Z.ai: GLM 5

Text input Text output
Author's Description

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-grade performance on large-scale programming tasks, rivaling leading...

Key Specifications
Cost
$$$$$
Context
202K
Released
Feb 11, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

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

This model supports the following features:

Tools Reasoning Structured Outputs Response Format
Performance Summary

Z.ai's GLM-5, a flagship open-source foundation model, demonstrates a strong focus on complex systems design and long-horizon agent workflows. While its speed performance tends to be slower, ranking in the 7th percentile, and its pricing is positioned at premium levels (11th percentile), the model exhibits exceptional reliability with a 95% success rate across benchmarks, indicating minimal technical failures. GLM-5 excels in several key areas. It shows strong performance in Instruction Following (84th percentile accuracy), Reasoning (77th percentile accuracy), and Mathematics (75th percentile accuracy), highlighting its capabilities for intricate problem-solving and precise execution of multi-step directives. Its General Knowledge and Ethics scores are also commendable at 98.9% and 99.0% accuracy respectively, suggesting a broad understanding and adherence to ethical principles. A notable weakness is its performance in Hallucinations, where it scores 80.0% accuracy (24th percentile), indicating a tendency to provide answers for fictional concepts rather than acknowledging uncertainty. Its Coding performance is solid at 87.9% accuracy (58th percentile), making it suitable for large-scale programming tasks.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.95
Completion $3.15
Input Cache Read $0.19

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
AtlasCloud
AtlasCloud | z-ai/glm-5-20260211 202K $0.95 / 1M tokens $3.15 / 1M tokens
Novita
Novita | z-ai/glm-5-20260211 202K $1 / 1M tokens $3.2 / 1M tokens
Z.AI
Z.AI | z-ai/glm-5-20260211 202K $1 / 1M tokens $3.2 / 1M tokens
Phala
Phala | z-ai/glm-5-20260211 202K $1.2 / 1M tokens $3.5 / 1M tokens
GMICloud
GMICloud | z-ai/glm-5-20260211 202K $0.6 / 1M tokens $1.92 / 1M tokens
Parasail
Parasail | z-ai/glm-5-20260211 202K $1 / 1M tokens $3.2 / 1M tokens
Friendli
Friendli | z-ai/glm-5-20260211 202K $1 / 1M tokens $3.2 / 1M tokens
Venice
Venice | z-ai/glm-5-20260211 198K $1 / 1M tokens $3.2 / 1M tokens
Fireworks
Fireworks | z-ai/glm-5-20260211 202K $1 / 1M tokens $3.2 / 1M tokens
Together
Together | z-ai/glm-5-20260211 202K $1 / 1M tokens $3.2 / 1M tokens
SiliconFlow
SiliconFlow | z-ai/glm-5-20260211 204K $0.95 / 1M tokens $2.55 / 1M tokens
DeepInfra
DeepInfra | z-ai/glm-5-20260211 202K $0.6 / 1M tokens $2.08 / 1M tokens
Ambient
Ambient | z-ai/glm-5-20260211 202K $0.6 / 1M tokens $1.92 / 1M tokens
Io Net
Io Net | z-ai/glm-5-20260211 202K $0.6 / 1M tokens $1.92 / 1M tokens
BaseTen
BaseTen | z-ai/glm-5-20260211 202K $0.95 / 1M tokens $3.15 / 1M tokens
Venice
Venice | z-ai/glm-5-20260211 198K $0.6 / 1M tokens $1.92 / 1M tokens
StreamLake
StreamLake | z-ai/glm-5-20260211 200K $0.65 / 1M tokens $2.08 / 1M tokens
Chutes
Chutes | z-ai/glm-5-20260211 202K $0.95 / 1M tokens $2.55 / 1M tokens
Nebius
Nebius | z-ai/glm-5-20260211 202K $0.6 / 1M tokens $1.92 / 1M tokens
Amazon Bedrock
Amazon Bedrock | z-ai/glm-5-20260211 202K $1 / 1M tokens $3.2 / 1M tokens
Baidu
Baidu | z-ai/glm-5-20260211 202K $0.7 / 1M tokens $2.24 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by z-ai