uttapen

LongCat 2.0 API: toman pricing and code

meituan/longcat-2.0

toolsreasoning
Input · per 1M tokens
87,038 toman
Output · per 1M tokens
348,150 toman
One 1,000-word request ≈
566 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 1,741 toman / 1M.Pricing and top-ups

LongCat 2.0 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="meituan/longcat-2.0", 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="meituan/longcat-2.0", messages=messages, tools=tools)
print(final.choices[0].message.content)

What is LongCat 2.0 good for?

The id for LongCat 2.0 in our API is "meituan/longcat-2.0", served from Meituan. Context is 1,048,756 tokens; past that you have to summarise the history yourself. A single response can run to 262,144 tokens. On price it sits in the "cheap" band — cheaper than 151 and dearer than 255 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 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 566 toman per 1,000-word exchange (87,038 in, 348,150 out, per 1M tokens). It supports cached input: repeated context is billed at 1,741 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 KAT-Coder-Pro V2: LongCat 2.0 works out roughly 1× more expensive, 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 177 thousand-word requests on LongCat 2.0, and every 1,000 toman is about 1,767 words of round trip. A job with one million input tokens and one million output tokens comes to 435,188 toman in total. Filling this model's 1,048,756-token window costs 91,281 toman on the input side alone, which is the real reason to keep conversation history short.

Among the less common parameters it accepts logit_bias, min_p, repetition_penalty, top_k — all through the standard request body. It does not support response_format, structured_outputs, 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 DeepSeek V4 Flash 0423 at 1,048,576 tokens.

What to use it for: high-volume work such as classification, tagging and bulk summarising, logic puzzles and code review, agents that reach out to APIs and databases, analysing a long document or codebase in one request.

Provider's own description

LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizon problem solving, and agentic...

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 out270 toman
Summarising a ten-page document4,000 in + 600 out557 toman
Classifying a thousand short rows120,000 in + 20,000 out17,408 toman

Frequently asked

How do I call LongCat 2.0 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 "meituan/longcat-2.0". Nothing else in your code changes.
What does LongCat 2.0 cost in toman?
87,038 toman per 1M input tokens and 348,150 toman per 1M output tokens; a 1,000-word request is around 566 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does LongCat 2.0 take?
Up to 1,048,756 tokens per request, roughly 787k words. A single answer can reach 262,144 tokens.
Does LongCat 2.0 support streaming and tool calling?
Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape.