uttapen
Create an API key

Gemma 4 31B API: toman pricing and code

google/gemma-4-31b-it

visiontoolsreasoningjson
Create a keyTry it
Input · per 1M tokens
26,111 toman
Output · per 1M tokens
98,643 toman
One 1,000-word request ≈
162 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 14,506 toman / 1M.Pricing and top-ups

Gemma 4 31B 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/gemma-4-31b-it",
    "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 Gemma 4 31B good for?

Gemma 4 31B comes from Google; in uttapen you reach it with the model id "google/gemma-4-31b-it". It accepts up to 262,144 tokens of input per call, so a long document or several source files fit in a single request. A single response can run to 16,384 tokens. On price it sits in the "very cheap" band — cheaper than 69 and dearer than 337 of the other paid models in the catalogue.

What it can do beyond plain text: 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.

Pricing is 26,111 toman per 1M input tokens and 98,643 per 1M output tokens. A 1,000-word round trip on Gemma 4 31B lands near 162 toman. It supports cached input: repeated context is billed at 14,506 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 Seed 1.6 Flash: Gemma 4 31B works out roughly 1.1× more expensive, and its context window is the same size. 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 617 thousand-word requests on Gemma 4 31B, and every 1,000 toman is about 6,173 words of round trip. A job with one million input tokens and one million output tokens comes to 124,754 toman in total. Filling this model's 262,144-token window costs 6,845 toman on the input side alone, which is the real reason to keep conversation history short.

This id gets confused with "google/gemma-4-31b-it:batch", because the underlying model is the same. The difference is the suffix: no suffix (the standard variant) against "batch". On a thousand-word request this variant works out 3.2× cheaper (162 against 513 toman). Maximum answer length differs as well: 16,384 against 235,929 tokens. On parameters, this one takes logprobs, seed, top_logprobs.

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 logit_bias, logprobs, min_p, repetition_penalty, top_k, top_logprobs — all through the standard request body. By context size the nearest option from another provider is Trinity Large Thinking at 262,144 tokens.

Good fits: 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

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

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 out79 toman
Summarising a ten-page document4,000 in + 600 out164 toman
Classifying a thousand short rows120,000 in + 20,000 out5,106 toman

Other variants of this model

Same core model, different execution terms and different price. This page is the standard variant.

VariantModel idOutput / 1MContext
batch (cheaper, slower)google/gemma-4-31b-it:batch281,421262,144
freegoogle/gemma-4-31b-it:free0262,144

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

Frequently asked

How do I call Gemma 4 31B 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/gemma-4-31b-it". Nothing else in your code changes.
What does Gemma 4 31B cost in toman?
26,111 toman per 1M input tokens and 98,643 toman per 1M output tokens; a 1,000-word request is around 162 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Gemma 4 31B take?
Up to 262,144 tokens per request, roughly 197k words. A single answer can reach 16,384 tokens.
Does Gemma 4 31B 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.