AI model
xiaomi/mimo-v2.6-pro
Xiaomi: MiMo-V2.6-Pro is a 1,050,000-token model served on Composite at $0.408 per million tokens in and $0.816 per million tokens out. Ranked #30 of 179 models by traffic on Composite over the last 30 days, taking 0.76% of tokens and 0.6% of requests (this model and its routing variants). Measured on Composite, 99.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 9976 ms, output runs at about 61.7 tokens per second.
Try in Playground| Model ID | xiaomi/mimo-v2.6-pro |
|---|---|
| Provider | cv11 |
| Context window | 1,050,000 tokens |
| Accepts | text, image, video, audio |
| Returns | text |
| Input price | $0.408 per million tokens |
| Output price | $0.816 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Moderated | No |
| Cost on a monthly plan | About 3.3 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 10 (base plus 9 routing variants) |
Make a Composite API key and type xiaomi/mimo-v2.6-pro as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
#30 of 179
0.76% of tokens and 0.6% of requests over 30 days, including routing variants.
99.0%
Across the last 100 requests Composite served for this model.
9976 ms
Median across the same sample.
61.7 tok/s
Median generation rate after the first token.
59.7%
Share of prompt tokens served from the provider's cache over 7 days.
The same model behind 9 alternative endpoints. Call the id directly to pin a route; the base id above picks for you.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| Normal | xiaomi/mimo-v2.6-pro-normal |
cv11 | $0.544 per million tokens input · $1.09 per million tokens output |
| Normal + cheapThink | xiaomi/mimo-v2.6-pro-normal:cheapThink |
cv11 | $0.544 per million tokens input · $1.09 per million tokens output |
| Cheapest provider | xiaomi/mimo-v2.6-pro:cheapest-provider |
GMICloud | $0.408 per million tokens input · $0.816 per million tokens output |
| Cheapest provider + cheapThink | xiaomi/mimo-v2.6-pro:cheapest-provider:cheapThink |
GMICloud | $0.408 per million tokens input · $0.816 per million tokens output |
| cheapThink | xiaomi/mimo-v2.6-pro:cheapThink |
cv11 | $0.408 per million tokens input · $0.816 per million tokens output |
| Fast | xiaomi/mimo-v2.6-pro:fast |
GMICloud | $0.408 per million tokens input · $0.816 per million tokens output |
| Fast + cheapThink | xiaomi/mimo-v2.6-pro:fast:cheapThink |
GMICloud | $0.408 per million tokens input · $0.816 per million tokens output |
| Quality | xiaomi/mimo-v2.6-pro:quality |
GMICloud | $0.408 per million tokens input · $0.816 per million tokens output |
| Quality + cheapThink | xiaomi/mimo-v2.6-pro:quality:cheapThink |
GMICloud | $0.408 per million tokens input · $0.816 per million tokens output |
$0.408 per million tokens input · $0.816 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 3.3 plan credits, at the provider's own price.
cv11
MiMo models are a newer entrant focused on efficient inference, which tends to show up as lower latency per reply.
With a 1,050,000-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
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...
Supplied by cv11, not written by Composite.
Xiaomi: MiMo-V2.6-Pro-UltraSpeed · Xiaomi: MiMo-V2.6-Flash · Xiaomi: MiMo-V2.5-Pro