Traffic rank on Composite
#6 of 194
4.33% of tokens and 4.12% of requests over 30 days, including routing variants.
AI model
MoonshotAI: Kimi K3
moonshotai/kimi-k3
MoonshotAI: Kimi K3 is a 1,048,576-token model served on Composite at $0.228 per million tokens in and $11.7 per million tokens out. Ranked #6 of 194 models by traffic on Composite over the last 30 days, taking 4.33% of tokens and 4.12% of requests (this model and its routing variants). Measured on Composite, 100.0% of its last 100 requests on Composite succeeded, the typical first token arrives in 22505 ms, output runs at about 321.6 tokens per second.
Try in PlaygroundSpecifications
| Model ID | moonshotai/kimi-k3 |
|---|---|
| Provider | cv11 |
| Context window | 1,048,576 tokens |
| Accepts | text, image, video |
| Returns | text |
| Input price | $0.228 per million tokens |
| Output price | $11.7 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Thinking | Optional - see "MoonshotAI: Kimi K3 (Reasoning)" in the catalog to turn it on by default |
| Moderated | No |
| Cost on a monthly plan | About 11 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 10 (base plus 9 routing variants) |
Success rate
100.0%
Across the last 100 requests Composite served for this model.
Time to first token
22505 ms
Median across the same sample.
Output speed
321.6 tok/s
Median generation rate after the first token.
Prompt cache hits
58.5%
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.
| Route | Model ID | Provider | Price |
|---|---|---|---|
| Normal | moonshotai/kimi-k3-normal |
cv11 | $0.240 per million tokens input · $18.8 per million tokens output |
| Normal + cheapThink | moonshotai/kimi-k3-normal:cheapThink |
cv11 | $0.240 per million tokens input · $18.8 per million tokens output |
| Cheapest provider | moonshotai/kimi-k3:cheapest-provider |
Relace | $0.228 per million tokens input · $11.7 per million tokens output |
| Cheapest provider + cheapThink | moonshotai/kimi-k3:cheapest-provider:cheapThink |
Relace | $0.228 per million tokens input · $11.7 per million tokens output |
| cheapThink | moonshotai/kimi-k3:cheapThink |
cv11 | $0.228 per million tokens input · $11.7 per million tokens output |
| Fast | moonshotai/kimi-k3:fast |
Relace | $0.228 per million tokens input · $11.7 per million tokens output |
| Fast + cheapThink | moonshotai/kimi-k3:fast:cheapThink |
Relace | $0.228 per million tokens input · $11.7 per million tokens output |
| Quality | moonshotai/kimi-k3:quality |
Morph | $1.44 per million tokens input · $18.3 per million tokens output |
| Quality + cheapThink | moonshotai/kimi-k3:quality:cheapThink |
Morph | $1.44 per million tokens input · $18.3 per million tokens output |
Pricing
$0.228 per million tokens input · $11.7 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 11 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 is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
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.
Related models
MoonshotAI: Kimi K3.1 Pro · MoonshotAI: Kimi K2.7 Code · MoonshotAI: Kimi K2.6