uttapen

o3 Mini (batch) API: toman pricing and code

openai/o3-mini:batch

toolsreasoningjsonfiles
Input · per 1M tokens
159,569 toman
Output · per 1M tokens
638,275 toman
One 1,000-word request ≈
1,037 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 79,784 toman / 1M. Web search: 2,901.25 toman / request.Pricing and top-ups

o3 Mini (batch) example: JSON output against a schema

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

from openai import OpenAI
import json

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

schema = {
    "name": "ticket",
    "schema": {
        "type": "object",
        "properties": {
            "category": {"type": "string", "enum": ["fani", "mali", "forush"]},
            "priority": {"type": "integer", "minimum": 1, "maximum": 5},
            "summary": {"type": "string"},
        },
        "required": ["category", "priority", "summary"],
        "additionalProperties": False,
    },
    "strict": True,
}

resp = client.chat.completions.create(
    model="openai/o3-mini:batch",
    messages=[{"role": "user", "content": "Ticket: "For two days I cannot download my invoice and I was charged twice.""}],
    response_format={"type": "json_schema", "json_schema": schema},
)
print(json.loads(resp.choices[0].message.content))

What is o3 Mini (batch) good for?

o3 Mini (batch) comes from OpenAI; in uttapen you reach it with the model id "openai/o3-mini:batch". It accepts up to 200,000 tokens of input per call, so a long document or several source files fit in a single request. A single response can run to 100,000 tokens. On price it sits in the "mid-range" band — cheaper than 215 and dearer than 191 of the other paid models in the catalogue.

What it can do beyond plain text: 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.

Pricing is 159,569 toman per 1M input tokens and 638,275 per 1M output tokens. A 1,000-word round trip on o3 Mini (batch) lands near 1,037 toman. It supports cached input: repeated context is billed at 79,784 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 MiniMax M1: o3 Mini (batch) works out roughly 1× more expensive, 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 96 thousand-word requests on o3 Mini (batch), and every 1,000 toman is about 964 words of round trip. A job with one million input tokens and one million output tokens comes to 797,844 toman in total. Filling this model's 200,000-token window costs 31,914 toman on the input side alone, which is the real reason to keep conversation history short.

This id gets confused with "openai/o3-mini", 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× cheaper (1,037 against 2,074 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. 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 Claude 3 Haiku at 200,000 tokens.

Good fits: product chatbots and internal assistants, where cost and quality have to balance, 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

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...

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 out495 toman
Summarising a ten-page document4,000 in + 600 out1,021 toman
Classifying a thousand short rows120,000 in + 20,000 out31,914 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
standardopenai/o3-mini1,276,550200,000

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

Frequently asked

How do I call o3 Mini (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 "openai/o3-mini:batch". Nothing else in your code changes.
What does o3 Mini (batch) cost in toman?
159,569 toman per 1M input tokens and 638,275 toman per 1M output tokens; a 1,000-word request is around 1,037 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does o3 Mini (batch) take?
Up to 200,000 tokens per request, roughly 150k words. A single answer can reach 100,000 tokens.
Does o3 Mini (batch) 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.