Mistral AI

Magistral Medium

Vérifié par l’équipe de recherche de GetInfoUsDernière révision : October 2026Politique éditoriale
Raisonneur transparentOfficial Source Verified ↗
51
Intelligence Index

de Mistral spécialisé raisonnement moteur engineered avec inspectable chaîne de pensée, mathématique proof synthèse, et deliberate decision trees.

Technical Specifications

Provider
Mistral AI
Category
reasoning
Release Date
2025-03
Knowledge Cutoff
January 2025
Architecture
Reinforcement-Learned Reasoning Transformer
Parameters
Confidential (~70B)
Context Window
128K tokens
Max Output
33K tokens
Cached Input Price
$0.25 / 1M tokens
Batch API Discount
50% off async batch
Consumer Subscription
API Pay-as-you-go
Reasoning Mode
Yes (Chain-of-Thought)
Reasoning Effort Control
Configurable (Low / Med / High)
Tool Calling
Yes
Structured Outputs
Yes
Open Weights
No (Proprietary Cloud)
Input Modalities
text
Output Modalities
text
Official Documentation
Visit Official Docs ↗

Data Privacy, Licensing & Deployment Governance

API Data Training Policy
API payloads are excluded from model training by default
Model License & Commercial Rights
Proprietary Commercial API (Mistral AI Terms)
Deployment & Cloud Availability
Mistral AI Cloud API & Enterprise Endpoints
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)
magistral-medium-latest
Supported SDK & API Protocol
Mistral AI REST API (OpenAI-Compatible)
Lifecycle & Deprecation Status
Active GA (Guaranteed support through 2027+)
Production Rate Limits (RPM & TPM)
5,000 – 15,000 RPM (Production Tier) · 800,000 – 2,000,000 TPM
Long-Context Pricing Tier (>128K / >200K)
Flat rate ($1/1M in) across full 128K window
Prompt Cache Write & TTL Policy
Cached input at $0.25/1M 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
API Prompt Engineering & RAG Distillation
Multimodal Tokenization Billing
Text BPE (~4 chars/token)
Weights Precision & Quantization
Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster)
Minimum GPU VRAM Requirement
Zero Local VRAM Required (100% Serverless Cloud API)
Supported Inference Engines
Managed Mistral AI Cloud API
System Card & Safety Framework
Mistral AI Production Safety & Alignment Verified
Enterprise Compliance (SOC2 / HIPAA / ZDR)
SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier
Engineering & Pricing Workbench

Magistral Medium 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)
$90.00$112.50
Monthly Savings: $22.50 (Caching/Batch)
Subscription ($20/mo) vs API

For single-user chat, a $20/mo subscription caps your bill below this API volume.

Break-even point: ~111 requests/day equals $20/month.

Same Monthly Workload Cost Across Popular Reference Models

Magistral Medium (Active)
$90.00
/ 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 Magistral Medium:

Cascaded Monthly Bill:$36.00/mo
Saves $54.00/mo (60% cost reduction) vs sending 100% of traffic to Magistral Medium.

Benchmark Scores & 6-Axis Capability Radar

Benchmark Encyclopedia
Coding (52)Reasoning (78)Knowledge (83)Speed (33)Context (75)Cost Value (72)
Magistral Medium2026 Frontier Median
SWE-bench Verified
45.2%
GPQA Diamond
67.8%
MMLU-Pro
82.5%
HumanEval
90%
Terminal-Bench
40%
AIME
76.5%
Long-Context Reasoning
80%
Chatbot Arena Elo
1335pts

Strengths

  • Transparent, auditable internal raisonnement trace before final synthèse
  • substantiel improvements sur compétitif mathematics et algorithmic proofs
  • complet 128K fenêtre de contexte avec deliberate outil planning

Limitations & Trade-offs

  • supérieur token sortie overhead due à étendu raisonnement traces
  • texte-seulement entrée sans natif image ou vidéo traitement

Editorial Assessment

de Mistral answer au raisonnement de pointe, pairing transparency avec rigorous deduction.

Best for: complexe audit reports, juridique clause contradiction analyse, et mathématique logique proofs

Frequently Asked Questions about Magistral Medium

How much does the Magistral Medium API cost per 1M tokens?+

Magistral Medium by Mistral AI is priced at $1 per 1M input tokens and $3.5 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.25 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.

Should I use a $20/month subscription or the Magistral Medium 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 Magistral Medium's context window?+

Magistral Medium features a 128K tokens context window, which equals approximately 96,000 English words or ~256 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 32,768 tokens.

Can I run Magistral Medium locally on my own GPU (Open Weights)?+

No, Magistral Medium is a proprietary closed-weights model hosted by Mistral AI. It cannot be downloaded for local GPU execution and must be accessed via Mistral AI's official API or cloud platform.

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

API payloads are excluded from model training by default. License tier: Proprietary Commercial API (Mistral AI Terms). Full commercial ownership of generated outputs. Supported deployment channels include: Mistral AI Cloud API & Enterprise Endpoints.

How does Magistral Medium perform on coding and reasoning benchmarks?+

Magistral Medium achieves a composite Intelligence Index of 51/100, scoring 45.2% on SWE-bench Verified, 67.8% on GPQA Diamond, 82.5% on MMLU-Pro, and 1335 pts on Chatbot Arena Elo.

What is Magistral Medium best used for?+

Magistral Medium is best suited for: complexe audit reports, juridique clause contradiction analyse, et mathématique logique proofs. Assessment: de Mistral answer au raisonnement de pointe, pairing transparency avec rigorous deduction.

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 Research Laboratory (March 2025)↗