de Mistral dedicado code motor trained un través de 80+ programación idiomas, con fill-en-el-middle y 32K contexto tailored para desarrollador productivity.
Technical Specifications
- Provider
- Mistral AI
- Category
- coding
- Release Date
- 2024-05
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Fixed
- 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)
- codestral-latest
- Supported SDK & API Protocol
- OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
- Lifecycle & Deprecation Status
- Legacy Stable (Upgrade path available in Mistral AI lineup)
- 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 ($0.2/1M in) across full 256K window
- Prompt Cache Write & TTL Policy
- Cached input at $0.05/1M 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
- 14 GB VRAM (4-bit Quantized) · 47 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
Codestral Cost, Context, Hardware & API Integration
Pay-as-you-go API is cheaper for this volume (saves $3.50/mo vs $20 flat plan).
Break-even point: ~606 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 Codestral:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 28%
- GPQA Diamond
- 42%
- MMLU-Pro
- 70%
- HumanEval
- 81.1%
- Chatbot Arena Elo
- 1240pts
Strengths
- Fluent en sobre 80 programación idiomas de Python y TypeScript un Rust y COBOL
- Fill-en-el-Middle (FIM) optimización tailored para en tiempo real IDE code completion
- rápido inferencia (110 tok/s) un económico-friendly desarrollador precios
Limitations & Trade-offs
- Non-producción license para direct weight downloads (Mistral Non-producción License)
- 32K ventana de contexto puede be tight para enorme multi-service mono-repos
Editorial Assessment
un lean, rápido, y remarkably capaz code asistente que rivals much larger foundation modelos.
Best for: VS Code y JetBrains extension backends, automatizado test generación, y multi-idioma traducción
Compare Codestral
Frequently Asked Questions about Codestral
How much does the Codestral API cost per 1M tokens?+
Codestral by Mistral AI is priced at $0.2 per 1M input tokens and $0.6 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.05 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the Codestral 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 Codestral's context window?+
Codestral 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 8,192 tokens.
Can I run Codestral locally on my own GPU (Open Weights)?+
Yes, Codestral (22B) 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 Codestral 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 Codestral perform on coding and reasoning benchmarks?+
Codestral achieves a composite Intelligence Index of 40/100, scoring 28% on SWE-bench Verified, 42% on GPQA Diamond, 70% on MMLU-Pro, and 1240 pts on Chatbot Arena Elo.
What is Codestral best used for?+
Codestral is best suited for: VS Code y JetBrains extension backends, automatizado test generación, y multi-idioma traducción. Assessment: un lean, rápido, y remarkably capaz code asistente que rivals much larger foundation modelos.
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 Codestral:
La unidad básica de texto que procesa un modelo de lenguaje, que normalmente equivale a 3 o 4 caracteres o aproximadamente 0,75 palabras. Por ejemplo, una frase típica se divide en varios tokens.
Un conjunto estandarizado de pruebas para evaluar y comparar objetivamente las capacidades de distintos modelos de IA en tareas como programación (SWE-bench) o matemáticas avanzadas (AIME).
La cantidad máxima de tokens que un modelo puede considerar a la vez, incluyendo tanto la entrada que lee como la salida que genera. Una ventana de 1.000.000 de tokens puede procesar unas 750.000 palabras en una sola petición.
La capacidad de un modelo de detectar la necesidad de una función externa y emitir argumentos JSON estructurados para ejecutar API, búsquedas web o consultas a bases de datos.
Un protocolo abierto desarrollado por Anthropic que permite a los agentes de IA conectarse de forma estandarizada a sistemas de archivos locales, entornos de desarrollo y servicios externos.
Una optimización donde los proveedores almacenan estados de atención previos para prefijos de prompts frecuentes, reduciendo el coste de entrada hasta en un 90% y acelerando la respuesta.
Las puntuaciones de benchmarks, precios por token y límites de tasa evolucionan rápidamente. Verifique siempre las especificaciones actuales en la documentación oficial del proveedor.