uttapen
Create an API key

GLM 5.2 API: toman pricing and code

z-ai/glm-5.2

toolsreasoningjson
Create a keyTry it
Input · per 1M tokens
280,261 toman
Output · per 1M tokens
880,820 toman
One 1,000-word request ≈
1,509 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 56,052 toman / 1M.Pricing and top-ups

GLM 5.2 example: JSON output against a schema

The example is picked from this model's own capabilities. Drop in your key and it runs as is.

from openai import OpenAI
import json

client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")

schema = {
    "name": "ticket",
    "schema": {
        "type": "object",
        "properties": {
            "category": {"type": "string", "enum": ["fani", "mali", "forush"]},
            "priority": {"type": "integer", "minimum": 1, "maximum": 5},
            "summary": {"type": "string"},
        },
        "required": ["category", "priority", "summary"],
        "additionalProperties": False,
    },
    "strict": True,
}

resp = client.chat.completions.create(
    model="z-ai/glm-5.2",
    messages=[{"role": "user", "content": "Ticket: "For two days I cannot download my invoice and I was charged twice.""}],
    response_format={"type": "json_schema", "json_schema": schema},
)
print(json.loads(resp.choices[0].message.content))

What is GLM 5.2 good for?

GLM 5.2 is one of Z.ai (GLM)'s models. Put "z-ai/glm-5.2" in the model field and the rest of your code stays as it is. GLM 5.2 keeps 1,048,576 tokens in view at once, and that number is what caps the conversation history in your product. A single response can run to 131,072 tokens. On price it sits in the "mid-range" band — cheaper than 249 and dearer than 157 of the other paid models in the catalogue.

What it can do beyond plain text: it supports tool calling, so it can invoke your own functions with valid arguments; it returns schema-valid JSON through response_format, ready to hand to your code; it has a reasoning mode that pays off on multi-step problems, maths and debugging. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper. Keep in mind that reasoning tokens are output tokens and do appear on the bill.

Pricing is 280,261 toman per 1M input tokens and 880,820 per 1M output tokens. A 1,000-word round trip on GLM 5.2 lands near 1,509 toman. It supports cached input: repeated context is billed at 56,052 toman per 1M, which matters a lot if your system prompt is long. You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.

The closest alternative with the same capabilities from a different provider is Relace Search: GLM 5.2 works out roughly 1× more expensive, and its context window is larger. Both run on the same key and the same code, so trying the other one is a single string change.

To make the figure concrete: 100,000 toman of credit buys roughly 66 thousand-word requests on GLM 5.2, and every 1,000 toman is about 663 words of round trip. A job with one million input tokens and one million output tokens comes to 1,161,080 toman in total. Filling this model's 1,048,576-token window costs 293,875 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "~z-ai/glm-latest", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 1.2× cheaper (1,509 against 1,750 toman). The context windows differ too: 1,048,576 against 1,310,720 tokens. Maximum answer length differs as well: 131,072 against 943,718 tokens.

Z.ai (GLM) has 17 models in our catalogue; the cheapest is GLM Flash Latest at 116 toman per thousand words and the dearest GLM 5.3 at 2,188. Among the less common parameters it accepts logit_bias, logprobs, min_p, parallel_tool_calls, reasoning_effort, repetition_penalty — all through the standard request body. By context size the nearest option from another provider is DeepSeek V4 Flash 0423 at 1,048,576 tokens.

Good fits: product chatbots and internal assistants, where cost and quality have to balance, logic puzzles and code review, agents that reach out to APIs and databases, extracting data against a fixed schema, analysing a long document or codebase in one request.

Provider's own description

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

Three real jobs, priced on this model

Each figure is derived from the prices above and moves when they do.

JobTokensCost
One chat turn with a medium history1,500 in + 400 out773 toman
Summarising a ten-page document4,000 in + 600 out1,650 toman
Classifying a thousand short rows120,000 in + 20,000 out51,248 toman

Frequently asked

How do I call GLM 5.2 from Iran?
Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "z-ai/glm-5.2". Nothing else in your code changes.
What does GLM 5.2 cost in toman?
280,261 toman per 1M input tokens and 880,820 toman per 1M output tokens; a 1,000-word request is around 1,509 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does GLM 5.2 take?
Up to 1,048,576 tokens per request, roughly 786k words. A single answer can reach 131,072 tokens.
Does GLM 5.2 support streaming and tool calling?
Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Structured output through response_format works too.