Mistral API Pricing and Model Catalog: Use-Case Guide
Mistral offers efficient European AI models with strong coding and multilingual capabilities. Here's how to pick the right model and optimize costs.
Pricing data sourced from our catalog. Check data sources for provenance and freshness.
Mistral model families
Mistral offers several model families, each optimized for different use cases:
- Mistral Large: Flagship models for complex reasoning and analysis
- Mistral Small: Balanced performance and cost for most workloads
- Ministral: Lightweight models for high-volume, low-cost tasks
- Codestral: Specialized models for code generation and analysis
- Devstral: Developer-focused models for coding workflows
Pricing overview
Mistral uses a per-token pricing model with separate rates for input and output tokens. Here are the current prices for the most popular models:
| Model | Input | Output | Context |
|---|---|---|---|
| ministral-3-3b-2512 | $0.10 | $0.10 | 131K |
| mistral-small-latest | $0.06 | $0.18 | 131K |
| mistral-small-3-2-2506 | $0.06 | $0.18 | 131K |
| ministral-3-8b-2512 | $0.15 | $0.15 | 262K |
| ministral-8b-2512 | $0.15 | $0.15 | 262K |
| ministral-8b-latest | $0.15 | $0.15 | 262K |
Cost estimation example
Let's estimate costs for a typical chatbot workload using Mistral Small:
Note: This is a simplified estimate. Actual costs may vary based on system prompts, caching, and other factors.
Use cases and recommendations
Code generation and analysis
Codestral and Devstral models excel at code generation, understanding entire codebases, and performing code reviews with high accuracy. They support multiple programming languages and coding workflows.
Multilingual applications
Mistral models are trained on European languages, making them ideal for multilingual chatbots, translation, and content generation across English, French, German, and other European languages.
Cost-effective chatbots
Ministral models offer excellent performance at very competitive prices, making them ideal for high-volume chatbot applications where cost efficiency matters.
Enterprise deployments
Mistral offers on-premise deployment options and European data residency, making them suitable for enterprise applications with strict data requirements.
Cost optimization tips
- Use prompt caching: Mistral supports context caching to reduce costs for repeated contexts
- Batch processing: Group multiple requests together for lower costs
- Right-size your model: Use Ministral for simple tasks, Small for balanced work, Large for complex reasoning
- Monitor token usage: Track input/output tokens to identify optimization opportunities
- Consider on-premise: For high-volume workloads, self-hosting can be more cost-effective
Compare Mistral models
Ready to compare Mistral models side by side? Use our tools:
Related guides
Cross-provider pricing comparison
How Mistral pricing compares against OpenAI, Anthropic, Google, and DeepSeek.
Hidden costs of LLM APIs
Rate limits, latency, evaluation overhead, and vendor risk beyond per-token pricing.
Model routing cascade
When to use budget vs premium models across providers.
Mistral Small vs Ministral 8B vs Ministral 3B
Detailed pricing and capability comparison of Mistral's model families.
Frequently asked questions
What is the cheapest Mistral model?
Ministral 3B is typically the most cost-effective option for high-volume, low-complexity tasks.
Does Mistral offer batch pricing?
Yes, Mistral offers batch API pricing for asynchronous workloads. Check the current pricing page for details.
How does Mistral compare to OpenAI?
Mistral focuses on efficiency and European languages, while OpenAI offers broader model types. Pricing is competitive, with Mistral often being more cost-effective for coding and multilingual tasks.