Question 1

What is Mistral Medium 3?

Accepted Answer

Mistral Medium 3 is a model from Mistral, released on May 7, 2025. Mistral Medium 3 is a Mistral AI model for coding, reasoning, instruction following, or multimodal language tasks.

Question 2

How much does Mistral Medium 3 cost?

Accepted Answer

On the Respan gateway, input starts at $0.40 per 1M tokens on OpenRouter, and output starts at $2.00 per 1M tokens on every provider, after gateway discounts. Averaged across 3 providers, it costs $0.40 per 1M input tokens and $2.00 per 1M output tokens.

Question 3

Which providers serve Mistral Medium 3 on Respan?

Accepted Answer

3 providers serve Mistral Medium 3: OpenRouter, Mistral, and Google Vertex AI. Mistral and Google Vertex AI require your own provider API key (BYOK).

Question 4

What is Mistral Medium 3's context window?

Accepted Answer

Mistral Medium 3 accepts up to 262K tokens of context on its largest provider route.

Question 5

How do I use Mistral Medium 3 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/mistral-medium-3". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Mistral Medium 3?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Mistral at 31 tokens per second, and the lowest response latency was 0.4 seconds on Mistral. Speed varies with request size and provider.

Provider	Context	Input	Output
OpenRouter`openrouter/mistralai/mistral-medium-3`	131K	$0.40/M	$2.00/M
MistralBYOK only`mistral/mistral-medium-3`	262K	$0.40/M	$2.00/M
Google Vertex AIBYOK only`vertex_ai/mistralai/mistral-medium-3`	131K	$0.40/M	$2.00/M

Mistral Medium 3

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps

Mistral Medium 3 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.