AI model
minimax/minimax-m2.5
MiniMax: MiniMax M2.5 is a 200,000-token model served on Composite at $0.338 per million tokens in and $1.19 per million tokens out. Ranked #53 of 179 models by traffic on Composite over the last 30 days, taking 0.14% of tokens and 0.22% of requests. Measured on Composite, 100.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 8638 ms, output runs at about 59.8 tokens per second.
Try in Playground| Model ID | minimax/minimax-m2.5 |
|---|---|
| Provider | cv11 |
| Context window | 200,000 tokens |
| Accepts | text |
| Returns | text |
| Input price | $0.338 per million tokens |
| Output price | $1.19 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Thinking | Always on for this model |
| Moderated | No |
| Cost on a monthly plan | About 3.1 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 10 (base plus 9 routing variants) |
Make a Composite API key and type minimax/minimax-m2.5 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
#53 of 179
0.14% of tokens and 0.22% of requests over 30 days.
100.0%
Across the last 100 requests Composite served for this model.
8638 ms
Median across the same sample.
59.8 tok/s
Median generation rate after the first token.
43.9%
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 | minimax/minimax-m2.5-normal |
cv11 | $0.338 per million tokens input · $1.35 per million tokens output |
| Normal + cheapThink | minimax/minimax-m2.5-normal:cheapThink |
cv11 | $0.338 per million tokens input · $1.35 per million tokens output |
| Cheapest provider | minimax/minimax-m2.5:cheapest-provider |
Venice | $0.338 per million tokens input · $1.19 per million tokens output |
| Cheapest provider + cheapThink | minimax/minimax-m2.5:cheapest-provider:cheapThink |
Venice | $0.338 per million tokens input · $1.19 per million tokens output |
| cheapThink | minimax/minimax-m2.5:cheapThink |
cv11 | $0.338 per million tokens input · $1.19 per million tokens output |
| Fast | minimax/minimax-m2.5:fast |
Venice | $0.338 per million tokens input · $1.19 per million tokens output |
| Fast + cheapThink | minimax/minimax-m2.5:fast:cheapThink |
Venice | $0.338 per million tokens input · $1.19 per million tokens output |
| Quality | minimax/minimax-m2.5:quality |
AtlasCloud | $0.369 per million tokens input · $1.50 per million tokens output |
| Quality + cheapThink | minimax/minimax-m2.5:quality:cheapThink |
AtlasCloud | $0.369 per million tokens input · $1.50 per million tokens output |
$0.338 per million tokens input · $1.19 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 3.1 plan credits, at the provider's own price.
cv11
This model is available on Composite alongside dozens of others from other labs, so it is easy to compare against similar options.
With a 200,000-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.
MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...
Supplied by cv11, not written by Composite.
Composite Anthropic Router · Composite Gemini Router · Composite GPT Router