Model Library
AlibabaReleased April 28, 2025Qwen3 4B
Alibaba · Released April 28, 2025
Intelligence score
8
At a glance
- Intelligence
- 8
- Speed
- —
- Latency
- —
- Input price
- $0.11per 1M tokens
- Output price
- $1.26per 1M tokens
- Context window
- 32Ktokens
- Parameters
- 4.02billions
Summary
Comparison summary
Qwen3 4B (Reasoning) scores 8 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 4). Qwen3 4B (Reasoning) costs $0.11 per 1M input tokens (very competitive, median: $0.11) and $1.26 per 1M output tokens (somewhat higher than average, median: $0.42), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3 4B |
|---|---|
| Provider | Alibaba |
| Release date | April 28, 2025 |
| Intelligence score | 8 |
| Speed | — |
| Latency (TTFT) | — |
| Input price | $0.11 / 1M tokens |
| Output price | $1.26 / 1M tokens |
| Context window | 32,000 tokens |
| Parameters | 4.02B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-4b-instruct-reasoning |
Pricing
Token prices
Price per 1M tokens
Qwen3 4B, as listed in the catalog record
- Input$0.11
- Output$1.26
| Token type | Price per 1M |
|---|---|
| Input | $0.11 |
| Output | $1.26 |
Model Intelligence legacy profile: qwen3-4b-instruct-reasoning
FAQ · 17
Frequently asked questions
Qwen3 4B (Reasoning) was released on April 28, 2025.
Qwen3 4B (Reasoning) was created by Alibaba.
Qwen3 4B (Reasoning) scores 8 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight models of similar size (median: 4).
Qwen3 4B (Reasoning) costs $0.11 per 1M input tokens (very competitive, median: $0.11) and $1.26 per 1M output tokens (somewhat higher than average, median: $0.42), based on Alibaba's API.
Qwen3 4B (Reasoning) costs $0.11 per 1M input tokens and $1.26 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.23 per 1M tokens. Pricing may vary by provider.
Yes, Qwen3 4B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Qwen3 4B (Reasoning) supports text input.
Qwen3 4B (Reasoning) supports text output.
No, Qwen3 4B (Reasoning) does not support image input. It can only process text.
No, Qwen3 4B (Reasoning) is not multimodal. It only supports text input.
Qwen3 4B (Reasoning) has a context window of 32k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Qwen3 4B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 4B (Reasoning) has 4.02 billion parameters.
Qwen3 4B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Qwen3 4B (Reasoning) achieves a score of 8 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Qwen3 4B (Reasoning) is available via API through 1 provider.
Qwen3 4B (Reasoning) is available through 1 API provider.