Kimi K3
Kimi K3 is Moonshot AI's open-weight Mixture-of-Experts model with 2.8T total and 104B active parameters and a 1M-token context window. It accepts text, image and video input and produces text, always reasons with low, high or max effort, and is built for long-horizon coding, knowledge work and reasoning.
Modalities
In / out price
$2.50 / $12.50per 1M
Cached price
$0.25per 1M
Context
1M
Max output
131K
Providers
9 routesCompare providers by price, privacy, and speed.
| TEE | $4.00 | $20.00 | $0.80 | 262K | 33K | — | — | |
| TEE | $3.00 | $15.00 | $0.30 | 1M | 1M | — | — | |
| Private | $3.75 | $18.75 | $0.375 | 1M | 131K | — | — | |
| Private | $3.00 | $15.00 | $0.30 | 1M | 33K | — | — | |
| Private | $2.85 | $14.25 | $0.285 | 1M | 16K | — | — | |
Baseten | Private | $3.00 | $15.00 | $0.30 | 1M | 131K | — | — |
Relace | Private | $2.40 | $14.00 | $0.30 | 1M | 131K | — | — |
Sail | Private | $2.50 | $12.50 | $0.25 | 1M | 131K | — | — |
Wafer | Private | $3.00 | $15.00 | $0.30 | 1M | 131K | — | — |
Privacy
3 / 4Hardware-isolated routing
TEE tier
- Anonymous
- Private
- TEE
- E2EE
Inference runs inside a hardware-isolated, attestable environment. TEE protects processing, but does not by itself mean the client encrypted the request end to end. Learn more
Features
5Streaming
Tool calling
Vision
Reasoning
Confidential compute
Uptime
FAQ
Common questions about Kimi K3.