Kimi K3 Fast
Moonshot AI
Fast version of Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window.
- Language
- Reasoning
- Tool use
- Implicit caching
- File input
- Vision
- Context
- 1M
- Max output
- 131K
- Input / 1M
- $4.50
- Output / 1M
- $22.50
Quickstart
Point any OpenAI-compatible client at Maxynetic Systems and pass moonshotai/kimi-k3-fast as the model.
curl https://api.maxynetic.com/v1/chat/completions \
-H "Authorization: Bearer $MAXYNETIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/kimi-k3-fast",
"messages": [{ "role": "user", "content": "Explain routing in one line." }]
}'Pricing
Billed per token with no markup on the underlying provider rate.
Input
Per 1M prompt tokens
$4.50
Output
Per 1M completion tokens
$22.50
Cache read
Per 1M cached prompt tokens
$0.450
A 1M-token prompt with 250K tokens of output costs about $10.13.