MODEL PROOF
MiMo-V2.6-Pro
FRONTIER
Nothing is both better and cheaper under this workload.
Serving precision differs between offers.
- Independent LMArena score
- 1,491 ± 9.37 · 4,056 votes
- Context window
- 1.05M
- Maximum output
- 131.07K
- Input modalities
- text, image, video, audio
- Output modalities
- text
- Published input price
- $0.430 / 1M tokens
- Published output price
- $0.870 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from DeepInfra: the cheapest offer that is serving, at standard delivery and at the maker’s precision or better, at its standard rate.
Every price dimension · USD per million tokens
| Input | $0.430/M |
|---|---|
| Output | $0.870/M |
| Cached input | $0.0036/M |
| Cache write | Unknown/M |
| Cache write 1h | Unknown/M |
| Reasoning | Unknown/M |
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.435/M from GMICloud.
4 provider offers · rates, limits and conditions
Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.
| Seller | Input | Output | Precision | Uptime (1d) |
|---|---|---|---|---|
| DeepInfradeepinfra/fp8 Endpoint terms
| $0.430 | $0.870 | fp8 | 99.88% |
| GMICloudgmicloud/bf16 Endpoint terms
| $0.435 | $0.870 | bf16 | 96.97% |
| Novitanovita/fp8 Endpoint terms
| $0.435 | $0.870 | fp8 | 98.90% |
| Xiaomixiaomi/fp8 Endpoint terms
| $0.435 | $0.870 | fp8 | 99.10% |
Independent scores
| LMArena Elo | 1491default |
|---|
LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero.
Best rankings by task
- Web apps #5 1283
- Code categories #6 1322
- Websites #7 1315
- Data visualisation #7 1345
- UI components #7 1344
- 3D #8 1340
- Game development #10 1325
Per-task Elo and rank from Design Arena, via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list.
Capability
| Context window | 1M |
|---|---|
| Max output | 131K |
| Input modes | text, image, video, audio |
| Tool use | yes |
| Reasoning | optional |
| Open weights | Unknown |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-10-06 |
| Quality data | verified |
MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding...
Questions this page answers
What does MiMo-V2.6-Pro cost?
$0.430/M in, $0.870/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does MiMo-V2.6-Pro have an independent quality score?
MiMo-V2.6-Pro has an LMArena score in this catalogue.
What beats MiMo-V2.6-Pro?
Nothing is both better and cheaper than MiMo-V2.6-Pro.
Does this page use Artificial Analysis scores for MiMo-V2.6-Pro?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
Is the cheapest MiMo-V2.6-Pro endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.435/M from GMICloud.
MODEL MONUMENT
Save or share this proof
Badge
The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not.
[](https://undominated.ai/models/xiaomi__mimo-v2.6-pro/)<a href="https://undominated.ai/models/xiaomi__mimo-v2.6-pro/"><img src="https://undominated.ai/badge/xiaomi__mimo-v2.6-pro.svg" alt="MiMo-V2.6-Pro — Undominated.ai dominance verdict" height="36"></a>Direct file: https://undominated.ai/badge/xiaomi__mimo-v2.6-pro.svg — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never
older than the last deploy.
