Skip to content

Mistral AI · Chat

Mistral Small

Mistral AI 🇫🇷ChatMistral familyOpen weights. One of its sources says the weights are publicly available.The maker currently plans to deprecate it within the next 180 days (15 Feb 2027). Plans can change.
From Neosantara's listing:
Mistral Small is a fast, cost-effective model for text generation and function calling. Ideal for simple chat and code assistance.
llminfo IQ
107.8
Maker's price
$0.15 blended / 1M
Max context
262K
Listings
49

Evidence and sources

🤗 mistralai/Mistral-Small-4-119B-2603llminfo IQ 107.8, ranked among chat models. From 316 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 78.4, 95% interval 68–89. From 10 benchmark families across 7 sources. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (27.4). Costs more per task than its benchmark results predict. From 20 benchmarks with measured task costs. Plenty of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsChatty (59 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 25,336 output tokens per task at default effort.How the Yap score worksReleased 26 Feb 2024Maker HQ: FR (according to Mistral AI's own website)
All rankings: #16 in Google Trends interest this week #161 on OpenRouter this week #198 on OpenRouter this month #200 on OpenRouter todayAll rankings: #16 in Google Trends interest this week #161 on OpenRouter this week #198 on OpenRouter this month #200 on OpenRouter todaySources: Mistral API data, Models.dev data, LMArena data, LiteLLM data, AI/ML API data, Neosantara Inference data, llminfo researchPrimary data from Mistral API from Models.dev: name, weights availability from LMArena: family, variant from LiteLLM: deprecation date from AI/ML API: primary mode from Neosantara Inference: description from llminfo research: release date
Tags from its sources:instructvisiontoolsreasoning

Advantages and trade-offs

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

Advantages

Open weights available

The weights are public. 4 of the 8 peers that say either way have open weights.

Trade-offs

Deprecation scheduled

The maker plans to deprecate it on 15 Feb 2027, within the next 180 days.

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 6 maker's prices; 4 market median prices.

Input & output

as stated by the model's providers
Text
Images
Files
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction callingStructured outputPrompt cachingWeb searchBatch API

Listings

 Mistral AImistral-small-latest · latestSources: GenAI Prices data, LiteLLM data, Mistral API data, Models.dev data262K$0.10cache read $0.015$0.30
 Flowdotmistral-small-latest · latestSource: FlowDot data32K$0.05$0.08
 Microsoft Azureazure_ai/mistral-small-2503 · 2503Sources: LiteLLM data, Models.dev data128K$0.10$0.30
 Googlevertex_ai/mistral-small-2503@001 · 001, 2503Source: LiteLLM data32K$0.10$0.30
 Llmgatewaymistral-small-2506 · 2506Source: LLMGateway data128K$0.10$0.30
 Llmgateway Providersmistral/mistral-small-2506 · 2506Source: Models.dev data128K$0.10$0.30
 Vercel AI Gatewayvercel_ai_gateway/mistral/mistral-smallSource: LiteLLM data32K$0.10$0.30
 Watsonxwatsonx/mistralai/mistral-small-2503 · 2503Source: LiteLLM data32K$0.10$0.30
 Cortecs AImistral-small-2503 · 2503Sources: Cortecs EU Router data, Models.dev data128K
 RequestyInference by Mistral AImistral/mistral-small-2503 · 2503Source: Requesty data33K$0.11$0.33
Show all 44 listings

Showing 10 of 44: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Aimlapi, Eden AI, Empiriolabs, Eurouter, Kilo, Lowrouter, Merge Gateway, Neosantara, Nous Portal, OpenRouter, Opper, Prime, Sap AI Core, Vercel.

5 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Knowledge

HELM60 related benchmarks · 60 results
Show 54 more resultsHide 54 results
MMLU-ProSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Coding

General

OCR

OmniDocBenchSource: Nanonets IDP data

Agentic

GAIA4 results
Source: GAIA Leaderboard data · May 2026
Difficulty level
Difficulty not reported

Long context

Math

AIME 2025Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
ValsSource: Vals AI

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond4 results
Source: OpenRouter benchmark exports · Sep 2026
mistral-small-2603 · 90-day results
Across 2 providers lowest 75.3% median 75.4% highest 75.6%OpenRouter's automatic routing 75.8%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • OpenRouter's automatic routing
  • Venice
  • Mistral

Human preference

Arena HardSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Multilingual

Reasoning

COLLIESource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Vision

MMMU-ProSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Instruction following

IFBenchSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Safety

PhareSource: Phare

Factuality

Other

Horangi36 related benchmarks · 36 results
Nejumi 428 related benchmarks · 28 results
ValsSource: Vals AI

Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence) · BullshitBench by Peter Gostev, MIT (licence) · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · Galileo Agent Leaderboard, Apache-2.0 (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · Stanford HELM (Stanford CRFM), Apache-2.0 (licence) · Horangi 4, Weights & Biases Korea; public publisher-selected numeric evaluation results · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Phare (Giskard), CC BY 4.0 (licence)

Also known as: azure_ai/mistral-small-2503, empiriolabs/mistral-small-4, mistral-small-2503, mistral-small-2506, mistral-small-2603, mistral-small-2603@eu, mistral-small-4, mistral-small-latest, mistral/mistral-small, mistral/mistral-small-2503, mistral/mistral-small-2506, mistral/mistral-small-2603, mistral/mistral-small-2603@eu, mistral/mistral-small-latest, mistral/mistral-small-latest@eu, mistralai/mistral-small, mistralai/mistral-small-2603, vercel_ai_gateway/mistral/mistral-small, vertex_ai/mistral-small-2503, vertex_ai/mistral-small-2503@001, watsonx/mistralai/mistral-small-2503

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