Create an API key

Kimi K3 (batch) API: toman pricing and code

moonshotai/kimi-k3:batch

Image inputTool callingReasoningJSON output
Create a keyTry it
Input · per 1M tokens
789,380 toman
Output · per 1M tokens
3,946,901 toman
One 1,000-word request ≈
6,157 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 78,938 toman per 1M tokens.Pricing and top-ups

Kimi K3 (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": "moonshotai/kimi-k3: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"}}
      ]
    }]
  }'
import base64, json
from openai import OpenAI

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

img = base64.b64encode(open("factor.jpg", "rb").read()).decode()

resp = client.chat.completions.create(
    model="moonshotai/kimi-k3:batch",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Return the invoice number, the date and the total as JSON."},
            {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{img}"}},
        ],
    }],
    response_format={"type": "json_object"},
)
print(json.loads(resp.choices[0].message.content))
import OpenAI from "openai";
import { readFileSync } from "node:fs";

const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });
const img = readFileSync("factor.jpg").toString("base64");

const resp = await client.chat.completions.create({
  model: "moonshotai/kimi-k3:batch",
  messages: [{
    role: "user",
    content: [
      { type: "text", text: "Return the invoice number, the date and the total as JSON." },
      { type: "image_url", image_url: { url: `data:image/jpeg;base64,${img}` } },
    ],
  }],
  response_format: { type: "json_object" },
});
console.log(JSON.parse(resp.choices[0].message.content));

What is Kimi K3 (batch) good for?

Kimi K3 (batch) comes from Moonshot (Kimi); in uttapen you reach it with the model id "moonshotai/kimi-k3: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 16,384 tokens. On price it sits in the "expensive" band — cheaper than 51 and dearer than 347 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 789,380 toman per 1M input tokens and 3,946,901 per 1M output tokens. A 1,000-word round trip on Kimi K3 (batch) lands near 6,157 toman. It supports cached input: repeated context is billed at 78,938 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 Nano Banana Pro (Gemini 3 Pro Image), and Kimi K3 (batch) costs about the same, 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 16 thousand-word requests on Kimi K3 (batch), and every 1,000 toman is about 162 words of round trip. A job with one million input tokens and one million output tokens comes to 4,736,281 toman in total. Filling this model's 1,048,576-token window costs 827,725 toman on the input side alone, which is the real reason to keep conversation history short.

This id gets confused with "moonshotai/kimi-k3", 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 about 17% cheaper (6,157 against 7,288 toman). Maximum answer length differs as well: 16,384 against 943,718 tokens. On parameters the other takes logprobs, max_completion_tokens, parallel_tool_calls, top_logprobs.

Moonshot (Kimi) has 10 models in our catalogue; the cheapest is Kimi K2 0711 at 1,292 toman per thousand words and the dearest Kimi K3 at 7,288. Among the less common parameters it accepts logit_bias, min_p, presence_penalty, reasoning_effort, repetition_penalty, top_k — 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.

Good fits: 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

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

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 out2,763 toman
Summarising a ten-page document4,000 in + 600 out5,526 toman
Classifying a thousand short rows120,000 in + 20,000 out173,664 toman

Other variants of this model

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

VariantModel idOutput / 1MContext
standardmoonshotai/kimi-k35,539,5101,048,576

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

Price history

DateInput (toman/1M)Output (toman/1M)
22 Sep 2026789,3803,946,901
7 Sep 20261,038,6585,193,290

Every price change for this model is recorded. Toman figures use today's rate.

Frequently asked

How do I call Kimi K3 (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 "moonshotai/kimi-k3:batch". Nothing else in your code changes.
What does Kimi K3 (batch) cost in toman?
789,380 toman per 1M input tokens and 3,946,901 toman per 1M output tokens; a 1,000-word request is around 6,157 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Kimi K3 (batch) take?
Up to 1,048,576 tokens per request, roughly 786k words. A single answer can reach 16,384 tokens.
Does Kimi K3 (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.