DevTk.AI

Mistral Small 4

Mistral

Mistral Small 4 by Mistral: $0.15/M cache-miss input, $0.6/M output tokens. Cached input: $0.015/M. 256K context, 33K max output. Vision & Function Calling. Price verified 2026-11-18.

Input Price

$0.15

cache miss / 1M tokens

Cached Input

$0.015

per 1M tokens

Output Price

$0.6

per 1M tokens

Context Window

256K

tokens

Mistral Small 4 price history

No price changes recorded for Mistral Small 4 in our AI API price change log (earliest entry: 2026-05-27). Current rates last verified against the official Mistral pricing page on 2026-11-18. See all AI API price changes

Specifications

ProviderMistral
Model IDmistral-small-2603
Input Price$0.15 / 1M cache-miss tokens
Cached Input Price$0.015 / 1M tokens
Output Price$0.6 / 1M tokens
Context Window256K tokens
Max Output33K tokens
Capabilities
textvisionfunction_callingstructured_output
Release Date2026-03-16
Pricing SourceOfficial Mistral pricing
Price Verified2026-11-18
NotesCurrent low-cost Mistral model for high-volume production routing. 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 $0.1125 $1.35
50K $0.5625 $6.75
100K $1.13 $13.50
500K $5.63 $67.50
1.0M $11.25 $135.00

How Mistral Small 4 Pricing Compares

Standard cache-miss input / output prices per 1M tokens, compared with active, price-verified models priced in USD. Cached, batch and long-context rates are not included.

  • Within Mistral: 1 of 5 other active Mistral models has a lower input price, and 3 have a lower output price.
  • Similar context window: among the 21 active models with a 128K–512K token context window, Mistral Small 4 ranks #8 from cheapest at a 50/50 input/output mix. Cheapest: GLM-4.7-Flash ($0.00/$0.00). Most expensive: Jamba Large 1.7 ($2.00/$8.00).
  • Versus the previous release: compared with Mistral Small 3.1 (released 2025-03, $0.2/$0.6), input is -25% and output is unchanged.

Use our Token Counter to estimate how many tokens your prompts use, and our Pricing Calculator to compare costs across all models.

Mistral Small 4 Key Details

  • Pricing: $0.15/M cache-miss input tokens, $0.015/M cached input tokens, $0.6/M output tokens
  • Context window: 256K tokens — 74 of 90 active models we track have a larger window
  • Max output: 33K tokens per response
  • Capabilities: text, vision, function_calling, structured_output
  • Highlights: Current low-cost Mistral model for high-volume production routing. Mistral lists a 90% discount for cached input tokens.
  • Released: 2026-03-16

Other Mistral Models

Similar Price Range

Related Tools

FAQ

How much does Mistral Small 4 cost?

Mistral Small 4 costs $0.15 per million cache-miss input tokens and $0.6 per million output tokens. Cached input costs $0.015 per million tokens. For a typical workload of 100K input tokens/day and 50K output tokens/day, expect approximately $1.35/month before cache-hit savings.

What is Mistral Small 4's context window?

Mistral Small 4 supports a context window of 256K tokens. This means your combined input prompt and output response can be up to 256K tokens. The maximum output per response is 33K tokens.

Is Mistral Small 4 good for my use case?

Mistral Small 4 supports text, vision, function_calling, structured_output. We track pricing and limits, not output quality, so test it on your own prompts before committing. The price comparison above lists cheaper and pricier models with a similar context window, and the Pricing Calculator estimates your monthly cost across all of them.