Compositev12
← All models Model directory

AI model

MoonshotAI: Kimi K2.5

moonshotai/kimi-k2.5

MoonshotAI: Kimi K2.5 is a 262,144-token model served on Composite at $0.612 per million tokens in and $3.13 per million tokens out. Ranked #21 of 196 models by traffic on Composite over the last 30 days, taking 1.19% of tokens and 1.46% of requests (this model and its routing variants). Measured on Composite, 90.7% of its last 97 requests on Composite succeeded, the typical first token arrives in 38496 ms, output runs at about 64.8 tokens per second.

Try in Playground

Community rating

— No community ratings yet.

Sign in to rate this model. Ratings come from accounts that have run requests through Composite.

Specifications

Specifications and pricing as served by Composite
Model IDmoonshotai/kimi-k2.5
Providercv11
Context window262,144 tokens
Acceptstext, image
Returnstext
Input price$0.612 per million tokens
Output price$3.13 per million tokens
Prompt cachingSupported — cached input is billed at the provider's cache rate, on credits and plans alike
ModeratedNo
Cost on a monthly planAbout 6.4 plan credits per typical call (8k in, 1k out)
Routing endpoints10 (base plus 9 routing variants)

Traffic rank on Composite

#21 of 196

1.19% of tokens and 1.46% of requests over 30 days, including routing variants.

Success rate

90.7%

Across the last 97 requests Composite served for this model.

Time to first token

38496 ms

Median across the same sample.

Output speed

64.8 tok/s

Median generation rate after the first token.

Prompt cache hits

18.6%

Share of prompt tokens served from the provider's cache over 7 days.

Routing variants

The same model behind 9 alternative endpoints. Call the id directly to pin a route; the base id above picks for you.

RouteModel IDProviderPrice
Normal moonshotai/kimi-k2.5-normal cv11 $0.625 per million tokens input · $3.13 per million tokens output
Normal + cheapThink moonshotai/kimi-k2.5-normal:cheapThink cv11 $0.625 per million tokens input · $3.13 per million tokens output
Cheapest provider moonshotai/kimi-k2.5:cheapest-provider AtlasCloud $0.612 per million tokens input · $3.13 per million tokens output
Cheapest provider + cheapThink moonshotai/kimi-k2.5:cheapest-provider:cheapThink AtlasCloud $0.612 per million tokens input · $3.13 per million tokens output
cheapThink moonshotai/kimi-k2.5:cheapThink cv11 $0.612 per million tokens input · $3.13 per million tokens output
Fast moonshotai/kimi-k2.5:fast SiliconFlow $0.625 per million tokens input · $3.13 per million tokens output
Fast + cheapThink moonshotai/kimi-k2.5:fast:cheapThink SiliconFlow $0.625 per million tokens input · $3.13 per million tokens output
Quality moonshotai/kimi-k2.5:quality AtlasCloud $0.612 per million tokens input · $3.13 per million tokens output
Quality + cheapThink moonshotai/kimi-k2.5:quality:cheapThink AtlasCloud $0.612 per million tokens input · $3.13 per million tokens output

Pricing

$0.612 per million tokens input · $3.13 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 6.4 plan credits, at the provider's own price.

Provider

cv11

Roleplay fit

Kimi models are tuned for long-context recall, which helps a roleplay stay consistent with events from many messages earlier.

Context behavior

With a 262,144-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.

Cost for regular use

It sits in the mid-range on price, a reasonable pick for regular roleplay use without going for the cheapest option available.

From the provider

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

Supplied by cv11, not written by Composite.