Join our Newsletter — 33% off our NHI Course
Home› Guides› Mistral Small 4: Specs, Pricing, Context Window and…
Guide AI Platforms

Mistral Small 4: Specs, Pricing, Context Window and Availability Facts

PDF for newsletter subscribers · free to read online

← All guides
By NHI Mgmt Group, edited by Lalit Choda Updated 15 November 2026 14 min read
On this page

Mistral Small 4 is an open-weight, multimodal Mixture-of-Experts language model from Mistral AI, released on 16 March 2026 under the Apache 2.0 licence, that combines instruct, reasoning and coding in one model. This profile collects the published facts about it in one place: API identifier, context window, parameter counts, prices, reasoning modes, hardware guidance, where it can be run, provider-reported benchmarks, data handling and deprecation status. It is written for developers, architects, buyers and governance teams who want checked numbers rather than launch coverage. Every fact comes from Mistral AI's own documentation, model card, launch post, Hugging Face model card, pricing page or help centre, listed under Standards and references. Where Mistral AI publishes nothing on a point, the page says so.

Last checked: 2026-11-15.

This is an independent reference page from NHI Mgmt Group based on public provider documentation; it is not sponsored or endorsed by any provider. It uses Mistral AI's public documentation as of November 2026. Model details change, so confirm against Mistral AI's current documentation.

Key takeaways

  • Released 16 March 2026. The Mistral changelog and launch post record Mistral Small 4 (API ID mistral-small-2603, version 26.03) on that date, and the model card lists it as GA.
  • 256k context, 119B total and 6.5B active parameters. The model card gives 119B total with 6.5B active; the Hugging Face card describes 128 experts with 4 active per token, and text and image input with text output.
  • $0.15 input and $0.60 output per million tokens. The launch post labels these figures; the model card lists the same two numbers without labels. Batch processing is 50% off according to the pricing page.
  • Apache 2.0 open weights. Weights are on Hugging Face as mistralai/Mistral-Small-4-119B-2603 in BF16 and FP8, with an NVFP4 checkpoint and an EAGLE speculative decoding head.
  • One model replaces several. Mistral's models overview names Small 4 as the replacement for Mistral Small 3.0 to 3.2, Magistral Small 1.0 to 1.2 and Devstral Small 1.1; Small 4 itself has no deprecation date.

What is Mistral Small 4?

Mistral Small 4 is the current model in Mistral AI's Small line. The model card describes it as "Our powerful hybrid model unifying instruct, reasoning, and coding capabilities in a single model." The launch post says it is the first Mistral model to combine the capabilities of Magistral (reasoning), Pixtral (multimodal) and Devstral (agentic coding), so that "one model now delivers all three."

It accepts text and images and returns text. A per-request reasoning_effort parameter switches between fast replies in the style of Mistral Small 3.2 (none) and step-by-step reasoning similar in verbosity to earlier Magistral models (high). Because it is a Mixture-of-Experts model, only a fraction of its parameters are active per token; see Mixture of Experts Explained. For the full Mistral line-up, see Mistral AI Models.

Key facts at a glance

As of 2026-11-15. Sources: Mistral Small 4 model card (docs.mistral.ai), Hugging Face model card, Mistral changelog and launch post.

FieldValueSource
ProviderMistral AIModel card
API IDmistral-small-2603 (the card shows one further alias without naming it)Model card; launch post
Version26.03Model card; models overview
Release date2026-03-16Model card; changelog; launch post
StatusGA, currentModel card; models overview
Context window256k tokensModel card; changelog; launch post
Max outputNot stated by Mistral AI on the pages checked (2026-11-15)Model card
Knowledge cutoffNot stated by Mistral AI on the pages checked (2026-11-15)Model card; Hugging Face card
Input modalitiesText, imageLaunch post; Hugging Face card
Output modalitiesTextLaunch post; Hugging Face card
Reasoning effortnone, highLaunch post; Hugging Face card
Open weightsYes, mistralai/Mistral-Small-4-119B-2603 (BF16 and FP8)Hugging Face card
LicenceApache 2.0Model card; launch post
Parameters119B total, 6.5B active (model card); the launch post gives 6B active, 8B including embedding and output layersModel card; launch post
LanguagesDozens, including English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean and ArabicHugging Face card

Release and version history

As of 2026-11-15. Dates from the Mistral changelog, models overview and model card.

DateEventSource
2024-02-26mistral-small-latest first introduced, then pointing to mistral-small-2402 (Small 1.0)Changelog
2025-11-30Mistral Small 3.0 and 3.1, and Magistral Small 1.0 and 1.1, retired, with Small 4 named as replacementModels overview
2026-03-16Mistral Small 4 (mistral-small-2603) released, multimodal with a 256k context windowChangelog; launch post
2026-04-30Mistral Small 3.2 and Magistral Small 1.2 deprecated, replacement Small 4Models overview
2026-05-31Devstral Small 1.1 retired, replacement Small 4Models overview
2026-07-31Mistral Small 3.2 and Magistral Small 1.2 retiredModels overview

Mistral publishes one version of Small 4, 26.03. The replacement mappings show how Mistral folded its separate reasoning and small coding lines into this single model. See LLM Naming and Versioning Explained for how the year.month version labels work.

How much does Mistral Small 4 cost?

As of 2026-11-15. USD per million tokens. Sources: Mistral Small 4 model card, launch post and mistral.ai/pricing.

ItemPriceNotesSource
Input$0.15Labelled as input in the launch post; the model card lists $0.15 without a label and offers a EUR viewLaunch post; model card
Output$0.60Labelled as output in the launch post; reasoning tokens are generated as outputLaunch post; model card
Cached inputNot stated by Mistral AI on the pages checked (2026-11-15)Pricing page says cached input reduces input cost by up to 90% in generalmistral.ai/pricing
Batch50% reductionGeneral statement on the pricing page, not model specificmistral.ai/pricing
Self-hosted weightsNo per-token fee from Mistral; own compute costApache 2.0 permits commercial useHugging Face card; launch post

Worked example at list rates: a request with 100,000 input tokens and 10,000 output tokens costs $0.015 for input plus $0.006 for output, $0.021 in total. With reasoning_effort set to high, output includes the reasoning trace, so measure tokens per task in both modes. See Model Pricing Explained and How to set spend limits on LLM API keys.

Context window and output limits

The context window is 256k tokens on the model card, the changelog and the launch post. Mistral's published vLLM example sets max-model-len to 262,144 tokens, which matches 256k. Mistral does not publish a separate maximum output figure on the pages checked.

LimitValueNotesSource
Context window256k tokens262,144 in the vLLM exampleModel card; Hugging Face card
Max outputNot stated by Mistral AI on the pages checked (2026-11-15)NoneModel card
API rate limitsNot stated by Mistral AI on the pages checked (2026-11-15)Set per workspace in Mistral StudioModel card
Minimum self-hosting hardware4x NVIDIA HGX H100, 2x HGX H200 or 1x DGX B200As stated by MistralLaunch post
Recommended self-hosting hardware4x HGX H100, 4x HGX H200 or 2x DGX B200As stated by MistralLaunch post

Modalities and tools

Small 4 takes text and images and returns text. The launch post tags it as text-to-text, agentic, multimodal and lightweight.

  • API features listed on the model card: chat completions, function calling, agents and conversations, built-in tools, structured outputs, predicted outputs, document Q&A, prefix and batching (/v1/batch).
  • Reasoning effort: none (fast replies, matching the chat style of Mistral Small 3.2) or high (step-by-step reasoning). Mistral recommends high for complex prompts.
  • Recommended sampling: temperature 0.7 with reasoning_effort high; between 0.0 and 0.7 with none, depending on the task (Hugging Face card).
  • Tool use: native function calling and JSON output.
  • Self-hosting stacks named by Mistral: vLLM (recommended), SGLang, llama.cpp, LM Studio and Transformers; fine-tuning through Axolotl; an EAGLE head for speculative decoding and an NVFP4 checkpoint for 4-bit serving.
  • Efficiency claims: Mistral reports a 40% reduction in end-to-end completion time in a latency-optimised setup and 3x more requests per second in a throughput-optimised setup, both versus Mistral Small 3.

Built-in tools and agents give the model reach into other systems. Treat each tool as a credentialed integration with a least-privilege scope. See the Open-Weight Model Security Guide for self-hosted deployments.

Where is Mistral Small 4 available?

As of 2026-11-15. Channels as named in the launch post, the model card and the Hugging Face card.

ChannelDetailsSource
Mistral API and AI Studiomistral-small-2603Model card; launch post
Hugging Face weightsmistralai/Mistral-Small-4-119B-2603, plus NVFP4 and EAGLE repositoriesHugging Face card
NVIDIAFree prototyping on build.nvidia.com, day-0 NVIDIA NIM for production, NVIDIA NeMo for customisationLaunch post
Le ChatNot stated by Mistral AI on the pages checked (2026-11-15)Launch post
Amazon Bedrock, Google Vertex AI, Microsoft FoundryNot stated by Mistral AI on the pages checked (2026-11-15)Launch post

Access restrictions

Small 4 is not a restricted-access model. It is GA on the Mistral API and its weights are public on Hugging Face under Apache 2.0, which permits commercial and non-commercial use. The Hugging Face card adds that the model must not be used to infringe third-party rights. Mistral states no Model-as-a-Service condition for Small 4 on the pages checked.

Benchmarks (provider-reported, dated)

As of 2026-11-15. All figures are as reported by Mistral AI in the Small 4 launch post (16 March 2026) or Hugging Face model card. Several results appear only as charts without numbers in the text; those are described, not quoted.

EvaluationMistral Small 4Comparator in sourceSource and date
GPQA Diamond71.2None given in textHugging Face card
AA LCR (long-context reasoning)0.72, with about 1.6K characters of outputMistral states Qwen models need about 5.8K to 6.1K characters for comparable performanceLaunch post; Hugging Face card
LiveCodeBenchOutperforms GPT-OSS 120B (no number in text)About 20% less output than GPT-OSS 120BLaunch post; Hugging Face card
End-to-end completion time40% lowerVersus Mistral Small 3, latency-optimised setupLaunch post
Requests per second3x higherVersus Mistral Small 3, throughput-optimised setupLaunch post

The launch post states that with reasoning enabled Small 4 matches or surpasses GPT-OSS 120B on the three benchmarks it charts; AIME25 appears only as an image. Other comparators named are Mistral Small 3.2 24B Instruct and Magistral Small 2509. Benchmark settings differ between labs, so treat cross-lab comparisons with care.

Model card and system card

Mistral publishes two model cards for Small 4: the documentation card at docs.mistral.ai, with the API name, version, status, pricing, features and licence, and the Hugging Face card, with architecture, recommended settings and deployment guidance. Mistral does not publish a separate system card or safety evaluation for Small 4 on the pages checked. What the cards state:

  • Design: a hybrid of instruct, reasoning and coding, replacing separate Magistral and Devstral Small models.
  • Architecture: Mixture-of-Experts with 128 experts, 4 active per token; tagged mistral3, served in Transformers as Mistral3ForConditionalGeneration.
  • Weights formats: Safetensors in BF16 and FP8 (F8_E4M3), plus a separate NVFP4 checkpoint.
  • Usage condition: Apache 2.0, with a statement that the model must not be used to infringe third-party rights.
  • Parameter wording: the documentation card says 6.5B active; the launch post says 6B active, or 8B including embedding and output layers.

For what model and system cards usually contain, see Model Cards and System Cards Explained.

Data handling

Mistral AI's help centre applies the same rules to Small 4 as to other API models; there is no Small 4 specific data policy on the pages checked.

  • Free mode in Mistral Studio: Mistral states it may use inputs and outputs to train its models, with an opt-out available.
  • Pay-as-you-go: Mistral states customers keep control over this processing and can opt out at any time.
  • Zero Data Retention: available only on pay-as-you-go and only for stateless API calls (chat completions, FIM, embeddings, moderation and classification, OCR, audio). It is granted on request, at Mistral's discretion.
  • ZDR exclusions: agents, batch files, conversations, libraries, the Files API, Vibe Work and Chat. Small 4's agents, conversations, built-in tools and batching features therefore sit outside ZDR.
  • Self-hosted weights: data stays wherever you run the model; retention is your own responsibility.

Mistral API keys are non-human identities with direct spend and data exposure. See Zero Data Retention for AI and the LLMjacking Guide.

Deprecation status

As of 15 November 2026, Mistral's models overview lists Mistral Small 4 as a current model with no deprecation or retirement date. It is the named replacement for several retired small, reasoning and coding models. Watch the models overview and changelog for changes.

Model or itemDetailsSource
Mistral Small 4 (mistral-small-2603)Current; no deprecation or retirement date listed (2026-11-15)Models overview
Mistral Small 3.2 (mistral-small-2506)Deprecated 2026-04-30, retired 2026-07-31; replacement Small 4Models overview
Mistral Small 3.0 and 3.1Deprecated 2025-11-06, retired 2025-11-30; replacement Small 4Models overview
Magistral Small 1.0, 1.1 and 1.2Retired 2025-11-30 (1.0, 1.1) and 2026-07-31 (1.2); replacement Small 4Models overview
Devstral Small 1.1 (devstral-small-2507)Deprecated 2026-02-27, retired 2026-05-31; replacement Small 4Models overview

How Mistral Small 4 differs from other models in its family

As of 2026-11-15. Sources: Mistral model cards, models overview and changelog. Models listed by release date.

ModelReleasedContextParametersLicenceStatus
Mistral Small 3.2Version 25.06Not stated on the pages checked24B (as named in the Small 4 Hugging Face card)Not stated on the pages checkedRetired 2026-07-31
Mistral Small 42026-03-16256k119B total, 6.5B activeApache 2.0GA
Mistral Medium 3.5Version 26.04Not stated on the pages checkedNot stated by Mistral AINot stated on the pages checkedDeprecated, retires 2027-04-30
Mistral Large 4Preview 2026-10-06; GA 2026-11-051M1.05T total, 52B activeMistral Ecosystem Open-Weight LicenseGA

The documented differences from Large 4 are context (256k versus 1M), scale, reasoning modes (Small 4 offers none and high; Large 4 offers low, medium and high), licence (Apache 2.0 versus the Mistral Ecosystem Open-Weight License) and list price ($0.15 and $0.60 versus $0.70 and $2.10). Predicted outputs and built-in tools are listed on the Small 4 card. See Mistral Large 4, Reasoning Models Explained and Open-Weight Frontier Models Compared.

Practitioner checklist

  • Call mistral-small-2603 explicitly in production code and record the date you adopted it.
  • If you still reference Mistral Small 3.x, Magistral Small or Devstral Small 1.1, migrate to Small 4 and retest prompts; those models are retired.
  • Set reasoning_effort per workload (none or high) and measure output tokens and latency in both modes.
  • Size self-hosted clusters against Mistral's stated minimum and recommended hardware before committing.
  • Check whether your use relies on agents, conversations, batch or built-in tools, which sit outside Zero Data Retention.
  • Scope function-calling and built-in tools to least privilege, with approval for destructive actions.
  • Store Mistral API keys in a secrets manager, separate workspaces by environment and set spend limits.
  • Watch the models overview and changelog for a deprecation notice on Small 4.

Standards and references

Related NHI Mgmt Group resources: Mistral AI Models, Mistral Large 4, Open-Weight Frontier Models Compared, Open-Weight Model Licence Tracker, LLM Pricing Tracker.

PDF for subscribers

Take this guide with you

Every section, table and checklist in one PDF, with links to the sources and related guides. Subscribe to our weekly NHI & AI Identity Journal and we’ll email you a download link.

Free weekly newsletter

Subscribe to the NHI & AI Identity Journal

The latest on NHI and Agentic AI security – articles, research, breaches, news and events every week.

Bonus 33% off our NHI Course when you subscribe.

NHIMG Editorial Note
Researched and written by the NHI Mgmt Group editorial team using AI tools, under the editorial direction of Lalit Choda. Facts are drawn from the sources listed on this page and checked by our automated quality process. Last updated 15 November 2026. Spotted an error? Use our contact page.
NHI Mgmt Group, the independent authority on Non-Human Identity, IAM and Agentic AI security. nhimg.org

PDF Downloads for Newsletter Subscribers

Get the guide

Enter your details and we’ll email you a download link.

The full guide is free to read online. The PDF is a thank you for subscribing.

Fill in all fields marked * and tick the PDF box to continue.