AI Cost Calculators
Mistral API Cost Calculator
Estimate Mistral API costs using input tokens, output tokens, Batch API, requests, and monthly usage.
Enter Your Mistral API Usage
Use average token values for one request, then enter the expected number of requests in one month.
Price used per 1 million tokens
Input:$0.15
Output:$0.60
Estimated Mistral API Cost
This estimate covers the text token charges entered above.
Estimated monthly cost
Per request
$0.000375
Per day
$0.75
Per year
$270.00
Input cost
66,000,000 tokens
$9.90
Output cost
21,000,000 tokens
$12.60
Requests: 60,000
Total input tokens: 66,000,000
Total output tokens: 21,000,000
* Important: Calculated from the values currently shown. Default usage values are examples, so change them to match your expected usage. Built-in Mistral rates were checked on June 19, 2026. Final charges may include OCR, transcription, speech, fine-tuning, agents, tools, storage, taxes, discounts, retries, and other services.
Mistral API costs can change with the model, prompt size, answer length, request count, and pricing mode. This calculator helps you test a small launch, a normal month, and a higher-usage case before you build.
How the Mistral API Cost Calculator Works
Choose a Mistral model and enter the expected requests per month. Then add the average input and output tokens used by one request.
The calculator separates input and output costs. It also lets you compare standard API pricing with the lower Batch API estimate.
The result shows the estimated cost per request, day, month, and year.
What to Enter for a Useful Estimate
Include the system message, prompt, chat history, retrieved text, and other content sent to the model in your input estimate.
Use the average answer length expected in real use. Longer answers can increase the monthly bill.
Test a normal case and a busy case so you can see how cost may change as users and requests grow.
Common Ways to Use This Calculator
- Estimate the monthly cost of a Mistral chatbot.
- Compare Mistral Small, Large, Medium, and Codestral.
- Compare Standard API and Batch API pricing.
- Estimate cost per request, day, month, and year.
- Review the effect of longer prompts and answers.
- Prepare an early Mistral API budget.
Simple Mistral API Cost Example
Imagine an AI assistant with 60,000 requests per month. Each request uses 1,100 input tokens and 350 output tokens. Enter those values and choose Mistral Small 4.
You can then switch to Mistral Large 3, Mistral Medium 3.5, or Codestral without changing the workload.
Pricing and Estimate Notes
Built-in prices were checked against Mistral's official pricing and model pages on June 19, 2026.
This calculator covers text token charges only. OCR, transcription, speech, fine-tuning, agents, tools, storage, taxes, and other services may add separate costs.
Always check the official Mistral pricing page before making a final budget or purchase decision.
Frequently Asked Questions
How is Mistral API cost calculated?
The calculator multiplies total input and output tokens by the selected model rates. It then shows the estimated cost per request, day, month, and year.
Does Mistral Batch API cost less?
Yes. Mistral says Batch API processing can cost 50% less than standard synchronous API calls. Choose Batch API in the calculator to apply that reduction.
Can I compare Mistral models?
Yes. Keep the same request and token values, then switch models to compare their estimated costs.
Does this include every Mistral service?
No. It covers text token charges only. OCR, transcription, text-to-speech, fine-tuning, agents, tools, storage, and other services may have separate prices.
Are the results exact?
No. They are planning estimates. Your final bill may change because of price updates, retries, discounts, taxes, or other paid services.
Can I enter my own Mistral prices?
Yes. Turn on custom pricing and enter your own input and output rates per million tokens.