Mistral Large
Mistral's flagship model. Strong reasoning, multilingual, and coding capabilities.
Mistral Large is text & chat AI model from Mistral AI, priced at €20.00 per 1M input tokens with a 128K tokens context window.
0.7
Examples
See what Mistral Large can generate
Write a short product description for a smartwatch in English, then translate it to French and German
English: The AuraFit Pro tracks your heart rate, sleep, and workouts with medical-grade accuracy. Its always-on AMOLED display and 7-day battery life keep you connected without compromise. French: L'AuraFit Pro suit votre fréquence cardiaque, votre sommeil et vos entraînements avec une précision de qualité médicale. Son écran AMOLED toujours actif et son autonomie de 7 jours vous gardent connecté sans compromis. Deutsch: Die AuraFit Pro überwacht Herzfrequenz, Schlaf und Training mit medizinischer Präzision. Das Always-on-AMOLED-Display und die 7-Tage-Akkulaufzeit halten Sie ohne Kompromisse verbunden.
Write a brief API documentation entry for a POST /users endpoint that creates a new user
## POST /users Creates a new user account. **Request Body:** ```json { "email": "string (required)", "name": "string (required)", "password": "string (required, min 8 chars)" } ``` **Response 201:** ```json { "id": "uuid", "email": "string", "name": "string", "createdAt": "ISO 8601" } ``` **Errors:** 400 (validation failed), 409 (email already exists), 500 (internal error). Rate limit: 10 requests per minute per IP.
Pricing
API Integration
Use our OpenAI-compatible API to integrate Mistral Large into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
// Simple — just pass a string
const reply = await rw.run("mistral-large", "Hello! What can you do?");
console.log(reply);
// With message history
const reply2 = await rw.run("mistral-large", [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);
// Full response with usage info
const res = await rw.chat("mistral-large", [
{ role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);Deep dive — Mistral AI's Mistral Large
Mistral AI was founded in April 2023 in Paris by Arthur Mensch (former Google DeepMind research scientist, now CEO), Guillaume Lample (former Meta FAIR researcher, co-author of LLaMA) and Timothee Lacroix. The company is widely regarded as Europe's flagship frontier AI lab and has championed an open-weights strategy alongside premier commercial models. Mistral became one of the fastest companies to reach unicorn status, raising EUR 105M in seed funding in June 2023 followed by EUR 385M Series A in December 2023 and a EUR 600M Series B in June 2024 at a EUR 5.8B valuation. Investors include Andreessen Horowitz, Lightspeed, General Catalyst, Bpifrance, BNP Paribas, NVIDIA and Salesforce. Mistral has released Mistral 7B (Sep 2023), Mixtral 8x7B and 8x22B Mixture-of-Experts models (Dec 2023 / Apr 2024), the Mistral Large flagship (Feb 2024) and Mistral Large 2 (124B params, July 2024). The company also ships Codestral for code, Pixtral for vision, Mistral Nemo (in partnership with NVIDIA) and Le Chat, a consumer assistant. Partnerships include Microsoft Azure, AWS Bedrock, Vertex AI and a strategic deal with the French government.
Visit Mistral AI →Mistral Large is Mistral AI's flagship dense Transformer family. The original Mistral Large launched in February 2024 with 32K context. Mistral Large 2 followed in July 2024 with 123B parameters, a 128K context window and significantly improved code and reasoning capability. It is a decoder-only Transformer pretrained on a multi-trillion-token corpus emphasising high-quality multilingual web text, code repositories (80+ programming languages), books and scientific papers. Mistral has been a vocal advocate for European data and language coverage, with first-class performance on French, German, Spanish, Italian, Portuguese, Dutch, Russian, Chinese, Japanese and Korean. Post-training applies supervised fine-tuning followed by Direct Preference Optimisation (DPO) on a high-quality, multi-domain preference dataset. The model supports function calling, JSON mode, parallel tool calls and structured output. Mistral Large 2 weights are published under the Mistral Research License for non-commercial research, with a separate commercial license required for production deployment. Mistral also makes the model available through Le Plateforme (their API), Azure AI Studio, Amazon Bedrock, Google Vertex AI, IBM watsonx and Snowflake Cortex.
- Parameters
- 123B (Mistral Large 2; original Mistral Large undisclosed)
- Context
- 128K tokens
- 128K token context window
- Strong multilingual performance: French, German, Spanish, Italian, Portuguese, Dutch, Russian, Chinese, Japanese, Korean
- Code generation across 80+ programming languages
- Function calling and parallel tool calls
- JSON mode and Structured Output
- Strong math reasoning on MATH and GSM8K
- Available via Le Plateforme, Azure, Bedrock, Vertex AI, IBM watsonx and Snowflake
- Weights downloadable under Mistral Research License
- Open ecosystem with vLLM, llama.cpp, HuggingFace support
- European data residency option for regulated industries
- Best for: enterprise European deployments, multilingual chat, coding assistants, GDPR-sensitive workloads.
Multi-trillion-token pretraining mixture of curated multilingual web text (heavy emphasis on European languages), code repositories spanning 80+ languages, scientific papers and books. Knowledge cutoff is approximately mid-2024 for Mistral Large 2.
License: Dual license: Mistral Research License (non-commercial research) for downloadable weights; Mistral Commercial License required for production use. Also available via API and cloud-marketplace endpoints.
Known limitations
- Lower refusal rate can yield unsafe outputs without system-prompt guardrails
- No native vision in the base Mistral Large 2 model (use Pixtral for vision)
- Smaller real-world deployment base than OpenAI/Anthropic
- Commercial license costs separate from API usage
- Knowledge cutoff mid-2024
Frequently asked questions
Related Models
View all Text & ChatClaude Opus 4
Anthropic's most powerful model. Exceptional at complex analysis, agentic tasks, and extended reasoning.
Claude Sonnet 4
Anthropic's most capable model. Excellent for complex analysis, coding, math, and creative writing.
DeepSeek V3.1
DeepSeek's refreshed V3.1 release. 671B MoE / 37B active. Tops open-weights leaderboards on coding and reasoning.
DeepSeek V4 Pro
DeepSeek's April 2026 flagship. 1.6T MoE / 49B active params, 1M context, rivals top closed-source models on STEM and coding at a fraction of the price.
Start using Mistral Large today
Get started with free credits. No credit card required. Access Mistral Large and 100+ other models through a single API.