Mistral Small 4

Last verified August 24, 2026 · Mistral pricing ↗

$0.150/1M input · $0.600/1M output · 256K context · Mistral

Mistral Small 4 costs $0.150 per 1M input tokens and $0.600 per 1M output tokens from Mistral, with a 256K-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0005, or $4.65 per 10,000 requests. On that workload it is cheaper than 133 of the 168 other buyable models tracked here.

budgetmultilingualEU-compliancespeed

When to use Mistral Small 4

Compact European model from Mistral. Good for multilingual tasks and EU data residency requirements. Fast and affordable.

Strong multilingual support
EU-based provider (data residency)
Fast inference
Low cost per input token

Count Tokens

Tokens

—

Input Cost

—

Output Cost

—

Tokens

—

Input Cost

—

Output Cost

Estimate Monthly Cost

Monthly Cost Estimator

Quick:

API calls / dayAvg input tokens / callAvg output tokens / call

<$0.0001/mo

Pick a preset above or enter custom usage

What Mistral Small 4 Costs Per Request

At $0.150 per 1M input and $0.600 per 1M output tokens, before caching or batch discounts.

Workload	Input / output tokens	Per request	Per 10,000 requests
Chat reply	1,500 / 400	$0.0005	$4.65
RAG answer over retrieved docs	8,000 / 600	$0.0016	$15.60
Coding-agent step	30,000 / 2,000	$0.0057	$57.00

Mistral Small 4 vs Similarly Priced Models

Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.

Model	Input /1M	Output /1M	Context	RAG answer
Mistral Small 4 Mistral	$0.150	$0.600	256K	$0.0016
Ministral 3 14B Mistral	$0.200	$0.200	262K	$0.0017
GPT-OSS 120B (Bedrock) OpenAI	$0.150	$0.600	16K	$0.0016
DeepSeek V4.1 Flash DeepSeek	$0.150	$0.600	1.0M	$0.0016

Alternatives to Mistral Small 4

Cheaper Alternative

Hy3

$0.132 in · $0.528 out · Tencent

12% cheaper with same or larger context

Premium Upgrade

Hunyuan HY3 Preview

$0.178 in · $0.595 out · Tencent

Upgrade with 262K context

Same Provider

Ministral 3 14B

$0.200 in · $0.200 out · Mistral

47% cheaper in Mistral ecosystem

Pricing Details

Mistral119B MoE, 6.5B active params. Multimodal (text+image). Configurable reasoning_effort. Apache 2.0. API ID: mistral-small-2603.

Input / 1M tokens

$0.15

Output / 1M tokens

$0.6

Context Window

256K

Max Output

33K

Full Pricing Table Token Calculator

Price History

No price change recorded since 2026-07-27, when this site started tracking this model.

Frequently Asked Questions

Common questions about Mistral Small 4 pricing and usage

How much does Mistral Small 4 cost?

Mistral Small 4 costs $0.15 per 1 million input tokens and $0.6 per 1 million output tokens. This pricing is set by Mistral.

What tokenizer does Mistral Small 4 use?

Mistral Small 4 uses the cl100k_base tokenizer. This tokenizer has a vocabulary of ~100,000 tokens and is widely used across many models.

What is Mistral Small 4's context window?

Mistral Small 4 supports a context window of 256K tokens (256,000 tokens). The maximum output length is 33K tokens.

How does Mistral Small 4 compare to other models?

On an 8,000-token-in, 600-token-out RAG answer, Mistral Small 4 costs $0.0016 per request. The nearest-priced alternatives cost: Ministral 3 14B (Mistral) $0.0017, GPT-OSS 120B (Bedrock) (OpenAI) $0.0016, DeepSeek V4.1 Flash (DeepSeek) $0.0016. The table above lists their full rates and context windows.

How do I count tokens for Mistral Small 4?

Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for Mistral Small 4 using the cl100k_base tokenizer.