DevTk.AI

Mistral Large 3

Mistral

Updated August 2026. Mistral Large 3 by Mistral: $0.5/M cache-miss input, $1.50/M output tokens. Cached input: $0.05/M. 128K context, 33K max output. Vision & Function Calling. Free calculator + compare 40+ models.

Input Price

$0.5

cache miss / 1M tokens

Cached Input

$0.05

per 1M tokens

Output Price

$1.50

per 1M tokens

Context Window

128K

tokens

Specifications

ProviderMistral
Model IDmistral-large-3
Input Price$0.5 / 1M cache-miss tokens
Cached Input Price$0.05 / 1M tokens
Output Price$1.50 / 1M tokens
Context Window128K tokens
Max Output33K tokens
Capabilities
textvisionfunction_calling
Release Date2025-12
Pricing SourceOfficial Mistral pricing
Price Verified2026-08-01 · Small 4 is now $0.15/M input and $0.60/M output. Mistral lists a 90% discount for cached input tokens.

Monthly Cost Estimates

Estimated monthly costs based on different daily usage levels (assuming 50% input / 50% output split). Input estimates use cache-miss pricing, so cache-heavy workloads can be lower.

Daily TokensMonthly CostAnnual Cost
10K $0.3 $3.60
50K $1.50 $18.00
100K $3.00 $36.00
500K $15.00 $180.00
1.0M $30.00 $360.00

About Mistral Large 3

Mistral Large 3 is a large language model by Mistral. It features a 128K token context window with up to 33K tokens of output per request. The model supports 3 capabilities: text, vision, function_calling.

At $0.5 per million cache-miss input tokens and $1.50 per million output tokens, Mistral Large 3 is positioned as a cost-effective option in the Mistral lineup. Repeated prefix input can be charged at $0.05 per million cached tokens. Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.

Mistral Large 3 Key Details

  • Pricing: $0.5/M cache-miss input tokens, $0.05/M cached input tokens, $1.50/M output tokens
  • Context window: 128K tokens — good for standard conversations and tasks
  • Max output: 33K tokens per response
  • Capabilities: text, vision, function_calling
  • Released: 2025-12

Other Mistral Models

Similar Price Range

Related Tools

FAQ

How much does Mistral Large 3 cost?

Mistral Large 3 costs $0.5 per million cache-miss input tokens and $1.50 per million output tokens. Cached input costs $0.05 per million tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $3.75/month before cache-hit savings.

What is Mistral Large 3's context window?

Mistral Large 3 supports a context window of 128K tokens. This means your combined input prompt and output response can be up to 128K tokens. The maximum output per response is 33K tokens.

Is Mistral Large 3 good for my use case?

Mistral Large 3 supports text, vision, function_calling. As a budget-friendly model, it works well for high-volume tasks like classification, summarization, and simple generation. Use our Pricing Calculator to compare with alternatives.