Back to models
Kimi K3 vs Kimi K2.8 Preview
Kimi K3 and Kimi K2.8 Preview: current price, context, max output, and supported operations.
Pricing comparison
| Kimi K3 | Kimi K2.8 Preview | |
|---|---|---|
| Model maker | Moonshot | Moonshot |
| Delivery availability | Available | Available |
| Context window | 1M | 1M |
| Max output | 128K | 1M |
| Official price | Input$3.00per 1M tokensOutput$15.00per 1M tokens | Input$1.00per 1M tokensOutput$4.00per 1M tokens |
| Verified price | — | — |
| Model performance |
| Collecting data |
| Capabilities | JSON modePrompt CacheReasoningTool useVision | VisionTool usePrompt Cache |
Summary
- Kimi K3: —; Kimi K2.8 Preview: —. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
- Kimi K2.8 Preview supports 7.6x more output tokens
FAQ
Which is cheaper, Kimi K3 or Kimi K2.8 Preview?
Kimi K3: —; Kimi K2.8 Preview: —. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
What are the key differences between Kimi K3 and Kimi K2.8 Preview?
Kimi K3: JSON mode, Reasoning