Model Library
AlibabaReleased April 28, 2025Qwen3 32B
Alibaba · Released April 28, 2025
Intelligence score
12
At a glance
- Intelligence
- 12
- Speed
- 93.2tokens/sec
- Latency
- 2.62stime to first token
- Input price
- $0.70per 1M tokens
- Output price
- $8.40per 1M tokens
- Context window
- 33Ktokens
- Parameters
- 32.8billions
Summary
Comparison summary
Qwen3 32B (Reasoning) scores 12 on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 9). Qwen3 32B (Reasoning) generates output at 93.2 tokens per second (based on Alibaba's API), which is below average compared to other open weight models of similar size (median: 101.0 t/s). Qwen3 32B (Reasoning) costs $0.70 per 1M input tokens (at the higher end, median: $0.18) and $8.40 per 1M output tokens (at the higher end, median: $0.40), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3 32B |
|---|---|
| Provider | Alibaba |
| Release date | April 28, 2025 |
| Intelligence score | 12 |
| Speed | 93.2 tokens/sec |
| Latency (TTFT) | 2.62s |
| Input price | $0.70 / 1M tokens |
| Output price | $8.40 / 1M tokens |
| Context window | 33,000 tokens |
| Parameters | 32.8B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-32b-instruct-reasoning |
Pricing
Token prices
Price per 1M tokens
Qwen3 32B, as listed in the catalog record
- Input$0.70
- Output$8.40
| Token type | Price per 1M |
|---|---|
| Input | $0.70 |
| Output | $8.40 |
Model Intelligence legacy profile: qwen3-32b-instruct-reasoning
FAQ · 19
Frequently asked questions
Qwen3 32B (Reasoning) was released on April 28, 2025.
Qwen3 32B (Reasoning) was created by Alibaba.
Qwen3 32B (Reasoning) scores 12 on the Artificial Analysis Intelligence Index, placing it above average among other open weight models of similar size (median: 9).
Qwen3 32B (Reasoning) generates output at 93.2 tokens per second (based on Alibaba's API), which is below average compared to other open weight models of similar size (median: 101.0 t/s).
Qwen3 32B (Reasoning) has a time to first token (TTFT) of 2.62s (based on Alibaba's API), which is at the higher end compared to other open weight models of similar size (median: 2.09s).
Qwen3 32B (Reasoning) costs $0.70 per 1M input tokens (at the higher end, median: $0.18) and $8.40 per 1M output tokens (at the higher end, median: $0.40), based on Alibaba's API.
Qwen3 32B (Reasoning) costs $0.70 per 1M input tokens and $8.40 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $1.47 per 1M tokens. Pricing may vary by provider.
Yes, Qwen3 32B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Qwen3 32B (Reasoning) supports text input.
Qwen3 32B (Reasoning) supports text output.
No, Qwen3 32B (Reasoning) does not support image input. It can only process text.
No, Qwen3 32B (Reasoning) is not multimodal. It only supports text input.
Qwen3 32B (Reasoning) has a context window of 33k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Qwen3 32B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 32B (Reasoning) has 32.8 billion parameters.
Qwen3 32B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Qwen3 32B (Reasoning) achieves a score of 12 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3 32B (Reasoning) is available via API through 6 providers.
Qwen3 32B (Reasoning) is available through 6 API providers.