AI model
xiaomi/mimo-v2.5:free
Xiaomi: MiMo-V2.5 (Free) is a 1,000,000-token model free on Composite. Ranked #27 of 179 models by traffic on Composite over the last 30 days, taking 0.43% of tokens and 0.47% of requests. 0 up and 1 down from 1 vote. A positive score is published once a model reaches 5 votes. Measured on Composite, 89.5% of its last 57 requests on Composite succeeded, the typical first token arrives in 8874 ms, output runs at about 41.3 tokens per second.
Try in Playground| Model ID | xiaomi/mimo-v2.5:free |
|---|---|
| Provider | cv11 |
| Context window | 1,000,000 tokens |
| Accepts | text, audio, image, video |
| Returns | text |
| Input price | Included in free allowance |
| Output price | Included in free allowance |
| 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 | Free - does not spend plan credits |
| Routing endpoints | 1 |
Make a Composite API key and type xiaomi/mimo-v2.5:free 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.
Xiaomi: MiMo-V2.5 (Free) guide · JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
#27 of 179
0.43% of tokens and 0.47% of requests over 30 days.
89.5%
Across the last 57 requests Composite served for this model.
8874 ms
Median across the same sample.
41.3 tok/s
Median generation rate after the first token.
4.9%
Share of prompt tokens served from the provider's cache over 7 days.
Free - 80 requests/day shared across free models; each call counts as 80
Credits pay the provider’s price plus 25%; cache hits cost less.
Monthly plans serve this model without spending any of their included credits.
cv11
MiMo models are a newer entrant focused on efficient inference, which tends to show up as lower latency per reply.
With a 1,000,000-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 free on Composite, which makes it a reasonable place to test a character card, preset or lorebook before connecting your own provider.
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...
Supplied by cv11, not written by Composite.
Xiaomi: MiMo-V2.6-Pro-UltraSpeed · Xiaomi: MiMo-V2.6-Flash · Xiaomi: MiMo-V2.6-Pro