mistralai Open weights Vision

Ministral 3 8B 2512 pricing & benchmarks

Released Dec 2, 2025 · served by 2 providers

Input / 1M tokens$0.150
Output / 1M tokens$0.150
Context window262K
Cached input$0.015
Intelligence index9.0
Coding index9.7
Agentic index1.2
1M in + 300K out$0.20

What Ministral 3 8B 2512 is

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

Providers and prices for Ministral 3 8B 2512

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Mistralcheapest $0.150 $0.150 262K 99.2%
NextBit $0.300 $0.300 262K fp8 99.4%

Ministral 3 8B 2512 benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

CategoryArenaRankEloWin rate
3d models #83 1089 46.2%
codecategories models #88 1084 42.9%
website models #90 1090 42.9%
gamedev models #93 1047 38.7%

Cheaper models in the same class

Models scoring within 4 points of Ministral 3 8B 2512 on the Intelligence Index, but with a lower output price.

FAQ

How much does the Ministral 3 8B 2512 API cost?

$0.150 per 1M input tokens and $0.150 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.20.

Is Ministral 3 8B 2512 free?

No. It is a paid model starting at $0.150 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Ministral 3 8B 2512?

Mistral at $0.150 input / $0.150 output per 1M tokens.

Can I self-host Ministral 3 8B 2512?

Yes — weights are published as mistralai/Ministral-3-8B-Instruct-2512 on Hugging Face, so you can run it on your own hardware.