How do I use GLM 5 through YepAPI?

Sign up for a free API key, then send requests to the /v1/ai/chat endpoint.

Z.aiText Generation/v1/ai/chat

GLM 5

Access GLM 5 through one API key. Balanced bilingual model from Zhipu AI.

Zhipu AI's balanced model. Good performance across Chinese and English tasks at a lower price.

Full Docs Get API Key — Free $5 Credit

No credit card required. Takes 30 seconds.

2,400+

Developers

1.2M+

API calls served

100+

Endpoints

$0.01

Per call

Yep, that's it.

Try it live

Send a message and see GLM 5 respond in real time.

POST/v1/ai/chatz-ai/glm-5

Message *

Max Tokens

Maximum tokens in the response.

Stream

Real-time tokens

Hit "Send Request" to see the response

Context Window

80K tokens

Max Output

131K tokens

Input Price

$1.01 / 1M tokens

Output Price

$3.22 / 1M tokens

Strengths

✓

Bilingual CN/EN

GLM 5 delivers solid Chinese and English performance from Zhipu AI, suited to cross-language tasks at a lower price than the flagship line.

✓

131K output

A 131,072-token maximum output lets GLM 5 produce long documents and detailed responses in a single call.

✓

Competitive pricing

At $1.01 per 1M input and $3.22 per 1M output tokens, it offers balanced bilingual quality below GLM 5.1 and 5.2 pricing.

✓

General purpose

An 80,000-token context window and balanced tuning make it a well-rounded default for everyday reasoning, writing, and coding.

Quick start

Copy this snippet and start making calls with GLM 5.

const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    "model": "z-ai/glm-5",
    "messages": [
      {
        "role": "user",
        "content": "Explain API gateways in 2 sentences."
      }
    ],
    "maxTokens": 256
  }),
});
const { data } = await res.json();
console.log(data.message.content);

Why use GLM 5 through YepAPI?

✓One API key for all models — no separate accounts

✓OpenAI SDK compatible — just change the base URL

✓No monthly minimums — pay per token

✓Switch models with one line of code

✓Full provider passthrough — citations, search results, and all extras included

✓Streaming and non-streaming support on every model

✓Works with Cursor, Claude, LangChain, and any LLM tool

✓Unified billing across all providers

GLM 5 API: balanced bilingual model from Zhipu AI

GLM 5 is Zhipu AI's balanced general-purpose model, offering solid Chinese-English performance at a lower price than the newer GLM 5.1 and 5.2.

On YepAPI you access GLM 5 through one OpenAI-compatible endpoint at $1.01 per 1M input and $3.22 per 1M output tokens, with an 80,000-token context window.

What is GLM 5?

GLM 5 is the balanced, everyday model in Zhipu AI's GLM family. It is positioned below the flagship GLM 5.1 and 5.2 on price while still delivering good performance across Chinese and English tasks, making it a practical default for general work. The model carries an 80,000-token context window and a large 131,072-token output ceiling, so although its input window is smaller than the flagship tiers, it can still generate long, complete responses. GLM 5 is built for teams that want dependable bilingual quality for routine reasoning, writing, and coding without paying flagship rates for capability they may not need on every call.

Build with GLM 5 via YepAPI

Call GLM 5 through YepAPI's OpenAI-compatible /v1/ai/chat endpoint. Point your OpenAI SDK at YepAPI and set the model string to glm-5; switching to a flagship GLM or any other model later is a one-string edit. A single YepAPI key also reaches every other model plus SEO, SERP, and web-scraping tools, so you can default to GLM 5 for general traffic and escalate harder bilingual or agentic tasks to GLM 5.2 without changing keys.

GLM 5 API pricing — $1.01 / $3.22 per 1M tokens

GLM 5 costs $1.01 per 1M input tokens and $3.22 per 1M output tokens on YepAPI. That sits clearly below GLM 5.1 and 5.2, making GLM 5 the cost-efficient member of the family for general-purpose use. The large 131K output ceiling means long generations are still possible, and because your key spans the whole GLM line, you can reserve the pricier flagship models for the tasks that truly need them.

GLM 5 for general-purpose bilingual work

GLM 5 suits everyday bilingual workloads: writing technical guides, answering general questions, drafting content, and producing code in Chinese or English where balanced quality matters more than peak capability. The 131,072-token output supports long documents in one response, and the competitive pricing makes it economical for steady traffic. It is the sensible workhorse tier when you want reliable GLM quality at a lower cost than the flagship models.

Try GLM 5 free

New YepAPI accounts get $5 in free credit with no card required. Use it to test GLM 5 on your general bilingual tasks and compare its quality and cost against the flagship GLM tiers before deciding where to route traffic.