Y-API vs Xiaomi MiMo
xiaomi/mimo-v2.5 — Free — no credit deducted. Every call to these models deducts nothing from your balance. Same base_url, same key, same SDK — the model field is the only thing you change, so they are also the fastest way to try Y-API before you top up. Xiaomi MiMo is the vendor that builds the model itself, so this is not two labs competing — it is one question. For the three models both of us sell, does going through Y-API cost less? Both columns below are cash per 1M input tokens, and Xiaomi MiMo’s side is the cheapest tier we could find on its own price list, which makes every multiple a floor rather than a headline.
| Dimension | Y-API | Xiaomi MiMo |
|---|---|---|
| API protocol | Y-APIOpenAI Chat Completions. Point base_url at https://api.y-api.bestvirtualgoods.com/v1, swap the key, leave the rest of your code alone. | Xiaomi MiMoAn OpenAI-compatible endpoint of its own, on a different base URL and with different model strings — see the row for each model below. |
| Models on one key | Y-API47 model IDs from 10 vendors, one balance, one key. | Xiaomi MiMoIts own published catalog. Of the 3 models we compare against it, 3 are priced there. |
| xiaomi/mimo-v2.5 — Input / 1M tokens | Y-API$0.00 — Free — no credit deducted | Xiaomi MiMo$0.14 (mimo-v2.5) · a cheaper cache-hit tier also exists |
| xiaomi/mimo-v2.6-flash — input / 1M tokens | Y-API$0.018 in cash | Xiaomi MiMo$0.16 as mimo-v2.6-flash — 8.89× ours |
| xiaomi/mimo-v2.6-pro — input / 1M tokens | Y-API$0.05 in cash | Xiaomi MiMo$0.435 as mimo-v2.6-pro — 8.7× ours (a cheaper cache-hit tier also exists) |
| What a top-up converts to | Y-API$1 becomes $10 of account credit, then credit is deducted at each model’s own rate. | Xiaomi MiMoYou pay the list price in cash. There is no credit multiplier, and nothing to expire. |
| Cache-hit pricing | Y-APINo cache discount. A repeated prompt is billed exactly like a new one. | Xiaomi MiMoA discounted rate for cached input, below our cash price on 1 of the 2 models compared here — see “Where Xiaomi MiMo costs less”. |
Against us
Where Xiaomi MiMo costs less
A comparison that only runs one way is an advertisement. Everything below comes from the same price list as the figures above. Free status is set by our upstream provider and can be withdrawn — when it is, these calls start billing at the listed rate and your code does not change. The models page always shows the current state.
xiaomi/mimo-v2.6-pro: cache hits
Xiaomi MiMo bills cached input at $0.0036 per 1M tokens. Our cash price is $0.05 with no cache tier at all, so on a workload where most of the prompt repeats, Xiaomi MiMo is the cheaper of the two on this model.
We have no cache discount at all
For paid models, every request is billed at the full rate whether or not the prompt is identical to the last one. Long fixed system prompts and repeated document context are exactly where that hurts.
Xiaomi MiMo builds the model
New versions, quota increases and behaviour changes land there first, and its own API may expose parameters we do not pass through. We are one hop further from the model than they are, and that hop is ours to explain when something breaks.
Fit
Which one to call
Call it through Y-API if
- xiaomi/mimo-v2.5 — Free — no credit deducted
- Your input is mostly fresh, where the gap is 8.89× on xiaomi/mimo-v2.6-flash and 8.7× on xiaomi/mimo-v2.6-pro at the current top-up rate.
- You want one balance and one key across 47 models from 10 vendors instead of an account per vendor.
- Your prompts change every call, so Xiaomi MiMo’s cache discount would not apply to you anyway.
Go to Xiaomi MiMo if
- Your workload is cache-heavy: its cached-input rate is below our cash price on 1 of the 3 models compared here.
- You need the newest build the day it ships, or a parameter that only the vendor’s own API exposes.
- You want the billing relationship, the SLA and the support to be with Xiaomi MiMo rather than with a reseller.
FAQ
Questions people ask before switching
- Free models
- xiaomi/mimo-v2.5 — Free — no credit deducted. Every call to these models deducts nothing from your balance. Same base_url, same key, same SDK — the model field is the only thing you change, so they are also the fastest way to try Y-API before you top up. Free status is set by our upstream provider and can be withdrawn — when it is, these calls start billing at the listed rate and your code does not change. The models page always shows the current state.
- Is Y-API cheaper than Xiaomi MiMo?
- On fresh input, yes: xiaomi/mimo-v2.6-flash runs $0.018 against their $0.16 and xiaomi/mimo-v2.6-pro runs $0.05 against their $0.435. Two things bound that. Their side is always the cheapest tier they publish, so each multiple is a floor rather than a peak; and the gap depends on the 1:10 top-up rate. For scale: our cheapest paid model starts at $0.01 per 1M input tokens.
- Why is it cheaper — are you buying below their price?
- No, and the honest answer matters here. For paid models, our catalog rates, read as credit, sit close to Xiaomi MiMo’s cash list prices. Almost the whole gap is the top-up conversion: $1 buys $10 of credit.
- Which models does Xiaomi MiMo price against ours?
- It prices 3 of our 47, with the name each one carries there: xiaomi/mimo-v2.5 (mimo-v2.5 there), xiaomi/mimo-v2.6-flash (mimo-v2.6-flash there) and xiaomi/mimo-v2.6-pro (mimo-v2.6-pro there). Those are the only rows in the table above — a row with a published price on one side only is not a comparison.
- How much of my code has to change?
- base_url, the key, and the model string. Both sides speak OpenAI Chat Completions, so nothing else in the request body changes — ours are prefixed, for example xiaomi/mimo-v2.5.
- Is Y-API up right now — where is the status page?
- Availability is not a row in the table above because it changes by the hour. Live status of the website, the gateway and account sign-up, plus incident history and 7/30-day uptime, is on the status page at https://y-api.bestvirtualgoods.com/status.
Provenance
Sources
Every Xiaomi MiMo figure on this page was read from the page below on 2026-10-11, at the cheapest tier it publishes. Our own figures are on our pricing and terms pages.
Point one call at it
Change base_url, the key, and the model string on a single call you already make. The request log will tell you what it costs before you move anything else.