Qwen: Qwen3 8B
🇨🇳 通義千問（阿里） · Qwen3 8B
Input Price $0.050 per million tokens NT$1.6
Output Price $0.400 per million tokens NT$12.8
Context Window 131K tokens Output limit: 8K
OpenRouter Route Price Please verify with official pricing pages
| Dimension | Unit | Price (USD) |
|---|---|---|
| Input | per 1M tokens | $0.050 |
| Output | per 1M tokens | $0.400 |
| Cached Input | per 1M tokens | $0.050 |
- Provider
- 通義千問（阿里） (Qwen (Alibaba))
- Model Family
- Qwen3 8B
- Version String
- qwen/qwen3-8b
- Status
- active
- Modality
- text
- Context Window
- 131,072 tokens
- Output Limit
- 8,192 tokens
Index Metrics
Cross-domain capability indexes evaluated by Artificial Analysis — Artificial Analysis
Agentic Index 13 F Measured: 2026-05-27
Coding Index 9 F Measured: 2026-05-27
Intelligence Index 13 F Measured: 2026-05-27
Benchmark Scores
Data source: Artificial Analysis
GPQA Diamond 58.9% C Measured: 2026-05-27
HLE 4.2% D Measured: 2026-05-27
HLE 4.2% D Measured: 2026-05-27
IFBench 33.5% D Measured: 2026-05-27
Non-Hallucination 10.7% Measured: 2026-05-27
Omniscience Accuracy 12.8% Measured: 2026-05-27
SciCode 22.6% C Measured: 2026-05-27
Tau2 27.8% Measured: 2026-05-27
TerminalBench 2.3% Measured: 2026-05-27
Performance Metrics
Real-world benchmarks, updated every 72 hours by Artificial Analysis — Artificial Analysis
First Token Latency 3.8s Measured: 2026-05-27
Output Speed 39 t/s Measured: 2026-05-27
Response Time 68.4s Measured: 2026-05-27
90-Day Price Trend
Input / Output price (USD per 1M tokens)
Past 90 days of records; every price change is shown here
| Date | Dimension | Price (USD) | Source |
|---|---|---|---|
| 2026-05-27 | Cached Input | $0.050 | openrouter |
| 2026-05-27 | Output | $0.400 | openrouter |
| 2026-05-27 | Input | $0.050 | openrouter |
| 2026-05-26 | Cached Input | $0.050 | openrouter |
| 2026-05-26 | Output | $0.400 | openrouter |
| 2026-05-26 | Input | $0.050 | openrouter |
| 2026-05-25 | Cached Input | $0.050 | openrouter |
| 2026-05-25 | Output | $0.400 | openrouter |
| 2026-05-25 | Input | $0.050 | openrouter |
| 2026-05-24 | Cached Input | $0.050 | openrouter |
| 2026-05-24 | Output | $0.400 | openrouter |
| 2026-05-24 | Input | $0.050 | openrouter |
| 2026-05-23 | Cached Input | $0.050 | openrouter |
| 2026-05-23 | Output | $0.400 | openrouter |
| 2026-05-23 | Input | $0.050 | openrouter |
| 2026-05-22 | Cached Input | $0.050 | openrouter |
| 2026-05-22 | Output | $0.400 | openrouter |
| 2026-05-22 | Input | $0.050 | openrouter |
| 2026-05-22 | Cached Input | $0.050 | openrouter |
| 2026-05-22 | Output | $0.400 | openrouter |
| 2026-05-22 | Input | $0.050 | openrouter |
| 2026-05-21 | Cached Input | $0.050 | openrouter |
| 2026-05-21 | Output | $0.400 | openrouter |
| 2026-05-21 | Input | $0.050 | openrouter |
| 2026-05-20 | Cached Input | $0.050 | openrouter |
| 2026-05-20 | Output | $0.400 | openrouter |
| 2026-05-20 | Input | $0.050 | openrouter |
| 2026-05-19 | Cached Input | $0.050 | openrouter |
| 2026-05-19 | Output | $0.400 | openrouter |
| 2026-05-19 | Input | $0.050 | openrouter |
| 2026-05-18 | Cached Input | $0.050 | openrouter |
| 2026-05-18 | Output | $0.400 | openrouter |
| 2026-05-18 | Input | $0.050 | openrouter |
| 2026-05-17 | Cached Input | $0.050 | openrouter |
| 2026-05-17 | Output | $0.400 | openrouter |
| 2026-05-17 | Input | $0.050 | openrouter |
| 2026-05-16 | Cached Input | $0.050 | openrouter |
| 2026-05-16 | Output | $0.400 | openrouter |
| 2026-05-16 | Input | $0.050 | openrouter |
| 2026-05-16 | Cached Input | $0.050 | openrouter |
| 2026-05-16 | Output | $0.400 | openrouter |
| 2026-05-16 | Input | $0.050 | openrouter |
| 2026-05-16 | Cached Input | $0.050 | openrouter |
| 2026-05-16 | Output | $0.400 | openrouter |
| 2026-05-16 | Input | $0.050 | openrouter |
| 2026-05-16 | Cached Input | $0.050 | openrouter |
| 2026-05-16 | Output | $0.400 | openrouter |
| 2026-05-16 | Input | $0.050 | openrouter |
| 2026-05-15 | Cached Input | $0.050 | openrouter |
| 2026-05-15 | Output | $0.400 | openrouter |
Description
Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...
Key Insights
Key data points from this page for quick reference and citation.
- Qwen: Qwen3 8B Input price: $0.05/M tokens
- Qwen: Qwen3 8B Output price: $0.4/M tokens
- Context window: 131,072 tokens
- Provider: Qwen (Alibaba)
- Model family: Qwen3 8B
- Modalities: text
- Data source: OpenRouter, updated daily