruct (Inference.net)Inference.net | $0.113 | $0.07 | $0.33 | 128K | +0% |
| Llama 3.2 11B InstructMeta | $0.113 | $0.07 | $0.33 | 128K | +0% |
| DeepSeek V4.1 FlashDeepSeek | $0.113 | $0.075 | $0.30 | 1.05M | −1% cheaper |
| DeepSeek V4.1 Flash 1017DeepSeek | $0.113 | $0.075 | $0.30 | 1M | −1% cheaper |
| gemini 2.0 flash liteGoogle | $0.113 | $0.075 | $0.30 | 1M | −1% cheaper |
| Qwen3 30B A3b fp8Alibaba (Qwen) | $0.115 | $0.08 | $0.29 | 129K | +1% |
| GPT-5.6 LunaOpenAI | $0.112 | $0.06 | $0.37 | 1.05M | −1% cheaper |
| Hy-MT2-30B-A3BTencent | $0.111 | $0.074 | $0.295 | 8.2K | −2% cheaper |
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 |