Model Library
AlibabaReleased April 28, 2025Qwen3 32B
Alibaba · Released April 28, 2025
Intelligence score
9
At a glance
- Intelligence
- 9
- Speed
- 92.5tokens/sec
- Latency
- 2.60stime to first token
- Input price
- $0.70per 1M tokens
- Output price
- $2.80per 1M tokens
- Context window
- 33Ktokens
- Parameters
- 32.8billions
Summary
Comparison summary
Qwen3 32B (Non-reasoning) scores 9 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6). Qwen3 32B (Non-reasoning) generates output at 92.5 tokens per second (based on Alibaba's API), which is below average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s). Qwen3 32B (Non-reasoning) costs $0.70 per 1M input tokens (at the higher end, median: $0.15) and $2.80 per 1M output tokens (at the higher end, median: $0.32), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3 32B |
|---|---|
| Provider | Alibaba |
| Release date | April 28, 2025 |
| Intelligence score | 9 |
| Speed | 92.5 tokens/sec |
| Latency (TTFT) | 2.60s |
| Input price | $0.70 / 1M tokens |
| Output price | $2.80 / 1M tokens |
| Context window | 33,000 tokens |
| Parameters | 32.8B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-32b-instruct |
Pricing
Token prices
Price per 1M tokens
Qwen3 32B, as listed in the catalog record
- Input$0.70
- Output$2.80
| Token type | Price per 1M |
|---|---|
| Input | $0.70 |
| Output | $2.80 |
Model Intelligence legacy profile: qwen3-32b-instruct
FAQ · 19
Frequently asked questions
Qwen3 32B (Non-reasoning) was released on April 28, 2025.
Qwen3 32B (Non-reasoning) was created by Alibaba.
Qwen3 32B (Non-reasoning) scores 9 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other open weight non-reasoning models of similar size (median: 6).
Qwen3 32B (Non-reasoning) generates output at 92.5 tokens per second (based on Alibaba's API), which is below average compared to other open weight non-reasoning models of similar size (median: 101.8 t/s).
Qwen3 32B (Non-reasoning) has a time to first token (TTFT) of 2.60s (based on Alibaba's API), which is at the higher end compared to other open weight non-reasoning models of similar size (median: 1.54s).
Qwen3 32B (Non-reasoning) costs $0.70 per 1M input tokens (at the higher end, median: $0.15) and $2.80 per 1M output tokens (at the higher end, median: $0.32), based on Alibaba's API.
Qwen3 32B (Non-reasoning) costs $0.70 per 1M input tokens and $2.80 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.91 per 1M tokens. Pricing may vary by provider.
No, Qwen3 32B (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Qwen3 32B (Non-reasoning) supports text input.
Qwen3 32B (Non-reasoning) supports text output.
No, Qwen3 32B (Non-reasoning) does not support image input. It can only process text.
No, Qwen3 32B (Non-reasoning) is not multimodal. It only supports text input.
Qwen3 32B (Non-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 (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 32B (Non-reasoning) has 32.8 billion parameters.
Qwen3 32B (Non-reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Qwen3 32B (Non-reasoning) achieves a score of 9 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3 32B (Non-reasoning) is available via API through 7 providers.
Qwen3 32B (Non-reasoning) is available through 7 API providers.