mistralai

Mistral: Mistral Small 4

Mistral Small 4 from MistralAI is designed for handling both text and image inputs with a context length of up to 262,144 tokens, making it suitable for complex tasks that require extensive contextual understanding. The model supports tools and reasoning, allowing for more dynamic interactions and problem-solving capabilities. This model stands as a solid choice for those looking for a reliable solution within its price range, offering $0.15 per million input tokens and $0.6 per million output tokens. With a blended benchmark score of 5.6 across one independent evaluation, it provides a balanced performance that justifies its cost, making it a reasonable option for businesses or projects seeking efficient AI assistance without overpaying.

Quality Score
100/100
price + capability + benchmarks
Input Price
$0.15
per 1M tokens
Output Price
$0.60
per 1M tokens
Context Window
262,144
tokens

Benchmark results

Independent, published benchmarks. Blended score 5.6 across 1 benchmark, last refreshed 2026-08-13. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 7.1
Model ID
mistralai/mistral-small-2603
Vendor
mistralai
Released
March 2026
Tokenizer
Mistral
Input Modalities
text, image
Output Modalities
text
Max Output
default
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
✓ accepts images
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.15/M input and $0.60/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.10
A month of a busy support chatbot 5M in / 2M out $1.95

Category rankings

Where Mistral: Mistral Small 4 places across the 1 category it ranks in. How we rank →

#CategoryScore
#23 Self-Hosted / LocalCost · of 25 ranked 117

Similar models

Quick answers

How much does Mistral: Mistral Small 4 cost?
$0.15 per million input tokens and $0.60 per million output tokens.
What is Mistral: Mistral Small 4's context window?
262,144 tokens, roughly 393 pages of text in a single request.
Does Mistral: Mistral Small 4 support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can Mistral: Mistral Small 4 process images?
Yes, it accepts image input.