Hormouz AIHormouzSign in

Z.ai: GLM 5: AI model

GLM 5 is Z.ai's flagship open-source foundation model, engineered for complex systems design and long-horizon agent workflows. Reachable from inside Iran through Hormouz.

Context window:
204,800 tokens
Input:
$0.6/1M tokens
Output:
$1.92/1M tokens
Type:
text
  • Tools
  • Streaming
  • Long context

Thinking levels:

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.

With advanced agentic planning, deep backend reasoning and iterative self-correction, GLM 5 moves beyond code generation to full-system construction and autonomous execution. Its roughly 200K-token context window suits large codebases and multi-step tasks. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs unchanged.

Pricing is usage-based: $1.2/M in · $3.5/M out. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

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...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorZ.ai
TypeText
Context window204,800 tokens
Pricing$0.60/M in · $1.92/M out
APIChat Completions
CapabilitiesStreaming · Tools

Benchmarks

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
82%
HLE
Humanity's Last Exam
29.3%
IFBench
Instruction-following
72.3%
AA-LCR
Long-context reasoning
75.7%
CritPt
Research-level physics reasoning
2%
AA Omniscience
Broad factual knowledge accuracy
26.3%
Non-Hallucination
Rate of avoiding fabricated answers
64.7%

Coding

Terminal-Bench Hard
Agentic coding & terminal use
43.2%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
98.2%

Source: Artificial Analysis

Ranking distribution

First
12,022
Second
11,409
Third
5,439
Fourth
3,234

32104 tournaments ?

Android Native
Top 65%
1,161Elo
Win rate: 55.1%
Full-Stack
Top 64%
1,121Elo
Win rate: 51.7%
Godot Game Dev
Top 58%
1,144Elo
Win rate: 46.7%
HTML Slides
Top 78%
1,147Elo
Win rate: 45.1%Avg time: 366s
Mobile Apps
Top 72%
1,133Elo
Win rate: 51.6%
3D
Top 26%
1,239Elo
Win rate: 56.3%Avg time: 135s
ASCII Art
Top 55%
1,158Elo
Win rate: 47.9%Avg time: 83.3s
Code
Top 24%
1,252Elo
Win rate: 55.5%Avg time: 197s
Data Viz
Top 29%
1,237Elo
Win rate: 53%Avg time: 150s
Game Dev
Top 24%
1,247Elo
Win rate: 57.4%Avg time: 190s
SVG
Top 37%
1,167Elo
Win rate: 54.4%Avg time: 57.0s
UI Component
Top 32%
1,237Elo
Win rate: 53.6%Avg time: 161s
Website
Top 25%
1,254Elo
Win rate: 55%Avg time: 233s

Metrics sourced from Design Arena

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="z-ai/glm-5",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "z-ai/glm-5",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Z.ai: GLM 5 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Z.ai: GLM 5 and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does GLM 5 cost?
Billing is usage-based: $1.2/M in · $3.5/M out. There is no fixed monthly fee. You pay only for what you use.
How do I use GLM 5 from inside Iran?
Create a Hormouz account and generate an API key. Hormouz gives you a stable route to the model from inside Iran, with no foreign credit card or circumvention tooling needed.
Is GLM 5 OpenAI-compatible?
Yes. Hormouz serves an OpenAI-compatible API. Point your base URL at Hormouz and swap in a Hormouz key; your existing SDKs and code work without a rewrite.
What is GLM 5 good for?
Complex systems design, large-scale programming, agentic planning and long-horizon workflows that need deep reasoning.
How does GLM 5 differ from prior generations?
It is the new-generation flagship, focused on full-system construction, iterative self-correction and autonomous execution rather than just code generation.
Does GLM 5 support tool calling?
Yes. It supports tool calling and is a fit for agent frameworks.

Updated 2026-10-13