Question 1

What is Mistral Small 4?

Accepted Answer

Mistral Small 4 is a model from Mistral, released on Mar 16, 2026. Mistral Small 4 is a Mistral model focused on efficient inference for chat, coding, and structured generation tasks. Mistral Small 4 is a Mistral model focused on efficient inference for chat, coding, and structured generation tasks. Supports tool use. Up to 256K context window.

Question 2

How much does Mistral Small 4 cost?

Accepted Answer

On the Respan gateway, input starts at $0.15 per 1M tokens on EmpirioLabs, and output starts at $0.60 per 1M tokens on EmpirioLabs, after gateway discounts.

Question 3

Which providers serve Mistral Small 4 on Respan?

Accepted Answer

Mistral Small 4 is served by EmpirioLabs.

Question 4

What is Mistral Small 4's context window?

Accepted Answer

Mistral Small 4 accepts up to 256K tokens of context.

Question 5

How do I use Mistral Small 4 with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "mistral-small-4". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How does Mistral Small 4 score on benchmarks?

Accepted Answer

Mistral Small 4 has 3 published benchmark scores, including GPQA Diamond 71.2% and MMLU-Pro 78%. Each score links to where it was published; the data is collected by llmmetric.com.

Mistral Small 4

Providers

Pricing

Cost by volume

Benchmarks

Certified where it counts.

Reasoning2

Knowledge1

Apps

Mistral Small 4 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.