MiMo-V2.5 API: toman pricing and code
xiaomi/mimo-v2.5
visiontoolsreasoningjsonaudioYou are billed for the usage the request actually reported. Prices follow the market. Cached input: 812 toman / 1M.Pricing and top-ups
MiMo-V2.5 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": "xiaomi/mimo-v2.5",
"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="xiaomi/mimo-v2.5",
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: "xiaomi/mimo-v2.5",
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 MiMo-V2.5 good for?
Xiaomi publishes this model; we expose it under the id "xiaomi/mimo-v2.5". Its context window is 1,050,000 tokens, roughly 788k English words in one request. A single response can run to 131,072 tokens. On price it sits in the "very cheap" band — cheaper than 54 and dearer than 352 of the other paid models in the catalogue.
What you get on top of text in, text out: it reads images directly, which makes it a real option for invoices, forms and screenshots; it accepts audio input; 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.
Input runs at 40,618 toman per 1M tokens and output at 81,235 — output costs 2× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 812 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: MiMo-V2.5 works out roughly 1.1× 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 633 thousand-word requests on MiMo-V2.5, and every 1,000 toman is about 6,329 words of round trip. A job with one million input tokens and one million output tokens comes to 121,853 toman in total. Filling this model's 1,050,000-token window costs 42,648 toman on the input side alone, which is the real reason to keep conversation history short.
Xiaomi has 2 models in our catalogue; the cheapest is MiMo-V2.5 at 158 toman per thousand words and the dearest MiMo-V2.5-Pro at 492. Among the less common parameters it accepts logit_bias, min_p, repetition_penalty, top_k — all through the standard request body. By context size the nearest option from another provider is GPT-5.4 at 1,050,000 tokens.
Where it makes sense: 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.
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
Three real jobs, priced on this model
Each figure is derived from the prices above and moves when they do.
| Job | Tokens | Cost |
|---|---|---|
| One chat turn with a medium history | 1,500 in + 400 out | 93 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 211 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 6,499 toman |
Frequently asked
- How do I call MiMo-V2.5 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 "xiaomi/mimo-v2.5". Nothing else in your code changes.
- What does MiMo-V2.5 cost in toman?
- 40,618 toman per 1M input tokens and 81,235 toman per 1M output tokens; a 1,000-word request is around 158 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does MiMo-V2.5 take?
- Up to 1,050,000 tokens per request, roughly 788k words. A single answer can reach 131,072 tokens.
- Does MiMo-V2.5 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.