Model Library
AlibabaReleased April 28, 2025Qwen3 8B
Alibaba · Released April 28, 2025
Intelligence score
8
At a glance
- Intelligence
- 8
- Speed
- 37.0tokens/sec
- Latency
- 3.90stime to first token
- Input price
- $0.18per 1M tokens
- Output price
- $2.10per 1M tokens
- Context window
- 130Ktokens
- Parameters
- 8.19billions
Summary
Comparison summary
Qwen3 8B (Reasoning) scores 8 on the Artificial Analysis Intelligence Index, placing it below average among other open weight models of similar size (median: 9). Qwen3 8B (Reasoning) generates output at 37.0 tokens per second (based on Alibaba's API), which is at the lower end compared to other open weight models of similar size (median: 101.0 t/s). Qwen3 8B (Reasoning) costs $0.18 per 1M input tokens (better than average, median: $0.18) and $2.10 per 1M output tokens (at the higher end, median: $0.40), based on Alibaba's API.
Specifications
Technical specifications
| Model name | Qwen3 8B |
|---|---|
| Provider | Alibaba |
| Release date | April 28, 2025 |
| Intelligence score | 8 |
| Speed | 37.0 tokens/sec |
| Latency (TTFT) | 3.90s |
| Input price | $0.18 / 1M tokens |
| Output price | $2.10 / 1M tokens |
| Context window | 130,000 tokens |
| Parameters | 8.19B |
| Reasoning | Yes |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: qwen3-8b-instruct-reasoning |
Pricing
Token prices
Price per 1M tokens
Qwen3 8B, as listed in the catalog record
- Input$0.18
- Output$2.10
| Token type | Price per 1M |
|---|---|
| Input | $0.18 |
| Output | $2.10 |
Model Intelligence legacy profile: qwen3-8b-instruct-reasoning
FAQ · 19
Frequently asked questions
Qwen3 8B (Reasoning) was released on April 28, 2025.
Qwen3 8B (Reasoning) was created by Alibaba.
Qwen3 8B (Reasoning) scores 8 on the Artificial Analysis Intelligence Index, placing it below average among other open weight models of similar size (median: 9).
Qwen3 8B (Reasoning) generates output at 37.0 tokens per second (based on Alibaba's API), which is at the lower end compared to other open weight models of similar size (median: 101.0 t/s).
Qwen3 8B (Reasoning) has a time to first token (TTFT) of 3.90s (based on Alibaba's API), which is at the higher end compared to other open weight models of similar size (median: 2.09s).
Qwen3 8B (Reasoning) costs $0.18 per 1M input tokens (better than average, median: $0.18) and $2.10 per 1M output tokens (at the higher end, median: $0.40), based on Alibaba's API.
Qwen3 8B (Reasoning) costs $0.18 per 1M input tokens and $2.10 per 1M output tokens (based on Alibaba's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.37 per 1M tokens. Pricing may vary by provider.
Yes, Qwen3 8B (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
Qwen3 8B (Reasoning) supports text input.
Qwen3 8B (Reasoning) supports text output.
No, Qwen3 8B (Reasoning) does not support image input. It can only process text.
No, Qwen3 8B (Reasoning) is not multimodal. It only supports text input.
Qwen3 8B (Reasoning) has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Qwen3 8B (Reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Qwen3 8B (Reasoning) has 8.19 billion parameters.
Qwen3 8B (Reasoning) is released under the Apache 2.0 license. This license allows commercial use.
Qwen3 8B (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 8B (Reasoning) is available via API through 1 provider.
Qwen3 8B (Reasoning) is available through 1 API provider.