Skip to content

Mistral AI · Chat

Mistral Small 24B Instruct

Mistral AI 🇫🇷ChatMistral familyOpen weights. The weights are publicly available in a Hugging Face repo.
From Eurouter's listing:
Mistral Small 24B Instruct is a 24B parameter model with 128K context and multimodal (text + image) inputs, optimized for instruction following and long-document understanding.
llminfo IQ
106.3
Max context
128K
Listings
21

Evidence and sources

🤗 mistralai/Mistral-Small-24B-Instruct-2501llminfo IQ 106.3, ranked among chat models. From 74 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 77.9, 95% interval 67–89. From 3 benchmark families across 3 sources. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedReleased 30 Jan 2025Maker HQ: FR (according to Mistral AI's own website)
Sources: EURouter data, llminfo researchPrimary data from EURouter from llminfo research: release date
Tags from its sources:open-sourceinstruction-tunedvisionlong-contextmultilingual

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 3 of the 7 peers that say either way have open weights.

Trade-offs

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 7 maker's prices; 2 market median prices.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

Function callingStructured outputPrompt caching

Listings

 Mistral AImistral-small-24b-instruct-2501 · 2501Source: GenAI Prices dataNot published by the provider$0.05$0.08——
 OpenRouterInference by DeepInframistralai/mistral-small-24b-instruct-2501 · fp8/flex, 2501 · fp8Source: OpenRouter data docs33K$0.04$0.06490656ms
 Eden AIInference by DeepInfradeepinfra/mistralai/Mistral-Small-24B-Instruct-2501 · 2501Source: Models.dev data33K$0.05$0.08——
 Fastroutermistralai/Mistral-Small-24B-Instruct-2501 · 2501Source: FastRouter data28K$0.05$0.08——
 Flowdotmistralai/Mistral-Small-24B-Instruct-2501 · 2501Source: FlowDot data33K$0.05$0.08——
 Kilomistralai/mistral-small-24b-instruct-2501 · 2501Sources: Kilo AI Gateway data, Models.dev data33K$0.05$0.08——
 Wavespeedmistralai/mistral-small-24b-instruct-2501 · 2501Source: WaveSpeed AI data33K$0.05$0.08——
 DeepInframistralai/Mistral-Small-24B-Instruct-2501 · 2501 · fp8Sources: DeepInfra data, LiteLLM data, Models.dev data33K$0.05$0.08——
 NanoGPTInference by DeepInfraRegions: 🇺🇸 USmistralai/mistral-small-24b-instruct-2501 · 2501 · fp8Source: NanoGPTNot published by the provider$0.0525$0.084—926ms
 Aimlapimistralai/mistral-small-24b-instruct-2501 · 2501Source: Models.dev data33K$0.0529$0.0846——
Show all 18 listings

Showing 10 of 18: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Eurouter, Fireworks AI, Together AI.

3 listings without a price are hidden.

Benchmarks

No benchmark scores yet.

Also known as: deepinfra/mistralai/mistral-small-24b-instruct-2501, fireworks_ai/accounts/fireworks/models/mistral-small-24b-instruct-2501, mistral-small-24b-instruct, mistral-small-24b-instruct-2501, mistralai/mistral-small-24b-instruct-2501, mistralai/mistral-small-24b-instruct-2501:free, together_ai/mistralai/mistral-small-24b-instruct-2501

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works