Qwen3 8B
Qwen3 8B is a general-purpose chat-tuned model. Available via Qwen. 131,072-token context. Efficient pricing.
Qwen3 8B is a efficient AI model from Qwen. It costs $0.1170 per million input tokens and $0.4550 per million output tokens (blended $0.2184/M), with a 131,072-token context window.
RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.
The last price on OpenRouter's listing; the model left the feed by 3 Nov 2026.
- Solid general chat performance
- Reasonable instruction following
- General chat
- Drafting and rewriting
- Personal productivity
Benchmarks
More from Qwen
See all 22 →Frequently asked questions
How much does Qwen3 8B cost?
Qwen3 8B costs $0.1170 per million input tokens and $0.4550 per million output tokens, for a blended reference rate of $0.2184 per million tokens.
What is Qwen3 8B's context window?
Qwen3 8B supports up to 131,072 tokens of context in a single request.
What is Qwen3 8B best for?
Qwen3 8B is well suited to Solid general chat performance, Reasonable instruction following and General chat.
Who makes Qwen3 8B?
Qwen3 8B is developed and served by Qwen.
