uttapen

Gemini 3.1 Pro Preview (batch) API: toman pricing and code

google/gemini-3.1-pro-preview:batch

visiontoolsreasoningjsonfilesaudio
Input · per 1M tokens
290,125 toman
Output · per 1M tokens
1,740,750 toman
One 1,000-word request ≈
2,640 toman

You are billed for the usage the request actually reported. Prices follow the market. Reasoning tokens: 1,740,750 toman / 1M. Per input image: 0.29 toman. Web search: 4,061.75 toman / request.Pricing and top-ups

Gemini 3.1 Pro Preview (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": "google/gemini-3.1-pro-preview: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 Gemini 3.1 Pro Preview (batch) good for?

Gemini 3.1 Pro Preview (batch) comes from Google; in uttapen you reach it with the model id "google/gemini-3.1-pro-preview:batch". It accepts up to 1,048,576 tokens of input per call, so a long document or several source files fit in a single request. A single response can run to 65,536 tokens. On price it sits in the "mid-range" band — cheaper than 297 and dearer than 109 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 accepts audio 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 290,125 toman per 1M tokens and output at 1,740,750 — output costs 6× input, so trimming the answer saves more than trimming the prompt. Each input image is billed separately at about 0.29 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 GPT-5.6 Terra Pro (batch): Gemini 3.1 Pro Preview (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 38 thousand-word requests on Gemini 3.1 Pro Preview (batch), and every 1,000 toman is about 379 words of round trip. A job with one million input tokens and one million output tokens comes to 2,030,875 toman in total. Filling this model's 1,048,576-token window costs 304,218 toman on the input side alone, which is the real reason to keep conversation history short.

This id gets confused with "google/gemini-3.1-pro-preview", 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 (2,640 against 5,280 toman).

Google has 45 models in our catalogue; the cheapest is Gemma 3 4B at 57 toman per thousand words and the dearest Google Gemini Pro Latest at 5,280. Among the less common parameters it accepts reasoning_effort — all through the standard request body. By context size the nearest option from another provider is DeepSeek V4 Flash 0423 at 1,048,576 tokens.

Where it makes sense: product chatbots and internal assistants, where cost and quality have to balance, 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

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...

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 out1,131 toman
Summarising a ten-page document4,000 in + 600 out2,205 toman
Classifying a thousand short rows120,000 in + 20,000 out69,630 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
standardgoogle/gemini-3.1-pro-preview3,481,5001,048,576

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

Frequently asked

How do I call Gemini 3.1 Pro Preview (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 "google/gemini-3.1-pro-preview:batch". Nothing else in your code changes.
What does Gemini 3.1 Pro Preview (batch) cost in toman?
290,125 toman per 1M input tokens and 1,740,750 toman per 1M output tokens; a 1,000-word request is around 2,640 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Gemini 3.1 Pro Preview (batch) take?
Up to 1,048,576 tokens per request, roughly 786k words. A single answer can reach 65,536 tokens.
Does Gemini 3.1 Pro Preview (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.