Compare AI models

Specifications
Parameters
119B30B
Context window
256k200k
API pricing
Input price
$0.15$0.00
Output price
$0.60$0.00
Cached input price
$0.015$0.00
Cheapest input
$0.15Mistral—
Cheapest output
$0.60Mistral—
$60.00Mistral list price$0.00Z.ai list price
Benchmarks
LiveCodeBench
63.6%64%
AIME 2025
83.8%91.6%
Overview
CompanyMistralZ.ai
Release dateMar 16 2026Jan 19 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

GLM-4.7-Flash leads Mistral Small 4 on 2 of the 2 benchmarks they both report (LiveCodeBench, AIME 2025). GLM-4.7-Flash is cheaper on both input and output: $0.00 vs $0.15 per million input tokens, and $0.00 vs $0.60 per million output tokens. GLM-4.7-Flash shipped 56 days before Mistral Small 4, so benchmark comparisons should account for the intervening progress.

Mistral Small 4 has 119B parameters, while GLM-4.7-Flash has 30B. Context windows are 256k (Mistral Small 4) vs 200k (GLM-4.7-Flash).

On LiveCodeBench, GLM-4.7-Flash leads at 64% vs Mistral Small 4 at 63.6%. On AIME 2025, GLM-4.7-Flash leads at 91.6% vs Mistral Small 4 at 83.8%.