GLM 4.6 API: toman pricing and code
z-ai/glm-4.6
toolsreasoningjsonYou are billed for the usage the request actually reported. Prices follow the market. Cached input: 23,210 toman / 1M.Pricing and top-ups
GLM 4.6 example: a multi-step problem with reasoning
The example is picked from this model's own capabilities. Drop in your key and it runs as is.
from openai import OpenAI
client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")
resp = client.chat.completions.create(
model="z-ai/glm-4.6",
messages=[{"role": "user", "content": (
"A shop has 3 warehouses. A ships 120 orders a day, B ships 85 and C ships 40. "
"If C closes and its load is split between A and B in proportion to their capacity, how many does each ship a day? "
"Work through it step by step and give just the two numbers at the end."
)}],
reasoning_effort="medium", # low | medium | high
)
print(resp.choices[0].message.content)
# reasoning tokens count as output tokens too:
print(resp.usage.completion_tokens_details)curl https://api.uttapen.ir/v1/chat/completions \
-H "Authorization: Bearer sk-up-…" \
-H "Content-Type: application/json" \
-d '{
"model": "z-ai/glm-4.6",
"messages": [{"role": "user", "content": "120 and 85 daily orders split across two warehouses; work through it step by step."}],
"reasoning": {"effort": "medium"}
}'import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });
const resp = await client.chat.completions.create({
model: "z-ai/glm-4.6",
messages: [{ role: "user", content: "120 and 85 daily orders are split between two warehouses; work through it step by step and give just the two numbers at the end." }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);
console.log(resp.usage.completion_tokens_details);What is GLM 4.6 good for?
The id for GLM 4.6 in our API is "z-ai/glm-4.6", served from Z.ai (GLM). Context is 204,800 tokens; past that you have to summarise the history yourself. A single response can run to 16,384 tokens. On price it sits in the "cheap" band — cheaper than 187 and dearer than 219 of the other paid models in the catalogue.
What you get on top of text in, text out: 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.
Input runs at 124,754 toman per 1M tokens and output at 507,719 — output costs 4.1× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 23,210 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 Qwen3 235B A22B: GLM 4.6 works out roughly 1× 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 122 thousand-word requests on GLM 4.6, and every 1,000 toman is about 1,217 words of round trip. A job with one million input tokens and one million output tokens comes to 632,473 toman in total. Filling this model's 204,800-token window costs 25,550 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-4.7", and choosing between those two is where most people hesitate. Both land at nearly the same price on a thousand-word request (822 and 811 toman). Maximum answer length differs as well: 16,384 against 131,072 tokens. On parameters the other takes top_a.
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, min_p, repetition_penalty, top_k — all through the standard request body. By context size the nearest option from another provider is MiniMax M2 at 204,800 tokens.
Where it makes sense: 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.
Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
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 | 390 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 804 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 25,125 toman |
Price history
| Date | Input (toman/1M) | Output (toman/1M) |
|---|---|---|
| 2026-09-07 | 124,754 | 507,719 |
| 2026-09-06 | 159,569 | 638,275 |
Every price change for this model is recorded. Toman figures use today's rate.
Frequently asked
- How do I call GLM 4.6 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-4.6". Nothing else in your code changes.
- What does GLM 4.6 cost in toman?
- 124,754 toman per 1M input tokens and 507,719 toman per 1M output tokens; a 1,000-word request is around 822 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does GLM 4.6 take?
- Up to 204,800 tokens per request, roughly 154k words. A single answer can reach 16,384 tokens.
- Does GLM 4.6 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.