Z.ai: GLM 5.2

Text input Text output
Author's Description

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

Key Specifications
Cost
$$$$$
Context
1M
Parameters
5.2B (Rumoured)
Released
Jun 16, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Frequency Penalty Logprobs Structured Outputs Min P Logit Bias Top Logprobs Reasoning Presence Penalty Stop Top P Response Format Include Reasoning Temperature Seed Max Tokens Tools Tool Choice
Features

This model supports the following features:

Tools Structured Outputs Reasoning Response Format
Performance Summary

Z.ai's GLM 5.2, a large-scale reasoning model with a 1M-token context window, generally exhibits longer response times, ranking in the 16th percentile for speed across benchmarks. Its pricing is moderate, placing it in the 25th percentile. A significant strength is its exceptional reliability, boasting a 97% success rate, indicating minimal technical failures. The model demonstrates perfect accuracy in the Hallucinations benchmark, effectively acknowledging uncertainty, and is noted as the most accurate model at its price point and speed for this category. It also shows strong performance in Instruction Following (82nd percentile accuracy) and Reasoning (75th percentile accuracy), suggesting proficiency in complex task execution and problem-solving. However, its General Knowledge accuracy is lower (28th percentile), and its performance in Mathematics (44th percentile) and Ethics (34th percentile) is average. Email Classification is solid at 97% accuracy. Overall, GLM 5.2 excels in reliability and specific reasoning tasks, making it suitable for long-horizon agent workflows, despite its slower processing speed and moderate general knowledge.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $1.2
Completion $4.1
Input Cache Read $0.2

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Wafer
Wafer | z-ai/glm-5.2-20260616 1M $1.2 / 1M tokens $4.1 / 1M tokens
DeepInfra
DeepInfra | z-ai/glm-5.2-20260616 1M $1.2 / 1M tokens $4.2 / 1M tokens
Phala
Phala | z-ai/glm-5.2-20260616 1M $1.4 / 1M tokens $4.4 / 1M tokens
Ambient
Ambient | z-ai/glm-5.2-20260616 202K $1.4 / 1M tokens $4.4 / 1M tokens
Cloudflare
Cloudflare | z-ai/glm-5.2-20260616 262K $1.4 / 1M tokens $4.4 / 1M tokens
Fireworks
Fireworks | z-ai/glm-5.2-20260616 1M $1.4 / 1M tokens $4.4 / 1M tokens
Z.AI
Z.AI | z-ai/glm-5.2-20260616 1M $1.4 / 1M tokens $4.4 / 1M tokens
Friendli
Friendli | z-ai/glm-5.2-20260616 1M $1.4 / 1M tokens $4.4 / 1M tokens
Parasail
Parasail | z-ai/glm-5.2-20260616 262K $1.4 / 1M tokens $4.4 / 1M tokens
Novita
Novita | z-ai/glm-5.2-20260616 1M $1.4 / 1M tokens $4.4 / 1M tokens
AtlasCloud
AtlasCloud | z-ai/glm-5.2-20260616 202K $1.4 / 1M tokens $4.4 / 1M tokens
StreamLake
StreamLake | z-ai/glm-5.2-20260616 1M $1.4 / 1M tokens $4.4 / 1M tokens
Io Net
Io Net | z-ai/glm-5.2-20260616 262K $1.68 / 1M tokens $5.28 / 1M tokens
Together
Together | z-ai/glm-5.2-20260616 262K $1.4 / 1M tokens $4.4 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by z-ai