Mistral AI

Mistral Small 3.2 24B API Pricing 2026

Compare pricing, benchmarks, and providers for Mistral Small 3.2 24B. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Mistral Small 3.2 24B was released on June 20, 2025. Pricing starts at $0.075 per million input tokens and $0.200 per million output tokens. The model supports a context window of up to 131K tokens. API access is available through Mistral AI.

Context Window
131K
tokens
Pricing
Input$0.075
Output$0.200
Cached$0.050
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
VisionToolsCaching

Mistral Small 3.2 24B is priced at $0.075 per million input tokens and $0.200 per million output tokens. It has a context window of 131,072 tokens. It is available from 5 providers, with DeepInfra the cheapest at $0.075 per million input tokens (input prices range from $0.075 to $0.500).

Pricing Comparison

Compare Mistral Small 3.2 24B with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.075
$0.200
—
—
—
131,072
Try
$0.070
$0.070
—
—
—
8,192
Try
$0.070
$0.350
—
—
—
32,000
Try
$0.070
$0.140
—
47.6
20.8
16,384
Try
$0.074
$0.295
—
—
—
8,192
Try
$0.074
$0.295
—
—
—
8,192
Try
$0.075
$0.400
—
—
—
1,000,000
Try
$0.075
$0.400
—
—
—
262,144
Try
$0.075
$0.625
—
—
—
262,144
Try
$0.075
$0.625
—
—
—
262,144
Try
$0.075
$0.300
—
—
—
262,144
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Mistral Small 3.2 24B is available from multiple providers with different pricing and availability.

5
Providers
$0.075
Cheapest Input/M
$0.200
Cheapest Output/M
DeepInfra
Best Price

Provider Pricing

5 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Input $/M
Output $/M
Cache Read $/M
Cache Write $/M
Uptime
DeepInfra
DeepInfra
Best Price
$0.075
$0.200
-
-
100.0%
OpenRouter
OpenRouter
Best Price
$0.075
$0.200
-
-
-
$0.090
$0.300
$0.050
-
89.7%
V
Venice
$0.094
$0.250
-
-
100.0%
$0.500
$1.500
-
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Mistral Small 3.2 24B perform? Vote based on your experience.

Cost vs. Quality

Compare Mistral Small 3.2 24B's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Try Mistral Small 3.2 24B

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Mistral Small 3.2 24B directly in your browser.

Open Playground

Frequently Asked Questions

Mistral Small 3.2 24B costs $0.000075 per 1,000 input tokens and $0.000200 per 1,000 output tokens.
Mistral Small 3.2 24B is available from 5 providers. DeepInfra offers the best price.
DeepInfra offers Mistral Small 3.2 24B at $0.075 per million input tokens, the lowest of 5 providers (input prices range from $0.075 to $0.500 per million tokens).
We compare Mistral Small 3.2 24B with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Mistral AI Models

See pricing for all Mistral AI models.

View all Mistral AI models →