ZMIME
Z.ai (Zhipu) · Released Feb 12, 2026

GLM-5

General GLM flagship for coding, analysis, and tool-heavy engineering workflows.

  • Open weights
  • Reasoning
  • Tool calling
Capability
145.8ECI · #74 of 148
Input
$1.00per 1M tokens
Output
$3.20per 1M tokens
Context
205K131K max output
Pricing

What it costs

Input
$1.00per million tokens
Output
$3.20per million tokens
Cached input
$0.20per million tokens
Blended (3:1)
$1.55pricier than 64% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$3.60
Team assistant25M input + 5M output tokens$41.00
Production app250M input + 50M output tokens$410.00

Official Z.AI API price, as listed on models.dev.

Capability

Independent benchmarks

145.8Epoch Capabilities Index
#74 of 148 scored models
88Median 146167

The shaded band is Epoch AI’s confidence range (143.9–147.7); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions87.8%
  • OTIS Mock AIME 2024–2025Competition mathematics80.0%
  • SWE-bench VerifiedFixing real GitHub issues72.1%

Scores from Epoch AI, run independently of Z.ai (Zhipu).

Specifications

The details

Lab
Z.ai (Zhipu)
Released
Feb 12, 2026
Context window
204,800 tokens
Max output
131,072 tokens
Inputs
Text
Output
Text
Reasoning
Can be switched on or off
Tool calling
Yes
Structured output
No
API model ID
glm-5on Z.AI
Availability
27 API providerslisted on models.dev

Z.AI model documentation

Lab-reported

What Z.ai (Zhipu) claims

Published by the lab at launch. Settings vary, so compare these only with care.

BenchmarkScoreSettingSource
SWE-Bench Verified72.8 resolved—Source
SWE-Atlas Codebase QnA20.5—Source
SWE-Atlas Refactoring24.24—Source
SWE-Atlas Test Writing28.74—Source
Same lab

More from Z.ai (Zhipu)

Questions

About GLM-5

How much does GLM-5 cost?

GLM-5 costs $1.00 input / $3.20 output per million tokens (official Z.AI API price). Cached input is $0.20 per million tokens. At a 3:1 input-to-output mix that is $1.55 per million tokens, more expensive than 64% of the 360 priced models we track.

What is the context window of GLM-5?

GLM-5 accepts up to 204,800 tokens per request and can write up to 131,072 tokens in one response.

How good is GLM-5?

Epoch AI gives GLM-5 a Capabilities Index score of 145.8 (likely range 143.9–147.7), ranking it #74 of 148 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 87.8%, OTIS Mock AIME 2024–2025 80.0%, SWE-bench Verified 72.1%.

Is GLM-5 open source?

Yes. Z.ai (Zhipu) publishes the weights, so it can be downloaded and self-hosted.

What inputs does GLM-5 support?

GLM-5 accepts text and replies in text. It is a reasoning model, supports tool calling.

When was GLM-5 released?

Z.ai (Zhipu) released GLM-5 on Feb 12, 2026.

What are the best alternatives to GLM-5?

The closest current models from other labs on capability, price and release date are Qwen3.5 397B-A17B (Alibaba (Qwen), ECI 146.7, $0.60 / $3.60), Kimi K2 Thinking (Moonshot AI, ECI 146.0, $0.60 / $2.50), GPT-5.4 mini (OpenAI, ECI 148.8, $0.75 / $4.50) and Nemotron 3 Ultra 550B A55B (NVIDIA, ECI 146.2, $0.50 / $2.50).