Skip to content
LLMs
Mistral AI logo

Mistral: Mistral Small 4

by Mistral AI

Mistral: Mistral Small 4 is a large language model from Mistral AI. It costs $0.150 per million input tokens and $0.600 per million output tokens. Its context window is 262K tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tierOpen weightsimage input
Input / 1M tokens
$0.150
Output / 1M tokens
$0.600
Cached input / 1M
$0.015

On repeated prefixes

Context window
262K

tokens

Who serves it cheapest

2 hosts serve Mistral Small 4. Same weights, same API - the price difference is pure margin and routing.

Providers serving Mistral: Mistral Small 4, cheapest first
ProviderInput / 1MOutput / 1MContextThroughputUptime 24h
MistralCheapest$0.150$0.600262K-100.0%
Venicefp8$0.188$0.750256K-99.6%

The spread between Mistral and Venice is 1.3× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index
11.5
Coding index
26.6
Agentic index
1.4

About Mistral Small 4

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...

Specifications

Mistral: Mistral Small 4 specifications
Model IDmistralai/mistral-small-2603
ProviderMistral AI
Context window262K tokens
Max output210K tokens
Input modalitiestext, image
Output modalitiestext
Knowledge cutoff-
Open weightsYes - mistralai/Mistral-Small-4-119B-2603
ReleasedMarch 16, 2026

Cheaper alternatives

Models that cost less than Mistral Small 4 while keeping at least half its context window and every input modality it supports.

GLM 5.3 Flash

$0.150 in · $0.500 out

1.1× cheaper

Qwen3.8 Flash

$0.150 in · $0.470 out

1.1× cheaper

Qwen3 VL 8B Instruct

$0.117 in · $0.455 out

1.3× cheaper

Nemotron 3.5 Content Safety

$0.200 in · $0.200 out

1.3× cheaper

Ministral 3 14B 2512

$0.200 in · $0.200 out

1.3× cheaper

Frequently asked

How much does Mistral: Mistral Small 4 cost?

$0.150 per million input tokens and $0.600 per million output tokens. Cached input reads cost $0.015 per million tokens.

What is the context window of Mistral: Mistral Small 4?

262K tokens, with up to 210K tokens of output per request.

Which provider serves Mistral: Mistral Small 4 cheapest?

Mistral at $0.150 per million input tokens - 1.3× cheaper than Venice, the most expensive of the 2 hosts serving it.

Confirm against the source: Mistral AI official pricing.