Home › VastLLM Catalog › Kimi K3
Kimi K3
by Moonshot AI · Language Models
Context 1049K tokensReasoning / thinkingFunction calling
by Moonshot AI · Language Models
Kimi K3 is an open-weight, native multimodal model developed by Moonshot AI. It has 2.8 trillion total parameters and is built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a context window of up to 1 million tokens. It is designed for long-horizon coding, knowledge work, and reasoning.
$2.3166 in · $11.583 out · $0.2317 cached / 1M
| Usage | Rate (USD) | Unit |
|---|---|---|
| Input tokens | $2.3166 | per 1M tokens |
| Cached input (cache hit) | $0.2317 | per 1M tokens |
| Output tokens | $11.583 | per 1M tokens |
Official model pricing · currency: USD · pre-deduction settled by actual usage
OpenAI-compatible · base URL https://api.tunerouter.com/v1/
curl https://api.tunerouter.com/v1/chat/completions \
-H "Authorization: Bearer $TUNEROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "kimi-k3", "messages": [{"role": "user", "content": "Hello!"}]}'Model ID: kimi-k3 · works with OpenAI SDKs — just point base_url at api.tunerouter.com