Compositev12
← All models Model directory

AI model

MoonshotAI: Kimi K3

moonshotai/kimi-k3

MoonshotAI: Kimi K3 is a 1,048,576-token model served on Composite at $0.912 per million tokens in and $12.5 per million tokens out. Ranked #2 of 196 models by traffic on Composite over the last 30 days, taking 8.77% of tokens and 12.62% of requests (this model and its routing variants). Measured on Composite, 22.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 2447 ms, output runs at about 35.2 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-k3
Providercv11
Context window1,048,576 tokens
Acceptstext, image, video
Returnstext
Input price$0.912 per million tokens
Output price$12.5 per million tokens
Prompt cachingSupported — cached input is billed at the provider's cache rate, on credits and plans alike
ThinkingOptional - see "MoonshotAI: Kimi K3 (Reasoning)" in the catalog to turn it on by default
ModeratedNo
Cost on a monthly planAbout 16 plan credits per typical call (8k in, 1k out)
Routing endpoints10 (base plus 9 routing variants)

Traffic rank on Composite

#2 of 196

8.77% of tokens and 12.62% of requests over 30 days, including routing variants.

Success rate

22.0%

Across the last 100 requests Composite served for this model.

Time to first token

2447 ms

Median across the same sample.

Output speed

35.2 tok/s

Median generation rate after the first token.

Prompt cache hits

16.4%

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-k3-normal cv11 $0.912 per million tokens input · $12.5 per million tokens output
Normal + cheapThink moonshotai/kimi-k3-normal:cheapThink cv11 $0.912 per million tokens input · $12.5 per million tokens output
Cheapest provider moonshotai/kimi-k3:cheapest-provider InferenceNet $0.912 per million tokens input · $12.5 per million tokens output
Cheapest provider + cheapThink moonshotai/kimi-k3:cheapest-provider:cheapThink InferenceNet $0.912 per million tokens input · $12.5 per million tokens output
cheapThink moonshotai/kimi-k3:cheapThink cv11 $0.912 per million tokens input · $12.5 per million tokens output
Fast moonshotai/kimi-k3:fast InferenceNet $0.912 per million tokens input · $12.5 per million tokens output
Fast + cheapThink moonshotai/kimi-k3:fast:cheapThink InferenceNet $0.912 per million tokens input · $12.5 per million tokens output
Quality moonshotai/kimi-k3:quality Morph $1.25 per million tokens input · $18.6 per million tokens output
Quality + cheapThink moonshotai/kimi-k3:quality:cheapThink Morph $1.25 per million tokens input · $18.6 per million tokens output

Pricing

$0.912 per million tokens input · $12.5 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 16 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 1,048,576-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 K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

Supplied by cv11, not written by Composite.