mistralai Open weights Vision Reasoning

Mistral Small 4 pricing & benchmarks

Released Mar 16, 2026 · served by 2 providers

Input / 1M tokens$0.150
Output / 1M tokens$0.600
Context window262K
Cached input$0.015
Intelligence index19.6
Coding index26.6
Agentic index4.7
1M in + 300K out$0.33

What Mistral Small 4 is

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...

Providers and prices for Mistral Small 4

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Mistralcheapest $0.150 $0.600 262K 100.0%
Venice $0.188 $0.750 256K fp8 100.0%

Cheaper models in the same class

Models scoring within 4 points of Mistral Small 4 on the Intelligence Index, but with a lower output price.

FAQ

How much does the Mistral Small 4 API cost?

$0.150 per 1M input tokens and $0.600 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.33.

Is Mistral Small 4 free?

No. It is a paid model starting at $0.150 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Mistral Small 4?

Mistral at $0.150 input / $0.600 output per 1M tokens.

Can I self-host Mistral Small 4?

Yes — weights are published as mistralai/Mistral-Small-4-119B-2603 on Hugging Face, so you can run it on your own hardware.