All times Eastern (ET)Provider pages checked daily at
ProSign inRSS

Ministral 8B

API ID ministral-8b-2410

Ministral 8B was a Mistral model, released October 2024. It had a 128,000-token context window. It took PDF input and supported function calling and structured outputs.

Powerful edge model with extremely high performance/price ratio. Learn more in our [blog post](https://mistral.ai/news/ministraux/)

Mistral's description
Status
Retired
Released
October 2024
Shutdown
Dec 31, 2025

ministral-8b-2410 stopped serving on December 31, 2025. Recommended replacement: ministral-8b-2512.

How to migrate to Ministral 3 8B

Benchmarks

Scores as each source published them
or

No comparison. Pick a model to see the difference on each benchmark.

Arena

ArenaMinistral 8BRankDateSource
Text
By category
  • Math 1213 rank 315
  • Creative writing 1222 rank 313
  • Instruction following 1211 rank 330
  • Hard prompts 1251 rank 324
  • Long prompts 1259 rank 320
  • Multi-turn 1208 rank 326
  • Expert 1238 rank 309
1238 ±9325 of 415
4,781 votes		Oct 13, 2026source
Text: Coding1274 ±19325 of 410
838 votes		Oct 13, 2026source

Rated as ministral-8b-2410. Ratings come from people voting between two anonymous answers; Text is style-controlled, as on arena.ai. Data: Arena (arena.ai), CC BY 4.0.

Epoch AI

BenchmarkMinistral 8BSettingRunSource
GPQA Diamond27.1%Jan 27, 2025source
MATH Level 514.9%Jan 27, 2025source

Run independently by Epoch AI. Data: Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features

Compare models
FeatureValueSinceSource
Structured outputsThe model can be held to a JSON schema you supply, so every reply parses without retries or cleanup.Supportedin place when tracking began (October 6, 2026)source
Function callingAlso called tool use. You describe functions; the model replies with a function name and arguments for your code to run, then uses the result.Supportedin place when tracking began (October 6, 2026)source
Batch APISend many requests as one job that runs in the background, usually finished within 24 hours, at a lower price than live requests.Supportedin place when tracking began (October 6, 2026)source
PDF inputPDF files can go in the prompt directly, without converting them to text first.Supportedin place when tracking began (October 6, 2026)source
Context windowThe most the model can work with in one request, in tokens: your prompt, conversation history and files. A token is about three-quarters of an English word.128,000 tokensin place when tracking began (October 6, 2026)source

Not published by Mistral: Prompt caching, Image input, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Max output tokens.

Price history

USD per 1M tokens, standard tier
$0.000$0.025$0.050$0.075$0.100$0.125Oct 2026In $0.10Out $0.10Oct 5, 2026 to Oct 15, 2026: Input $0.10, Output $0.10
$0.000$0.025$0.050$0.075$0.100$0.125Oct 2026In $0.10Out $0.10Oct 5, 2026 to Oct 15, 2026: Input $0.10, Output $0.10

We started recording this model's prices on Oct 5, 2026. The history grows with each daily check.

Show as a table
FromTypePrice
Oct 5, 2026Input$0.10
Oct 5, 2026Output$0.10

Prices

USD per 1M tokens, every type and band, by tier
TypePrice $/1MIn effect
Standard
input$0.10
output$0.10

Changelog

Changes we detected on Mistral's pages

No changes recorded yet.

Last checked · Sources: Mistral models