uttapen

GLM 5.3 Flash (batch) API: toman pricing and code

z-ai/glm-5.3-flash:batch

visiontoolsreasoningjson
Input · per 1M tokens
43,519 toman
Output · per 1M tokens
145,063 toman
One 1,000-word request ≈
245 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 8,704 toman / 1M.Pricing and top-ups

GLM 5.3 Flash (batch) example: reading an image into JSON

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

# tip: a data URI works too — base64 the file and prefix it with data:image/jpeg;base64,
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-flash:batch",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Return only the invoice number and the total, as JSON."},
        {"type": "image_url", "image_url": {"url": "https://example.com/factor.jpg"}}
      ]
    }]
  }'

What is GLM 5.3 Flash (batch) good for?

Z.ai (GLM) publishes this model; we expose it under the id "z-ai/glm-5.3-flash:batch". Its context window is 1,048,575 tokens, roughly 786k English words in one request. A single response can run to 943,717 tokens. On price it sits in the "very cheap" band — cheaper than 88 and dearer than 318 of the other paid models in the catalogue.

What you get on top of text in, text out: it reads images directly, which makes it a real option for invoices, forms and screenshots; 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 43,519 toman per 1M tokens and output at 145,063 — output costs 3.3× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 8,704 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 Qwen3.8 Flash: GLM 5.3 Flash (batch) 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 408 thousand-word requests on GLM 5.3 Flash (batch), and every 1,000 toman is about 4,082 words of round trip. A job with one million input tokens and one million output tokens comes to 188,581 toman in total. Filling this model's 1,048,575-token window costs 45,633 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-flash", because the underlying model is the same. The difference is the suffix: "batch" against the standard variant. On a thousand-word request this variant works out 2× dearer (245 against 123 toman). The context windows differ too: 1,048,575 against 1,310,720 tokens. Maximum answer length differs as well: 943,717 against 131,072 tokens. On parameters the other takes seed.

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, reasoning_effort, repetition_penalty, top_k — all through the standard request body. It does not support seed, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is DeepSeek V4 Flash 0423 at 1,048,576 tokens.

Where it makes sense: high-volume work such as classification, tagging and bulk summarising, logic puzzles and code review, pulling text and fields out of images, 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-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

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 out123 toman
Summarising a ten-page document4,000 in + 600 out261 toman
Classifying a thousand short rows120,000 in + 20,000 out8,124 toman

Other variants of this model

Same core model, different execution terms and different price. This page is the batch (cheaper, slower) variant.

VariantModel idOutput / 1MContext
standardz-ai/glm-5.3-flash72,5311,310,720

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

Frequently asked

How do I call GLM 5.3 Flash (batch) 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-flash:batch". Nothing else in your code changes.
What does GLM 5.3 Flash (batch) cost in toman?
43,519 toman per 1M input tokens and 145,063 toman per 1M output tokens; a 1,000-word request is around 245 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does GLM 5.3 Flash (batch) take?
Up to 1,048,575 tokens per request, roughly 786k words. A single answer can reach 943,717 tokens.
Does GLM 5.3 Flash (batch) support streaming and tool calling?
Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Image input is accepted through image_url, as a data URI or a public URL. Structured output through response_format works too.