How do I call GLM 5.3 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-5.3". Nothing else in your code changes.

What does GLM 5.3 cost in toman?

24,201 toman per 1M input tokens and 484,707 toman per 1M output tokens; a 1,000-word request is around 662 toman. You pay for the usage that request actually reported, and a failed request costs nothing.

How much input does GLM 5.3 take?

Up to 1,048,576 tokens per request, roughly 786k words. A single answer can reach 943,718 tokens.

Does GLM 5.3 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.

GLM 5.3 API: toman pricing and code

z-ai/glm-5.3

Tool callingReasoningJSON output

Create a key Try it

Input · per 1M tokens

24,201 toman

Output · per 1M tokens

484,707 toman

One 1,000-word request ≈

662 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 23,855 toman per 1M tokens.Pricing and top-ups

GLM 5.3 example: tool calling

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

PythonNode.jscurl

from openai import OpenAI
import json

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

tools = [{
    "type": "function",
    "function": {
        "name": "check_stock",
        "description": "Returns the stock level of a product",
        "parameters": {
            "type": "object",
            "properties": {"sku": {"type": "string"}},
            "required": ["sku"],
        },
    },
}]

messages = [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}]
first = client.chat.completions.create(model="z-ai/glm-5.3", messages=messages, tools=tools)
call = first.choices[0].message.tool_calls[0]

# you run the function yourself — the model never touches the database
args = json.loads(call.function.arguments)
result = {"sku": args["sku"], "qty": 7}

messages += [first.choices[0].message, {"role": "tool", "tool_call_id": call.id, "content": json.dumps(result)}]
final = client.chat.completions.create(model="z-ai/glm-5.3", messages=messages, tools=tools)
print(final.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });

const tools = [{
  type: "function",
  function: {
    name: "check_stock",
    description: "Returns the stock level of a product",
    parameters: { type: "object", properties: { sku: { type: "string" } }, required: ["sku"] },
  },
}];

const messages = [{ role: "user", content: "How many of the Nike NK-42 shoe are in stock?" }];
const first = await client.chat.completions.create({ model: "z-ai/glm-5.3", messages, tools });
const call = first.choices[0].message.tool_calls[0];

const args = JSON.parse(call.function.arguments);
const result = { sku: args.sku, qty: 7 };

messages.push(first.choices[0].message, { role: "tool", tool_call_id: call.id, content: JSON.stringify(result) });
const final = await client.chat.completions.create({ model: "z-ai/glm-5.3", messages, tools });
console.log(final.choices[0].message.content);

curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-5.3",
    "messages": [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "check_stock",
        "parameters": {"type": "object", "properties": {"sku": {"type": "string"}}, "required": ["sku"]}
      }
    }]
  }'

What is GLM 5.3 good for?

The id for GLM 5.3 in our API is "z-ai/glm-5.3", served from Z.ai (GLM). Context is 1,048,576 tokens; past that you have to summarise the history yourself. A single response can run to 943,718 tokens. On price it sits in the "cheap" band — cheaper than 221 and dearer than 174 of the other paid models in the catalogue.

Capabilities available on this id: 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.

For a back-of-envelope figure: about 662 toman per 1,000-word exchange (24,201 in, 484,707 out, per 1M tokens). It supports cached input: repeated context is billed at 23,855 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 Aion-3.0-Mini: GLM 5.3 works out about 29% cheaper, 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 151 thousand-word requests on GLM 5.3, and every 1,000 toman is about 1,511 words of round trip. A job with one million input tokens and one million output tokens comes to 508,908 toman in total. Filling this model's 1,048,576-token window costs 25,376 toman on the input side alone, which is the real reason to keep conversation history short.

This id gets confused with "z-ai/glm-5.3:batch", because the underlying model is the same. The difference is the suffix: no suffix (the standard variant) against "batch". On a thousand-word request this variant works out about 41% cheaper (662 against 1,103 toman). Maximum answer length differs as well: 943,718 against 131,072 tokens. On parameters, this one takes logprobs, parallel_tool_calls, top_logprobs.

Z.ai (GLM) has 21 models in our catalogue; the cheapest is GLM Flash Latest at 54 toman per thousand words and the dearest GLM 5.3 Prime at 5,221. Among the less common parameters it accepts logit_bias, logprobs, min_p, parallel_tool_calls, presence_penalty, reasoning_effort — 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.

What to use it for: high-volume work such as classification, tagging and bulk summarising, 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-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves...

Three real jobs, priced on this model

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

Job	Tokens	Cost
One chat turn with a medium history	1,500 in + 400 out	230 toman
Summarising a ten-page document	4,000 in + 600 out	388 toman
Classifying a thousand short rows	120,000 in + 20,000 out	12,598 toman

Job

Tokens

Cost

One chat turn with a medium history

1,500 in + 400 out

230 toman

Summarising a ten-page document

4,000 in + 600 out

388 toman

Classifying a thousand short rows

120,000 in + 20,000 out

12,598 toman

Other variants of this model

Same core model, different execution terms and different price. This page is the standard variant.

Variant	Model id	Output / 1M	Context
batch	z-ai/glm-5.3:batch	692,439	1,048,576

Variant

Model id

Output / 1M

Context

batch

z-ai/glm-5.3:batch

692,439

1,048,576

Put the variant's id verbatim in the model field; nothing else in your code changes.

Price history

Date	Input (toman/1M)	Output (toman/1M)
4 Nov 2026	24,201	484,707
4 Nov 2026	27,698	1,246,390
31 Oct 2026	24,201	484,707
31 Oct 2026	27,698	1,102,362
27 Oct 2026	24,201	484,707
27 Oct 2026	26,624	484,707
27 Oct 2026	24,201	484,707
27 Oct 2026	26,624	484,707
26 Oct 2026	24,201	484,707
25 Oct 2026	27,351	484,707
25 Oct 2026	25,620	484,707
25 Oct 2026	27,351	484,707

Every price change for this model is recorded. Toman figures use today's rate.

Frequently asked

How do I call GLM 5.3 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-5.3". Nothing else in your code changes.
What does GLM 5.3 cost in toman?: 24,201 toman per 1M input tokens and 484,707 toman per 1M output tokens; a 1,000-word request is around 662 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does GLM 5.3 take?: Up to 1,048,576 tokens per request, roughly 786k words. A single answer can reach 943,718 tokens.
Does GLM 5.3 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.