GLM API: Zhipu's three models and how to connect

GLM is Zhipu AI’s model family. It’s prized for value: capable models at a noticeably lower per-token cost, confident multilingual behavior (Russian, English, Chinese), and a dedicated model that reads images. Through RuAPI you get three IDs — a flagship, a fast turbo, and a vision variant. Below: which to pick per task, and how to connect.

The three GLM models

Model	Best for	Notes
GLM-5.2	The hardest tasks: reasoning, code, agents, long context	Flagship, top quality; use it when the result matters more than the price
GLM-5-Turbo	Everyday work and high volume: chat, code, general tasks	Fast, cheap all-rounder; the default choice
GLM-5V-Turbo	Reading images alongside text	Vision model: screenshots, photos, diagrams, charts; also fast

Not sure? Start with GLM-5-Turbo — it covers most work fast and cheap. Move up to GLM-5.2 when you need the best quality, and reach for GLM-5V-Turbo only when you actually pass an image.

Strong across languages

A key trait of GLM is confident multilingual coverage. The models handle Russian, English and Chinese equally well, which makes the family handy for mixed-language content: a Russian-language chatbot, translation, or parsing documents in several languages. The GLM-5.2 flagship gives the most even quality on hard multilingual tasks, while GLM-5-Turbo is plenty for everyday Russian text without overpaying. For long answers you can stream the response token by token instead of waiting for the full reply. For agents and structured tool calls, see function calling.

GLM-5V: working with images

Only GLM-5V-Turbo reads images — the other GLM lines are text-only. Pass an image (URL or base64) in the same request as your text and set the model field to GLM-5V-Turbo. It suits screenshots, photos, diagrams, charts and tables. The request format is OpenAI-compatible; for a ready image-passing example see the vision page.

Good value

GLM’s main draw is price. It’s one of the best-value families: capable models at a noticeably lower per-token cost, and the turbo variants are fast on top of that, which cuts both cost and latency across a stream of requests. We don’t pin numbers on this page — check the exact per-token price for each ID on the Pricing page at www.ruapi.ai. Top up in USDT — see the Top-up page.

Connecting GLM

GLM is served over the OpenAI-compatible protocol — no separate library needed. Take any OpenAI SDK, change the base_url to https://www.ruapi.ai/v1, and put the ID you want in the model field.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_RUAPI_KEY",
    base_url="https://www.ruapi.ai/v1",
)

resp = client.chat.completions.create(
    model="GLM-5.2",
    messages=[{"role": "user", "content": "Hi! In one line, what can you do?"}],
)
print(resp.choices[0].message.content)

You create a key in the Console after signing up. Step-by-step setup and a first request are in the Quickstart.

Connect and first request

base_url, key, Python and curl code.

DeepSeek models

Same key — another strong value line.

Gemini models

Multimodal input and long context.

Getting Started

Guides

API Reference

Model guides

Integrations

Capabilities

Recipes

Legal

GLM API: Zhipu's three models and how to connect

The three GLM models

Strong across languages

GLM-5V: working with images

Good value

Connecting GLM

Next

Connect and first request

DeepSeek models

Gemini models

​The three GLM models

​Strong across languages

​GLM-5V: working with images

​Good value

​Connecting GLM

​Next

Connect and first request

DeepSeek models

Gemini models

The three GLM models

Strong across languages

GLM-5V: working with images

Good value

Connecting GLM

Next