uttapen

GPT-5.3-Codex API: toman pricing and code

openai/gpt-5.3-codex

visiontoolsreasoningjsonfiles
Input · per 1M tokens
507,719 toman
Output · per 1M tokens
4,061,750 toman
One 1,000-word request ≈
5,940 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 50,772 toman / 1M. Web search: 2,901.25 toman / request.Pricing and top-ups

GPT-5.3-Codex 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": "openai/gpt-5.3-codex",
    "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 GPT-5.3-Codex good for?

The id for GPT-5.3-Codex in our API is "openai/gpt-5.3-codex", served from OpenAI. Context is 400,000 tokens; past that you have to summarise the history yourself. A single response can run to 128,000 tokens. On price it sits in the "expensive" band — cheaper than 355 and dearer than 51 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 takes files such as PDFs as input; 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 507,719 toman per 1M tokens and output at 4,061,750 — output costs 8× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 50,772 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 Claude Sonnet 4: GPT-5.3-Codex works out roughly 1.1× cheaper, and its context window is smaller. 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 17 thousand-word requests on GPT-5.3-Codex, and every 1,000 toman is about 168 words of round trip. A job with one million input tokens and one million output tokens comes to 4,569,469 toman in total. Filling this model's 400,000-token window costs 203,088 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "openai/gpt-5.2", and choosing between those two is where most people hesitate. Both land at nearly the same price on a thousand-word request (5,940 and 5,940 toman).

OpenAI has 95 models in our catalogue; the cheapest is gpt-oss-20b at 60 toman per thousand words and the dearest o1-pro at 282,872. Among the less common parameters it accepts max_completion_tokens, reasoning_effort — all through the standard request body. It does not support temperature, top_p, 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 Nova Lite 1.0 at 300,000 tokens.

Where it makes sense: work where the quality of the answer matters more than its cost, 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

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...

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 out2,386 toman
Summarising a ten-page document4,000 in + 600 out4,468 toman
Classifying a thousand short rows120,000 in + 20,000 out142,161 toman

Frequently asked

How do I call GPT-5.3-Codex 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 "openai/gpt-5.3-codex". Nothing else in your code changes.
What does GPT-5.3-Codex cost in toman?
507,719 toman per 1M input tokens and 4,061,750 toman per 1M output tokens; a 1,000-word request is around 5,940 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does GPT-5.3-Codex take?
Up to 400,000 tokens per request, roughly 300k words. A single answer can reach 128,000 tokens.
Does GPT-5.3-Codex 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.