Kimi K3
Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback.
Modalities
In / out price
$2.85 / $14.25
per 1M
Cached price
$0.285
per 1M
Context
1M
Max output
16K
Released
Jul 16, 2026
Providers
4 routesThe same model can have different pricing and privacy guarantees depending on who serves it. The model's headline privacy uses the strongest available route below. Discovered routes awaiting approval remain listed as not live.
| Provider | Privacy | Input / 1M | Output / 1M | Cache read / 1M | Context | Max output | Uptime | Latency | Throughput |
|---|---|---|---|---|---|---|---|---|---|
| TEE | $4.00 | $20.00 | — | 262K | 33K | — | — | — | |
| 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 | — | — | — |
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