Mistral AI

Mistral Small 4

Vérifié par l’équipe de recherche de GetInfoUsDernière révision : October 2026Politique éditoriale
48
Intelligence Index

compact 2026 production moteur combining 256K contexte, léger hybrid raisonnement, natif vision, et ultra-rapide débit.

Technical Specifications

Provider
Mistral AI
Category
open-source
Release Date
2026-03
Knowledge Cutoff
January 2026
Architecture
Next-Gen Compact Multimodal Transformer
Parameters
24B
Context Window
256K tokens
Max Output
16K tokens
Cached Input Price
$0.03 / 1M tokens
Batch API Discount
50% off async batch
Consumer Subscription
Free / Self-Hosted
Reasoning Mode
Yes (Chain-of-Thought)
Reasoning Effort Control
Configurable (Low / Med / High)
Tool Calling
Yes
Structured Outputs
Yes
Open Weights
Yes (Open Source / Self-Hostable)
Input Modalities
text, vision
Output Modalities
text
Official Documentation
Visit Official Docs ↗

Data Privacy, Licensing & Deployment Governance

API Data Training Policy
100% Isolated when self-hosted on private GPUs or VPC
Model License & Commercial Rights
Permissive Open-Weights (Apache 2.0 / MIT Commercial)
Deployment & Cloud Availability
Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API
Output Ownership
Full commercial ownership of generated outputs

Official Provider Release Intelligence, API Quotas & Agentic Specs

Compare Multi-Models Side-by-Side →
Official API Model ID (SDK String)
mistral-small-4-latest
Supported SDK & API Protocol
OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
Lifecycle & Deprecation Status
Active GA (Guaranteed support through 2028+)
Production Rate Limits (RPM & TPM)
Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
Long-Context Pricing Tier (>128K / >200K)
Flat rate ($0.1/1M in) across full 256K window
Prompt Cache Write & TTL Policy
Cached input at $0.03/1M tokens
Computer Use & Browser GUI Agent
API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
MCP & Parallel Tool Calling
Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
Web Search Grounding & Code Sandbox
Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
Fine-Tuning & Distillation Support
Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
Multimodal Tokenization Billing
Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile)
Weights Precision & Quantization
BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
Minimum GPU VRAM Requirement
15 GB VRAM (4-bit Quantized) · 52 GB VRAM (Native BF16)
Supported Inference Engines
vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
System Card & Safety Framework
Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
Enterprise Compliance (SOC2 / HIPAA / ZDR)
100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Engineering & Pricing Workbench

Mistral Small 4 Cost, Context, Hardware & API Integration

500 / day
4,000 tok
1,000 tok
Conversation Depth (History Re-billing):1 Turn (Single-Shot)
50%
Estimated Monthly API Cost (30 Days)
$8.40$10.50
Monthly Savings: $2.10 (Caching/Batch)
Subscription ($20/mo) vs API

Pay-as-you-go API is cheaper for this volume (saves $11.60/mo vs $20 flat plan).

Break-even point: ~1,190 requests/day equals $20/month.

Same Monthly Workload Cost Across Popular Reference Models

Mistral Small 4 (Active)
$8.40
/ month
Gemini 2.5 Flash
$18.00
/ month
DeepSeek V3
$32.70
/ month
GPT-4o
$300.00
/ month
Claude 3.7 Sonnet
$405.00
/ month

Live Prompt Paste Tokenizer & Cost Counter

Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.

Chars / Words
175 / 24
OpenAI o200k
~46 tok
Claude BPE
~49 tok
Llama / DeepSeek
~51 tok

Hybrid Prompt Routing Cascade Simulator

Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Mistral Small 4:

Cascaded Monthly Bill:$15.60/mo
This model is already priced at or below the fast router baseline.

Benchmark Scores & 6-Axis Capability Radar

Benchmark Encyclopedia
Coding (51)Reasoning (64)Knowledge (78)Speed (80)Context (85)Cost Value (94)
Mistral Small 42026 Frontier Median
SWE-bench Verified
44.5%
GPQA Diamond
56%
MMLU-Pro
78%
HumanEval
88%
Terminal-Bench
38%
AIME
66%
Long-Context Reasoning
80%
Chatbot Arena Elo
1315pts

Strengths

  • Colossal 256K fenêtre de contexte dans un compact 24B ouvert framework
  • Blazing 120 tokens/sec vitesse avec 340ms temps-à-premier-token
  • Integrated hybrid raisonnement effort et natif visuel compréhension

Limitations & Trade-offs

  • Outperformed par billions-paramètre phare titans sur recherche-level physics
  • visuel résolution limité à standard document tiles

Editorial Assessment

le benchmark standard pour élevé-vitesse, faible-coût ouvert multimodal AI dans 2026.

Best for: élevé-volume agent orchestration, faible-coût document parsing, et périphérie déploiements

Frequently Asked Questions about Mistral Small 4

How much does the Mistral Small 4 API cost per 1M tokens?+

Mistral Small 4 by Mistral AI is priced at $0.1 per 1M input tokens and $0.3 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.03 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.

Should I use a $20/month subscription or the Mistral Small 4 pay-as-you-go API?+

A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.

How many words and pages fit in Mistral Small 4's context window?+

Mistral Small 4 features a 256K tokens context window, which equals approximately 192,000 English words or ~512 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 16,384 tokens.

Can I run Mistral Small 4 locally on my own GPU (Open Weights)?+

Yes, Mistral Small 4 (24B) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.

Does Mistral AI train on data sent to the Mistral Small 4 API, and is commercial use allowed?+

100% Isolated when self-hosted on private GPUs or VPC. License tier: Permissive Open-Weights (Apache 2.0 / MIT Commercial). Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.

How does Mistral Small 4 perform on coding and reasoning benchmarks?+

Mistral Small 4 achieves a composite Intelligence Index of 48/100, scoring 44.5% on SWE-bench Verified, 56% on GPQA Diamond, 78% on MMLU-Pro, and 1315 pts on Chatbot Arena Elo.

What is Mistral Small 4 best used for?+

Mistral Small 4 is best suited for: élevé-volume agent orchestration, faible-coût document parsing, et périphérie déploiements. Assessment: le benchmark standard pour élevé-vitesse, faible-coût ouvert multimodal AI dans 2026.

Les scores de benchmarks, tarifs par token et limites évoluent rapidement. Vérifiez toujours les spécifications actuelles sur la documentation officielle du fournisseur.

Sources: Mistral AI 2026 Lineup Announcement (March 2026)↗