Mistral AI

Mistral Small 24B Instruct 2501 API Pricing 2026

Compare pricing, benchmarks, and providers for Mistral Small 24B Instruct 2501. 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 24B Instruct 2501 was released on January 30, 2025. Pricing starts at $0.040 per million input tokens and $0.064 per million output tokens. The model supports a context window of up to 33K tokens. API access is available through Mistral AI.

Context Window
33K
tokens
Pricing
Input$0.040
Output$0.064
Cached$0.450
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
Tools

Mistral Small 24B Instruct 2501 is priced at $0.040 per million input tokens and $0.064 per million output tokens. It has a context window of 32,768 tokens. It is available from 3 providers, with DeepInfra the cheapest at $0.040 per million input tokens (input prices range from $0.040 to $0.900). Over the past ~90 days its cheapest input price has fallen 20%, from $0.050 to $0.040 per million tokens.

Pricing Comparison

Compare Mistral Small 24B Instruct 2501 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
$0.040
$0.064
—
—
—
32,768
Try
$0.030
$0.120
—
—
—
32,768
Try
$0.030
$0.130
—
—
—
1,000,000
Try
$0.030
$0.150
—
—
—
128,000
Try
$0.033
$0.130
—
—
—
131,072
Try
$0.035
$0.000
—
—
—
-
Try
$0.035
$0.140
—
—
—
128,000
Try
$0.035
$0.900
—
—
81.8
1,000,000
Try
$0.037
$0.150
—
—
—
128,000
Try
$0.040
$0.078
—
—
91.2
1,048,575
Try
$0.040
$0.080
—
—
—
131,072
Try

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

Compare Providers

Mistral Small 24B Instruct 2501 is available from multiple providers with different pricing and availability.

3
Providers
$0.040
Cheapest Input/M
$0.064
Cheapest Output/M
DeepInfra
Best Price

Provider Pricing

3 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
$0.040
$0.064
-
-
-
$0.050
$0.080
-
-
-
$0.900
$0.900
$0.450
-
-
Provider pricing data sourced from OpenRouter and Helicone

Community Rankings

How does Mistral Small 24B Instruct 2501 perform? Vote based on your experience.

Cost vs. Quality

Compare Mistral Small 24B Instruct 2501's benchmark performance against all models.

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

Try Mistral Small 24B Instruct 2501

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Mistral Small 24B Instruct 2501 directly in your browser.

Open Playground

Frequently Asked Questions

Mistral Small 24B Instruct 2501 costs $0.000040 per 1,000 input tokens and $0.000064 per 1,000 output tokens.
Mistral Small 24B Instruct 2501 is available from 3 providers. DeepInfra offers the best price.
DeepInfra offers Mistral Small 24B Instruct 2501 at $0.040 per million input tokens, the lowest of 3 providers (input prices range from $0.040 to $0.900 per million tokens).
Yes. Over the past ~90 days, the cheapest input price for Mistral Small 24B Instruct 2501 has dropped 20%, from $0.050 to $0.040 per million tokens.
We compare Mistral Small 24B Instruct 2501 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 →