BenchLeader

Ministral 3 8B 2512

Ministral 3 8B 2512 is a Mistral AI open-weights model. It is not yet ranked: no independent benchmark results so far, only pricing and metadata. At $0.150 per million tokens blended it is among the cheapest fifth of ranked models. Output speed of 38 tokens per second puts it in the slowest quarter, with a first token in 0.3 s.

Blended price
$0.150/M
$0.150 in · $0.150 out
Output speed
38 tok/s
OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
First answer
0.34 s
Context
262k
Released
date not published by our sources

Versions

Mistral AI has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

ModelReleasedIndexRank
Ministral 3 8B2 Dec 202536.6#482
Ministral 3 8B 2512this page

No independent quality benchmark results yet — only pricing and metadata.

Where to run it

Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.

ProviderSpeedFirst tokenInput $/MOutput $/MContextQuantisation
Mistral50 tok/s0.31 s$0.150$0.150262k
Mistral (ZDR)7 tok/s0.38 s$0.150$0.150262k

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.00018.3 s
Summarise a 30-page report12,000 / 600$0.001916.3 s
Code edit6,000 / 1,500$0.001140.3 s
Agentic coding session60,000 / 4,000$0.00961.8 min
Structured extraction2,000 / 200$0.00035.7 s

See also

Data as of 13 Sept 2026. Compare with another model.

Cite as: BenchLeader, “Ministral 3 8B 2512: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/ministral-8b-2512, data as of 13 Sept 2026.