Create an API key

MiniMax M2.5 API: toman pricing and code

minimax/minimax-m2.5

Tool callingReasoningJSON output
Create a keyTry it
Input · per 1M tokens
93,479 toman
Output · per 1M tokens
328,908 toman
One 1,000-word request ≈
549 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 10,387 toman per 1M tokens.Pricing and top-ups

MiniMax M2.5 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="minimax/minimax-m2.5", 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="minimax/minimax-m2.5", messages=messages, tools=tools)
print(final.choices[0].message.content)
import OpenAI from "openai";

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

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

const messages = [{ role: "user", content: "How many of the Nike NK-42 shoe are in stock?" }];
const first = await client.chat.completions.create({ model: "minimax/minimax-m2.5", messages, tools });
const call = first.choices[0].message.tool_calls[0];

const args = JSON.parse(call.function.arguments);
const result = { sku: args.sku, qty: 7 };

messages.push(first.choices[0].message, { role: "tool", tool_call_id: call.id, content: JSON.stringify(result) });
const final = await client.chat.completions.create({ model: "minimax/minimax-m2.5", messages, tools });
console.log(final.choices[0].message.content);
curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax/minimax-m2.5",
    "messages": [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "check_stock",
        "parameters": {"type": "object", "properties": {"sku": {"type": "string"}}, "required": ["sku"]}
      }
    }]
  }'

What is MiniMax M2.5 good for?

MiniMax M2.5 is one of MiniMax's models. Put "minimax/minimax-m2.5" in the model field and the rest of your code stays as it is. MiniMax M2.5 keeps 204,800 tokens in view at once, and that number is what caps the conversation history in your product. A single response can run to 32,768 tokens. On price it sits in the "cheap" band — cheaper than 259 and dearer than 138 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 549 toman per 1,000-word exchange (93,479 in, 328,908 out, per 1M tokens). It supports cached input: repeated context is billed at 10,387 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 DeepSeek V3.1, and MiniMax M2.5 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 182 thousand-word requests on MiniMax M2.5, and every 1,000 toman is about 1,821 words of round trip. A job with one million input tokens and one million output tokens comes to 422,388 toman in total. Filling this model's 204,800-token window costs 19,145 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "minimax/minimax-m2.1", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out about 17% cheaper (549 against 675 toman). Maximum answer length differs as well: 32,768 against 131,072 tokens. On parameters, this one takes frequency_penalty, logit_bias, logprobs, min_p.

MiniMax has 9 models in our catalogue; the cheapest is MiniMax M3.1 Flash at 338 toman per thousand words and the dearest MiniMax M1 at 1,238. Among the less common parameters it accepts logit_bias, logprobs, min_p, presence_penalty, repetition_penalty, top_k — all through the standard request body. By context size the nearest option from another provider is GLM 4.6 at 204,800 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, extracting data against a fixed schema, analysing a long document or codebase in one request.

Provider's own description

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

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 out272 toman
Summarising a ten-page document4,000 in + 600 out571 toman
Classifying a thousand short rows120,000 in + 20,000 out17,796 toman

Price history

DateInput (toman/1M)Output (toman/1M)
31 Oct 202693,479328,908
24 Oct 2026103,866415,463
15 Oct 202693,479328,908
12 Sep 202693,479373,917
12 Sep 2026103,866415,463
11 Sep 202693,479373,917
11 Sep 2026103,866415,463
10 Sep 202693,479373,917
10 Sep 2026103,866415,463
7 Sep 202693,479373,917

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

Frequently asked

How do I call MiniMax M2.5 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 "minimax/minimax-m2.5". Nothing else in your code changes.
What does MiniMax M2.5 cost in toman?
93,479 toman per 1M input tokens and 328,908 toman per 1M output tokens; a 1,000-word request is around 549 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does MiniMax M2.5 take?
Up to 204,800 tokens per request, roughly 154k words. A single answer can reach 32,768 tokens.
Does MiniMax M2.5 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.