Saltar al contenido principal
DESTACADO · GRATISCalculadora VRAM, ¿qué GPU ejecuta qué modelo? →
Destacado Pack modelos de IA y moda →
Vantaige

Free Tool

Mistral API Cost Calculator

Estimate your monthly and annual Mistral Mistral API cost from your request volume and average token counts. See the full Mistral listing.

¿No sabes cuántos tokens usan tus prompts? Pega tu texto en la Calculadora de Tokens para obtener el recuento exacto primero.

Fórmula: costo mensual = solicitudes mensuales × ((tokens de entrada promedio × precio de entrada) + (tokens de salida promedio × precio de salida)) / 1,000,000

Más barato

ministral-3b

$0.1/M entrada · $0.1/M salida

Costo mensual$1.20
Costo anual$14.40
Costo por solicitud$0.00012

ministral-8b

$0.15/M entrada · $0.15/M salida

Costo mensual$1.80
Costo anual$21.60
Costo por solicitud$0.00018

ministral-14b

$0.2/M entrada · $0.2/M salida

Costo mensual$2.40
Costo anual$28.80
Costo por solicitud$0.00024

mistral-large

$0.5/M entrada · $1.5/M salida

Costo mensual$10.00
Costo anual$120.00
Costo por solicitud$0.001

Mistral Mistral pricing

Published list price per million tokens for Mistral's current Mistral models.

ModelInput $/M tokensOutput $/M tokens
mistral-large$0.5$1.5
ministral-14b$0.2$0.2
ministral-8b$0.15$0.15
ministral-3b$0.1$0.1
open-mistral-7b$0.25$0.25
mistral-medium$0.4$2
mistral-small$0.7$0.7
mistral-tiny$0.25$0.25

Frequently asked questions

How much does Mistral's mistral-large cost?

mistral-large costs $0.5 per million input tokens and $1.5 per million output tokens. Use the calculator above to estimate your own monthly cost from your expected request volume and average token counts.

What is the cheapest Mistral model?

ministral-3b is Mistral's cheapest current Mistral model, priced at $0.1 per million input tokens and $0.1 per million output tokens, versus $0.5 / $1.5 for the flagship mistral-large.

How does Mistral API pricing work?

Mistral bills per token, separately for input tokens (what you send) and output tokens (what the model generates), priced per million tokens. Output tokens typically cost more than input tokens because generation is more compute-intensive. Total request cost is (input tokens × input price + output tokens × output price) / 1,000,000, multiplied by your request volume.

How do I estimate my monthly Mistral API cost?

Enter your expected monthly request volume and average input/output tokens per request into the calculator above, pick one or more Mistral models to compare, and it computes monthly cost, annual cost, cost per request, and cost per user instantly. Add an optional monthly growth rate to see a 12-month cost projection.

Compare across providers

Want to compare Mistral against other providers side by side? Use the full AI Cost Calculator.