Mistral AI

Devstral 2

Vérifié par l’équipe de recherche de GetInfoUsDernière révision : October 2026Politique éditoriale
IA Agentique et Outils AutonomesOfficial Source Verified ↗
56
Intelligence Index

Devstral 2 de Mistral AI est un modèle d’IA conçu pour les flux de travail agentiques autonomes, l’appel d’outils et l’orchestration multi-étapes, offrant une fenêtre de contexte de 262K, une vitesse de 70 tokens/s, un indice d’intelligence de 56/100 et un tarif de $1.5/$4.5 par million de tokens.

Technical Specifications

Provider
Mistral AI
Category
flagship
Release Date
2025-12
Knowledge Cutoff
October 2025
Architecture
Advanced Agentic Code Transformer
Parameters
123B
Context Window
262K tokens
Max Output
66K tokens
Cached Input Price
$0.35 / 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
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)
devstral-2-latest
Supported SDK & API Protocol
OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
Lifecycle & Deprecation Status
Active GA (Guaranteed support through 2027+)
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 ($1.5/1M in) across full 262K window
Prompt Cache Write & TTL Policy
Cached input at $0.35/1M 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)
Weights Precision & Quantization
BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
Minimum GPU VRAM Requirement
76 GB VRAM (4-bit Quantized) · 264 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

Devstral 2 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)
$123.00$157.50
Monthly Savings: $34.50 (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: ~81 requests/day equals $20/month.

Same Monthly Workload Cost Across Popular Reference Models

Devstral 2 (Active)
$123.00
/ 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 Devstral 2:

Cascaded Monthly Bill:$44.25/mo
Saves $78.75/mo (64% cost reduction) vs sending 100% of traffic to Devstral 2.

Benchmark Scores & 6-Axis Capability Radar

Benchmark Encyclopedia
Coding (67)Reasoning (76)Knowledge (84)Speed (47)Context (85)Cost Value (72)
Devstral 22026 Frontier Median
SWE-bench Verified
58.2%
GPQA Diamond
66.5%
MMLU-Pro
83.5%
HumanEval
94%
Terminal-Bench
52%
AIME
78%
Long-Context Reasoning
82%
Chatbot Arena Elo
1365pts

Strengths

  • Fenêtre de contexte de 262K et capacité de sortie maximale de 66K tokens (SWE-bench Verified 58.2% · GPQA Diamond 66.5%)
  • Débit rapide de 70 tokens/seconde avec une latence au premier token (TTFT) de 520 ms
  • Poids ouverts (123B) permettant un déploiement sur site ou cloud privé via vLLM, SGLang ou Ollama

Limitations & Trade-offs

  • Nécessite des serveurs GPU dotés de suffisamment de mémoire VRAM pour l’inférence locale à pleine précision
  • Sur les problèmes de recherche fondamentale très complexes, les modèles de raisonnement lourd restent supérieurs

Editorial Assessment

Alliant un indice d’intelligence de 56/100, un contexte de 262K et un débit de 70 tok/s, Devstral 2 s’impose comme une valeur sûre de la gamme Mistral AI.

Best for: Conçu pour les flux de travail agentiques autonomes, l’appel d’outils et l’orchestration multi-étapes, l’intégration RAG et les pipelines de production évolutifs.

Frequently Asked Questions about Devstral 2

How much does the Devstral 2 API cost per 1M tokens?+

Devstral 2 by Mistral AI is priced at $1.5 per 1M input tokens and $4.5 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.35 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.

Should I use a $20/month subscription or the Devstral 2 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 Devstral 2's context window?+

Devstral 2 features a 262K tokens context window, which equals approximately 196,608 English words or ~524 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 65,536 tokens.

Can I run Devstral 2 locally on my own GPU (Open Weights)?+

Yes, Devstral 2 (123B) 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 Devstral 2 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 Devstral 2 perform on coding and reasoning benchmarks?+

Devstral 2 achieves a composite Intelligence Index of 56/100, scoring 58.2% on SWE-bench Verified, 66.5% on GPQA Diamond, 83.5% on MMLU-Pro, and 1365 pts on Chatbot Arena Elo.

What is Devstral 2 best used for?+

Devstral 2 is best suited for: Conçu pour les flux de travail agentiques autonomes, l’appel d’outils et l’orchestration multi-étapes, l’intégration RAG et les pipelines de production évolutifs.. Assessment: Alliant un indice d’intelligence de 56/100, un contexte de 262K et un débit de 70 tok/s, Devstral 2 s’impose comme une valeur sûre de la gamme Mistral AI.

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 Devstral 2 Release (December 2025)↗