Models / MiMo pricing
MiMo API pricing
4 MiMo models from Xiaomi on one key, per million tokens. Input 40% under Xiaomi's list price, output 40% to 67%. Lowest price: MiMo V2.6 Flash, $0.084 in and $0.09 out.
Prices · per million tokens, USD, next to Xiaomi's list price
| Model | Input | Cached input | Output | Under list |
|---|---|---|---|---|
| MiMo V2.6 Flashmimo-v2.6-flash | $0.084list $0.14 | $0.0025list $0.0028 | $0.09list $0.28 | 40% in · 67% out |
| MiMo V2.6 Promimo-v2.6-pro | $0.261list $0.435 | $0.0038list $0.0036 | $0.30list $0.87 | 40% in · 65% out |
| MiMo-V2.5mimo-v2.5 | $0.084list $0.14 | $0.0017list $0.0028 | $0.168list $0.28 | 40% in · 40% out |
| MiMo-V2.5-Promimo-v2.5-pro | $0.261list $0.435 | $0.0022list $0.0036 | $0.522list $0.87 | 40% in · 40% out |
List price: Xiaomi's published rate, read October 2026. Live from GET https://api.uplinkswitch.com/v1/catalog.
Call them · same base URL and key for every model
Python · OpenAI SDK
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="mimo-v2.6-flash",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)TypeScript · OpenAI SDK
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'mimo-v2.6-flash',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);Questions
- Which MiMo model costs the least?
- MiMo V2.6 Flash (mimo-v2.6-flash): $0.084 per million input tokens and $0.09 per million output tokens.
- How far under Xiaomi's list price is it?
- Input runs 40% under Xiaomi's list price, output 40% to 67%, depending on the model. Each row above shows both prices.
- Is there a subscription?
- No. Prepaid credit from $10, with no subscription or monthly fee. Each top-up locks your prices for 30 days.
- How is cached input billed?
- At the cached rate in the table. A model with no cached rate bills cached tokens at its input rate.
- Are there rate limits?
- Every key carries a request-per-minute limit and a concurrency limit.