M
Ministral 3 8B 2512 (batch)OPEN
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.
Prices update automatically — checked daily against provider list prices.
- $0.08 per 1M tokens, assuming 3 input for 1 output the convention used by Artificial Analysis
- cheaper than 82% of the 205 open-weight models tracked here
- 3 of 25 Mistral AI models tracked here, from cheapest
Benchmarks & performance
Independent benchmark scores for Ministral 3 8B 2512 (batch), measured by Artificial Analysis. Higher is better.
For the same budget, Ministral 3 8B 2512 (batch) delivers 5.1 times more capability. Open weights also mean you can self-host it and pay nothing per token.
Models at this level cost $0.2 per 1M tokens (median of 37) — this one costs $0.08.
Cheaper and better on this index: DeepSeek V4 Flash 0423 · Ling 3.0 Flash VL · Ling 3.0 Flash Fin and 9 more
About this model
Ministral 3 8B 2512 (batch) is an open-weight AI model by Mistral AI. 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 Ministral 3 8B 2512 (batch)?
Ministral 3 8B 2512 (batch) is an AI language model from Mistral AI. It is open-weight: you can download it and run it on your own hardware, for free. It scores 5.5 on the Artificial Analysis intelligence index.
Is Ministral 3 8B 2512 (batch) free?
The weights are free and open — you can self-host Ministral 3 8B 2512 (batch) and pay nothing per token. If you prefer a hosted API, list prices are $0.08 per million input tokens and $0.08 per million output tokens.
What is Ministral 3 8B 2512 (batch) good at?
Independent benchmarks from Artificial Analysis give it GPQA 47.1%, MMLU-Pro 64.2%, Humanity's Last Exam 4.3%, Long Context Reasoning 25.7%, LiveCodeBench 30.3%, SciCode 20.7%, AIME 2025 31.7%, IFBench 29.1%, τ²-Bench 26.6%, τ-Bench Banking 3.7%, Terminal-Bench 4.1%, Terminal-Bench Hard 4.5%. It is particularly used for code generation.
How fast is Ministral 3 8B 2512 (batch)?
It generates about 109.3 tokens per second, with a median 0.47s delay before the first token. Measured independently by Artificial Analysis.
Can I self-host Ministral 3 8B 2512 (batch)?
Yes. Ministral 3 8B 2512 (batch) 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.