Early access: features, availability, and pricing may change as Kyara Intelligence evolves.

All models
Above baseline Reasoning

MoonshotAI: Kimi K3

Moonshot AI's 2.8T multimodal flagship for million-token, long-horizon RP.

Model ID moonshotai/kimi-k3
Quick start

Drop this model into any OpenAI-compatible client by setting the base URL, your API key, and the model ID below.

curl https://api.kyara-intelligence.com/v1/chat/completions \
  -H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k3",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'
See the full API reference
Overview

Kimi K3 is Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model, built for complex coding, knowledge work, and long-horizon agentic workflows. Its 1,048,576-token context window can hold expansive lore, complete character histories, and intricate multi-session plots, while image understanding and configurable reasoning support visually grounded scenes and deeper narrative planning.

Specifications
Context / Memory 🌌 Extreme · 1M tokens
Cost vs baseline Above baseline
Input
6.9x
Output
13x
Input
54M
cr / M tokens
Output
270M
cr / M tokens

Multiples are relative to the catalog median; bars are scaled to the most expensive model.

Model ID
moonshotai/kimi-k3
Reasoning
Available
Status
Current
Upstream moderation

All models on Kyara Intelligence are accessed through their original API providers (Mistral, Z.AI/GLM, xAI, DeepSeek, and others). Each provider's content policies and moderation apply to all requests.

Kyara routes API calls without modifying inputs or outputs, and does not log prompt or response content. Users are responsible for complying with the relevant provider's terms of service in addition to Kyara's terms.