GPT-5 Image API: toman pricing and code

What is GPT-5 Image good for?

OpenAI publishes this model; we expose it under the id "openai/gpt-5-image". Its context window is 400,000 tokens, roughly 300k English words in one request. A single response can run to 128,000 tokens. On price it sits in the "mid-range" band — cheaper than 322 and dearer than 84 of the other paid models in the catalogue.

Capabilities available on this id: it reads images directly, which makes it a real option for invoices, forms and screenshots; it takes files such as PDFs as input; 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; it can return generated images. 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 7,543 toman per 1,000-word exchange (2,901,250 in, 2,901,250 out, per 1M tokens). It supports cached input: repeated context is billed at 362,656 toman per 1M, which matters a lot if your system prompt is long. Each generated image costs around 11.61 toman. 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 Nano Banana Pro (Gemini 3 Pro Image Preview): GPT-5 Image works out roughly 1.4× 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 13 thousand-word requests on GPT-5 Image, and every 1,000 toman is about 133 words of round trip. A job with one million input tokens and one million output tokens comes to 5,802,500 toman in total. Filling this model's 400,000-token window costs 1,160,500 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-5.4-image-2", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 1.2× cheaper (7,543 against 8,675 toman). The context windows differ too: 400,000 against 272,000 tokens. On parameters, this one takes temperature, top_p while the other takes reasoning_effort.

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 logit_bias, logprobs, top_logprobs — all through the standard request body. It does not support tool_choice, tools, 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.

What to use it for: product chatbots and internal assistants, where cost and quality have to balance, logic puzzles and code review, pulling text and fields out of images, extracting data against a fixed schema, analysing a long document or codebase in one request.