Question 1

What is Codestral?

Accepted Answer

Codestral is a model from Mistral, released on May 29, 2024. Codestral 2508 is a Mistral AI model for coding, reasoning, instruction following, or multimodal language tasks.

Question 2

How much does Codestral cost?

Accepted Answer

On the Respan gateway, input starts at $0.30 per 1M tokens on every provider, and output starts at $0.90 per 1M tokens on OpenRouter, after gateway discounts.

Question 3

Which providers serve Codestral on Respan?

Accepted Answer

3 providers serve Codestral: OpenRouter and Mistral. Mistral require your own provider API key (BYOK).

Question 4

What is Codestral's context window?

Accepted Answer

Codestral accepts up to 256K tokens of context on its largest provider route.

Question 5

How do I use Codestral 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/codestral-2508". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Codestral?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 33 tokens per second, and the lowest response latency was 0.4 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

How does Codestral score on benchmarks?

Accepted Answer

Codestral has 1 published benchmark score, including HumanEval 86.6%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
OpenRouter`openrouter/mistralai/codestral-2508`	256K	$0.30/M	$0.90/M
MistralBYOK only`mistral/codestral-2508`	256K	$0.30/M	$0.90/M
MistralBYOK only`mistral/codestral-latest`	256K	$0.30/M	$0.90/M

Codestral

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Coding1

Apps

Codestral FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.