Mistral AI が提供する Magistral Medium は、最大 128K トークンのコンテキストウィンドウを備え、入力 $1/100万トークン・出力 $3.5/100万トークンで利用可能な、コーディング・推論・業務自動化向け AI モデルです。
Technical Specifications
- Provider
- Mistral AI
- Category
- reasoning
- Release Date
- 2025-03
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- API Pay-as-you-go
- Reasoning Effort Control
- Configurable (Low / Med / High)
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- 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
Magistral Medium Cost, Context, Hardware & API Integration
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
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
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:
Benchmark Scores & 6-Axis Capability Radar
- 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
- Mistral AI の高度な Reinforcement-Learned Reasoning Transformer アーキテクチャと 128K トークンのコンテキスト処理能力
- 優れたコストパフォーマンス（入力 $1/1M、出力 $3.5/1M）と安定した応答速度
- プログラミング、論理的推論、多言語タスクにおいて高いベンチマーク精度を実現
Limitations & Trade-offs
- 大規模な長文コンテキスト処理時はトークン消費量の最適化が必要
- 専門領域のタスクでは適切なプロンプト設計や RAG の併用が推奨される
Editorial Assessment
Magistral Medium は、性能・速度・API コストのバランスに優れた Mistral AI の主力モデルです。
Best for: エンタープライズ自動化、ソフトウェア開発、AI エージェント構築、Mistral AI エコシステムの統合
Compare Magistral Medium
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: エンタープライズ自動化、ソフトウェア開発、AI エージェント構築、Mistral AI エコシステムの統合. Assessment: Magistral Medium は、性能・速度・API コストのバランスに優れた Mistral AI の主力モデルです。
Mistral AI Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Mistral AI's flagship reasoning tier:
Mistral Medium 3.5
Mistral Small 4
Devstral 2
Devstral Medium
Devstral Small
Mistral Small 3.2
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Magistral Medium:
The basic unit of text that a language model processes, typically representing about 3 to 4 English characters or roughly 0.75 words. For example, the sentence "Artificial intelligence is fast" breaks down into about 5 tokens.
A standardized evaluation suite used to objectively measure and rank an AI model's capabilities across specific tasks — such as SWE-bench Verified for software engineering, AIME for competitive math, or MMLU for general knowledge.
The maximum number of tokens a model can consider at once — both the input it reads and the output it writes. A 1,000,000-token context window can hold roughly 750,000 English words in a single request.
An AI model trained via reinforcement learning to spend dynamic compute thinking through complex logic, math, and architectural problems before outputting a solution. Examples include OpenAI o1, o3, and DeepSeek R1.
A step-by-step reasoning technique where an AI model generates intermediate problem-solving thoughts before arriving at a final answer. Native reasoning models like OpenAI o3 and DeepSeek R1 use CoT to solve complex math and coding challenges.
The ability of a language model to recognize when an external capability is needed and output structured JSON arguments to invoke external APIs, databases, or terminal commands. The runtime executes the tool and passes results back to the model.
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.