token.app › Mistral AI › Ministral 3 3B 2512

Ministral 3 3B 2512 pricing & benchmarks

Ministral 3 3B 2512 is available from Mistral AI at $0.100 per million input tokens and $0.100 per million output tokens ($0.100 blended at 3:1). It accepts up to 131,072 tokens of context. The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

Pricing
Per million tokens · OpenRouter
Input$0.100
Output$0.100
Blended (3:1)$0.100
Specification
mistralai/ministral-3b-2512
Context window131K
Max output—
ReleasedDec 2025
LicenceOpen weights
Modalitiesin:text, in:image, out:text
No independently-run benchmark scores are published for Ministral 3 3B 2512 yet. We show nothing rather than reprinting an unverified figure.
Compare Ministral 3 3B 2512
Ministral 3 3B 2512 vs Qwen3.8 Max Ministral 3 3B 2512 vs DeepSeek V4 Flash 0731 Ministral 3 3B 2512 vs Claude Opus 5 Ministral 3 3B 2512 vs Gemini 3.6 Flash Ministral 3 3B 2512 vs Kimi K3 Ministral 3 3B 2512 vs GPT-5.6 Luna Ministral 3 3B 2512 vs GPT-5.6 Terra Ministral 3 3B 2512 vs GPT-5.6 Sol
FAQ
How much does Ministral 3 3B 2512 cost?
Ministral 3 3B 2512 costs $0.100 per million input tokens and $0.100 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $0.100 per million tokens.
What is Ministral 3 3B 2512's context window?
Ministral 3 3B 2512 accepts up to 131,072 tokens of context.