Question 1

What is Mistral Small?

Accepted Answer

Mistral Small is a model from Mistral, released on Dec 11, 2023. The mistral-small model is a cost-efficient reasoning model designed for low-latency workloads. It leverages the Mixtral-8X7B-v0.1 architecture, which incorporates a sparse mixture of experts with 12B active parameters.

With improved reasoning capabilities, the model demonstrates a broad range of functionalities, including code generation and reasoning. It also supports multiple languages such as English, French, German, Italian, and Spanish, making it a versatile option for various linguistic tasks.

Question 2

How much does Mistral Small cost?

Accepted Answer

On the Respan gateway, input starts at $0.10 per 1M tokens on Google Vertex AI, and output starts at $0.30 per 1M tokens on Google Vertex AI, after gateway discounts. Averaged across 4 providers, it costs $0.14 per 1M input tokens and $0.53 per 1M output tokens.

Question 3

Which providers serve Mistral Small on Respan?

Accepted Answer

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

Question 4

What is Mistral Small's context window?

Accepted Answer

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

Question 5

How do I use Mistral Small 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-small-latest". 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 Small?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was Mistral at 108 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
Google Vertex AIBYOK only`vertex_ai/mistralai/mistral-small-2503`	131K	$0.10/M	$0.30/M
MistralBYOK only`mistral/mistral-small-2603`	262K	$0.15/M	$0.60/M
MistralBYOK only`mistral/mistral-small-latest`	262K	$0.15/M	$0.60/M
OpenRouter`openrouter/mistralai/mistral-small-2603`	262K	$0.15/M	$0.60/M

Mistral Small

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Time to first token

Response latency

Apps

Mistral Small FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.