Back to Models

Magistral Small 2506

Specialized Mistral model variant designed for specific enterprise use cases

Parameters
N/A
Context
32,768 tokens
Released
Jun 1, 2025

Leaderboards

Performance vs. Industry Average

Intelligence

Magistral Small 2506 is of lower intelligence compared to average (4.1), with an intelligence score of 3.7.

Price

Magistral Small 2506 is cheaper compared to average ($0.91 per 1M Tokens) with a price of $0.20 per 1M Tokens.

Latency

Magistral Small 2506 has a lower average latency compared to average (45.24s), with an average latency of 17.54s.

P99 Latency

Magistral Small 2506 has a lower P99 latency compared to average (172.60s), taking 89.52s to receive the first token at P99 (TTFT).

Context Window

Magistral Small 2506 has a smaller context window than average (246k tokens), with a context window of 33k tokens.

Magistral Small 2506 - AutoBench