A
Qwen3 8BOPEN
Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue.
Prices update automatically — checked daily against provider list prices.
- $0.2 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 59% of the 203 open-weight models tracked here
- 11 of 53 Alibaba models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Qwen3 8B, measured by Artificial Analysis. Higher is better. Measurement mode: Reasoning.
Models at this level cost $0.3 per 1M tokens (median of 58) — this one costs $0.2.
Cheaper and better on this index: Claude Haiku 5.5 · Claude Haiku 5.5 (batch) · GLM 5.3 Flash (batch) and 38 more
About this model
Qwen3 8B is an open-weight AI model by Alibaba. You can download and self-host it for free; the prices below are hosted-API list prices, tracked daily, for when you prefer convenience over self-hosting.
Frequently asked questions
What is Qwen3 8B?
Qwen3 8B is an AI language model from Alibaba. It is open-weight: you can download it and run it on your own hardware, for free. It scores 7.3 on the Artificial Analysis intelligence index.
Is Qwen3 8B free?
The weights are free and open — you can self-host Qwen3 8B and pay nothing per token. If you prefer a hosted API, list prices are $0.12 per million input tokens and $0.45 per million output tokens.
What is Qwen3 8B good at?
Independent benchmarks from Artificial Analysis give it GPQA 58.9%, MMLU-Pro 74.3%, Humanity's Last Exam 3.9%, Long Context Reasoning 0%, LiveCodeBench 40.6%, SciCode 27.9%, MATH-500 90.4%, AIME 74.7%, AIME 2025 19%, IFBench 33.5%, τ²-Bench 27.8%, τ-Bench Banking 4.7%, Terminal-Bench 2.2%, Terminal-Bench Hard 2.3%. It is particularly used for code generation.
Can I self-host Qwen3 8B?
Yes. Qwen3 8B has open weights, so you can download it and run it on your own GPU or server with tools like Ollama, vLLM or llama.cpp — with no per-token cost.