Mistral AI Models on XALEN
European AI lab building efficient open models. Strong function calling on XALEN.
Founded: 2023 · HQ: Paris, France · 5 models available
Available Models
Mistral Large 2
Open SourceMistral flagship with strong function calling and structured output.
Params: 123B
Context: 128K
Input: $0.06
Output: $0.10
Latency: ~400ms
Mistral Medium 3
Open SourceMid-tier model balancing quality and speed.
Params: 70B
Context: 128K
Input: $0.04
Output: $0.08
Latency: ~300ms
Mistral Small 3.1
CompactUpdated Mistral Small with better instruction following.
Params: 24B
Context: 128K
Input: $0.02
Output: $0.04
Latency: ~120ms
Mistral Small 3
CompactFast efficient model for simple faith-tech tasks.
Params: 24B
Context: 32K
Input: $0.02
Output: $0.04
Latency: ~150ms
Codestral
CodeCode-specialized model with 256K context.
Params: 22B
Context: 256K
Input: $0.03
Output: $0.05
Latency: ~200ms
Quick Start
import XALEN from 'xalen-sdk';
const client = new XALEN({ apiKey: 'xln_test_YOUR_KEY' });
const response = await client.chat.completions.create({
model: 'mistral-large-2',
messages: [{ role: 'user', content: 'Hello!' }]
});
Start Using Mistral AI Models
All models available through a single API. No separate accounts needed.
Get API KeyLast updated: 2026-05-21.