All models
Text & reasoningStable
Mistral AIMistral Small 4
Mistral's lower-cost open model that combines normal instruction following, reasoning, coding, vision, and agent tools in one endpoint.
Plain-English overview
What Mistral Small 4 actually is
Mistral Small 4 uses a 119B mixture-of-experts architecture with 6.5B active parameters. It is designed to cover everyday assistant work and deeper reasoning without making developers switch between separate instruct, reasoning, and coding models.
The model keeps a 256K context window while charging substantially less than Medium 3.5 on Mistral's hosted API. Apache-2.0 weights also make it appealing when a team needs local control, custom serving, or an offline development route.
Good fit for
- Cost-sensitive production assistants
- Coding and tool use on one flexible model
- Self-hosted text-and-image applications
Category comparison
The facts that matter for text models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Context window
- 256K tokens combinedMaximum combined prompt and working context documented by the provider.
- Maximum output
- Not separately publishedProvider-published response limit, where available.
- Knowledge cutoff
- Not publishedLatest reliable knowledge date explicitly published by the model provider. Search and connected tools can retrieve newer information but do not change the model's built-in cutoff.
- Input price
- $0.15 / 1MCurrent standard list price per million input tokens unless noted.
- Output price
- $0.60 / 1MCurrent standard list price per million output tokens unless noted.
- Inputs
- Text, imageMedia types accepted by the listed model endpoint.
- Tools & agents
- Functions, agents, built-in tools, structured and predicted outputsSelected native tools and agent-building capabilities, not an exhaustive list.
Pricing & comparisons
Estimate your cost
Set your usage. Your estimate updates as you type.
Example: 6,000 input tokens for 10 pages, plus a 500-token summary. Page lengths vary; adjust the numbers below.
One run sends your input to the model once and receives an answer. Tokens are pieces of text: input is what you send, output is the answer you receive.
Advanced options
Mistral Small 4
Mistral AI
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
- Input tokens
- $0.15 per 1M tokens
- Output tokens
- $0.60 per 1M tokens
How this estimate works
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Where to get Mistral Small 4
Availability
Regions and access stage
Available through the Mistral API and Studio and as Apache-2.0 open weights for self-hosting.
Hosted regional inference is offered through supported EU and US endpoints at a 10% surcharge; self-hosting gives the operator direct region control.
Check live availabilityData and training
The route matters.
Mistral's commercial terms exclude model training by default except when a customer opts in or uses designated Labs or preview models. Self-hosting keeps inference data under the operator's controls; hosted API retention is generally 30 days unless zero data retention is enabled.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Mistral Small 4 FAQ
What is Mistral Small 4?
Mistral's lower-cost open model that combines normal instruction following, reasoning, coding, vision, and agent tools in one endpoint. Mistral Small 4 uses a 119B mixture-of-experts architecture with 6.5B active parameters. It is designed to cover everyday assistant work and deeper reasoning without making developers switch between separate instruct, reasoning, and coding models.
When was Mistral Small 4 released?
Mistral Small 4 was released on March 16, 2026 according to the cited provider materials.
Where can I access Mistral Small 4?
Available through the Mistral API and Studio and as Apache-2.0 open weights for self-hosting. The access routes listed in this guide are Mistral AI and Mistral Studio.
How much does Mistral Small 4 cost?
$0.15 input · $0.60 output / 1M tokens. Mistral's standard hosted list price. The weights are Apache 2.0; self-hosted cost depends on infrastructure.
Where is Mistral Small 4 available?
Available through the Mistral API and Studio and as Apache-2.0 open weights for self-hosting. Hosted regional inference is offered through supported EU and US endpoints at a 10% surcharge; self-hosting gives the operator direct region control.
Is my Mistral Small 4 API data used for training?
Mistral's commercial terms exclude model training by default except when a customer opts in or uses designated Labs or preview models. Self-hosting keeps inference data under the operator's controls; hosted API retention is generally 30 days unless zero data retention is enabled. The policy belongs to the provider route and account terms, so verify it again before production use.
Price comparison
USD per million tokens for the shown API routes at standard context length. Cache and long-context rates may differ. Models without matching reviewed prices are omitted; lower cost does not mean better quality.
- Mistral Small 4$0.15
Mistral AI
This model
- Gemini 3.8 Flash$0.75
Google
- GPT-5.6 Sol$4.00
OpenAI
- GPT-6 Astra$10.00
OpenAI
- Claude Fable 5.1$10.00
Anthropic
- Mistral Small 4$0.60
Mistral AI
This model
- Gemini 3.8 Flash$3.75
Google
- GPT-5.6 Sol$20.00
OpenAI
- GPT-6 Astra$50.00
OpenAI
- Claude Fable 5.1$50.00
Anthropic
Related comparisons
Head-to-head comparisons
Mistral Small 4 vs GPT-6 Astra
OpenAI's most capable model for difficult end-to-end work, combining frontier reasoning with a million-token context window and a broad set of agent tools.
Open full comparisonMistral Small 4 vs GPT-5.6 Sol
OpenAI's flagship general model for difficult coding, analysis, and professional work, with a very large context window and a broad native tool set.
Open full comparisonMistral Small 4 vs Claude Fable 5.1
Anthropic's frontier model for ambitious, long-running agentic and coding work, with strong vision and enterprise marketplace availability.
Open full comparisonMistral Small 4 vs Gemini 3.8 Flash
Google's stable, high-efficiency multimodal model for agents, software work, and large mixed-media inputs at an introductory Flash-tier price.
Open full comparisonMistral Small 4 vs Grok 4.6
SpaceXAI's frontier text-and-image model for coding, agentic tasks, and knowledge work, with direct web, X, and code tools.
Open full comparisonMistral Small 4 vs Grok 4.20 Multi-Agent Beta
A specialist Grok model that sends several AI agents to investigate a difficult question in parallel, then combines their work into one researched answer.
Open full comparisonMistral Small 4 vs Inkling
Thinking Machines Lab's large open-weights model for customizable reasoning, coding, tools, vision, and audio workflows.
Open full comparisonMistral Small 4 vs Mistral Medium 3.5
Mistral's open-weight frontier model for demanding multimodal, coding, reasoning, and agent workflows, with a 256K context window.
Open full comparisonMistral Small 4 vs Qwen3.8 Max
Alibaba's frontier Qwen model for long-context reasoning, coding, tools, and understanding text, images, and video.
Open full comparisonMistral Small 4 vs MiniMax M3
MiniMax's million-token multimodal model for coding, agents, computer use, and long projects at a low direct API price.
Open full comparisonMistral Small 4 vs GLM-5.3
Z.ai's open-weight long-context reasoning model for coding, tools, and agentic work across self-hosted and managed routes.
Open full comparisonMistral Small 4 vs Kimi K3
Moonshot AI's frontier multimodal model for million-token coding, reasoning, knowledge work, and tool-driven agents.
Open full comparisonMistral Small 4 vs Falcon-H1R-7B
TII's compact open reasoning model for text tasks, long contexts, and self-hosted function-calling workflows.
Open full comparisonMistral Small 4 vs Falcon-H1-34B-Instruct
TII's 34B open instruction model for multilingual text, coding, and controlled self-hosted applications.
Open full comparisonMistral Small 4 vs Muse Spark 1.3
Meta's latest multimodal reasoning model for long-running agents, coding, tools, and complex user collaboration.
Open full comparisonMistral Small 4 vs Celeris-1 Magnus
Celeris' agent-focused diffusion language model for fast reasoning, tool loops, structured actions, and OpenAI-compatible integration.
Open full comparisonMistral Small 4 vs NVIDIA Nemotron 3 Ultra
NVIDIA's largest Nemotron 3 reasoning model for complex agents, coding, planning, tools, RAG, and million-token analysis.
Open full comparisonMistral Small 4 vs NVIDIA Nemotron 3.5 Lightning
NVIDIA's compact 30B mixture-of-experts model for efficient specialist agents and high-volume text workflows.
Open full comparisonMistral Small 4 vs Qwen3.8-Flash
Alibaba's efficient million-context multimodal model for fast agents, coding, document work, vision, video understanding, and tool use.
Open full comparisonMistral Small 4 vs DeepSeek-V4-Pro
DeepSeek's flagship million-context text model for difficult reasoning, coding, long-running agents, tools, and very large outputs.
Open full comparisonMistral Small 4 vs DeepSeek-V4-Flash
DeepSeek's lower-cost V4 model for high-volume reasoning, coding, agents, and million-token text workloads.
Open full comparison
