Qwen
Qwen3 8B
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, coding, and logical inference, and "non-thinking" mode for general conversation. The model is fine-tuned for instruction-following, agent integration, creative writing, and multilingual use across 100+ languages and dialects. It natively supports a 32K token context window and can extend to 131K tokens with YaRN scaling.
- Input / 1M tokens
- $0.050
- Output / 1M tokens
- $0.400
- Context window
- 41K tokens
- Provider
- Qwen
- Cached input / 1M
- $0.050
- Knowledge cutoff
- 2025-03-31
Performance
Median streaming throughput and first-token latency measured by Artificial Analysis.
- Output tokens / sec
- —
- Time to first token
- —