Mistral: Mistral Small 3.2 24B API Pricing
by mistralai · 131K context window ·
Explore Mistral Small 3.2's 24B model API pricing, crucial for ML engineers evaluating LLMs. Offered by mistralai, this powerful API features a 131,072 token context window. Understand the cost structure: Input tokens are priced at $0.06000 per 1 million tokens, while output tokens cost $0.18000 per 1 million. That is $0.2400 per 1 million tokens. For example, processing 100 million input tokens and generating 25 million output tokens would cost $10.50 per month. Get a clear breakdown to accurately estimate your monthly expenditure and compare Mistral Small's performance and cost-effectiveness with other leading LLM APIs.
Monthly Cost Examples
Assuming 50% input / 50% output token split
| Usage | Monthly cost |
|---|---|
| 100K tokens/month | $0.01 |
| 1M tokens/month | $0.12 |
| 10M tokens/month | $1.20 |
| 100M tokens/month | $12.00 |
Compare with other models
Mistral: Mistral Small 3.2 24B vs OpenAI: GPT-4o →Mistral: Mistral Small 3.2 24B vs OpenAI: GPT-4o-mini →Mistral: Mistral Small 3.2 24B vs OpenAI: o1 →Automate your model selection
StormRouter sends each request to the cheapest model that can handle it.
Only use Mistral: Mistral Small 3.2 24B when your quality requirements demand it.