AI model
moonshotai/kimi-k3:fast-reasoning
MoonshotAI: Kimi K3 (fast) (Reasoning) is a 1,048,576-token model served on Composite at $0.345 per million tokens in and $12.0 per million tokens out.
Try in Playground| Model ID | moonshotai/kimi-k3:fast-reasoning |
|---|---|
| Provider | Wafer |
| Context window | 1,048,576 tokens |
| Accepts | text, image, video |
| Returns | text |
| Input price | $0.345 per million tokens |
| Output price | $12.0 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 (fast) (Reasoning) (Reasoning)" in the catalog to turn it on by default |
| Moderated | No |
| Cost on a monthly plan | About 12 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 1 |
Make a Composite API key and type moonshotai/kimi-k3:fast-reasoning 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
This model has not carried enough traffic on Composite yet to publish a success rate, a latency figure or a traffic rank. The numbers appear here once it has.
$0.345 per million tokens input · $12.0 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 12 plan credits, at the provider's own price.
Wafer
Kimi models are tuned for long-context recall, which helps a roleplay stay consistent with events from many messages earlier.
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.
It is priced low enough for high-volume daily roleplay without the per-message cost adding up quickly.
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 Wafer, not written by Composite.
MoonshotAI: Kimi K3.1 Pro · MoonshotAI: Kimi K3 · MoonshotAI: Kimi K2.7 Code