uttapen
Create an API key

Kimi K2 Thinking API: toman pricing and code

moonshotai/kimi-k2-thinking

toolsreasoningjson
Create a keyTry it
Input · per 1M tokens
174,075 toman
Output · per 1M tokens
725,313 toman
One 1,000-word request ≈
1,169 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 43,519 toman / 1M.Pricing and top-ups

Kimi K2 Thinking example: tool calling

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-…")

tools = [{
    "type": "function",
    "function": {
        "name": "check_stock",
        "description": "Returns the stock level of a product",
        "parameters": {
            "type": "object",
            "properties": {"sku": {"type": "string"}},
            "required": ["sku"],
        },
    },
}]

messages = [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}]
first = client.chat.completions.create(model="moonshotai/kimi-k2-thinking", messages=messages, tools=tools)
call = first.choices[0].message.tool_calls[0]

# you run the function yourself — the model never touches the database
args = json.loads(call.function.arguments)
result = {"sku": args["sku"], "qty": 7}

messages += [first.choices[0].message, {"role": "tool", "tool_call_id": call.id, "content": json.dumps(result)}]
final = client.chat.completions.create(model="moonshotai/kimi-k2-thinking", messages=messages, tools=tools)
print(final.choices[0].message.content)

What is Kimi K2 Thinking good for?

Kimi K2 Thinking comes from Moonshot (Kimi); in uttapen you reach it with the model id "moonshotai/kimi-k2-thinking". 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 100,352 tokens. On price it sits in the "mid-range" band — cheaper than 228 and dearer than 178 of the other paid models in the catalogue.

Capabilities available on this id: 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.

For a back-of-envelope figure: about 1,169 toman per 1,000-word exchange (174,075 in, 725,313 out, per 1M tokens). It supports cached input: repeated context is billed at 43,519 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 R1: Kimi K2 Thinking works out roughly 1× cheaper, 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 86 thousand-word requests on Kimi K2 Thinking, and every 1,000 toman is about 855 words of round trip. A job with one million input tokens and one million output tokens comes to 899,388 toman in total. Filling this model's 262,144-token window costs 45,633 toman on the input side alone, which is the real reason to keep conversation history short.

Moonshot (Kimi) has 9 models in our catalogue; the cheapest is Kimi K2.5 at 1,018 toman per thousand words and the dearest Kimi K3 (batch) at 6,789. Among the less common parameters it accepts logprobs, 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.

What to use it for: 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

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...

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 out551 toman
Summarising a ten-page document4,000 in + 600 out1,131 toman
Classifying a thousand short rows120,000 in + 20,000 out35,395 toman

Frequently asked

How do I call Kimi K2 Thinking 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-k2-thinking". Nothing else in your code changes.
What does Kimi K2 Thinking cost in toman?
174,075 toman per 1M input tokens and 725,313 toman per 1M output tokens; a 1,000-word request is around 1,169 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Kimi K2 Thinking take?
Up to 262,144 tokens per request, roughly 197k words. A single answer can reach 100,352 tokens.
Does Kimi K2 Thinking 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.