mistralai/magistral-2

Transparent reasoning model with visible planning.

TextReasoningreasoningtools

Specifications

Context window: 128K
Max output tokens: 40,000
Released: 2025-12
Infra providers: 3
Throughput: 104 tok/s
Latency (TTFB, sample): 690 ms
Capabilities: Supports tools

Pricing

per million tokens

Input

$2.00

Output

$5.00

Blended (3:1)

$2.75

Use this model

Works with any OpenAI SDK — same request shape, different model id.

curl https://api.lokarouter.id/v1/chat/completions \  -H "Authorization: Bearer sk-lkr-your-key" \  -H "Content-Type: application/json" \  -d '{    "model": "mistralai/magistral-2",    "messages": [{ "role": "user", "content": "Hello" }]  }'

Sample data for demonstration — connect your workspace for live stats.