K
Kimi K3 on Vidman AI
kimi-k3
+50%First top-up
Get 50% extra on your first wallet top-up.
Create an account1M contextVisionTool callingReasoning
Pricing
₹ per 1M tokens · as of 29 August 2026| Input | ₹283.65 |
| Output | ₹1418.25 |
| Cached input | ₹28.37 |
Flat rate — every request bills the same. Full catalog and comparisons on the pricing comparison page.
Where it fits
Kimi’s flagship: 1M context, vision, and reasoning at a premium rate. The open-weights answer when the task needs everything at once.
Not sure? Vidman AI Adaptive routes to the best model per request, including this one.
Call it now — OpenAI-compatible
curl https://api.vidman.ai/v1/chat/completions \
-H "Authorization: Bearer $VIDMAN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k3",
"messages": [{ "role": "user", "content": "Hello" }]
}'Existing OpenAI SDK code works by changing the base URL to https://api.vidman.ai/v1 and the key.