Question 1

What is Mistral Large?

Accepted Answer

Mistral Large is a model from Mistral, released on Feb 26, 2024. Mistral AI's flagship model, renowned for tackling high-complexity tasks with top-tier reasoning capabilities. Expertise extends to various domains, such as reasoning, code, JSON, and chat applications.

Fluent in multiple languages, including English, French, Spanish, German, and Italian, boasting high grammatical accuracy. With a 32K tokens context window, it excels at precise information recall from extensive documents.

Question 2

How much does Mistral Large cost?

Accepted Answer

On the Respan gateway, input starts at $0.50 per 1M tokens on OpenRouter, and output starts at $1.50 per 1M tokens on OpenRouter, after gateway discounts. Averaged across 3 providers, it costs $1.50 per 1M input tokens and $4.50 per 1M output tokens.

Question 3

Which providers serve Mistral Large on Respan?

Accepted Answer

3 providers serve Mistral Large: OpenRouter.

Question 4

What is Mistral Large's context window?

Accepted Answer

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

Question 5

How do I use Mistral Large 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-large". 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 Large?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 24 tokens per second, and the lowest response latency was 0.6 seconds on OpenRouter. Speed varies with request size and provider.

Provider	Context	Input	Output
OpenRouter`openrouter/mistralai/mistral-large-2512`	262K	$0.50/M	$1.50/M
OpenRouter`openrouter/mistralai/mistral-large`	128K	$2.00/M	$6.00/M
OpenRouter`openrouter/mistralai/mistral-large-2407`	131K	$2.00/M	$6.00/M

Mistral Large

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps

Mistral Large FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.