- Good as a general-purpose model for text generation and everyday reasoning.
- Good when you want package quota first, with pay-as-you-go enabled by key configuration.
Moonshot active
Kimi K3 API Pricing and Package Multipliers
Model
kimi-k3 Kimi K3
Kimi K3 API Pricing
Official base: Input 3 / Output 15 / Cache read 0.3
| Channel | Billing unit | Quota multiplier | Final discount |
|---|---|---|---|
| Kimi | USD / 1M | 5.376x | 20% off |
Cache hits are billed at the cache read price. Cache writes use the cache write price, and the Console usage detail shows the final cost breakdown.
Kimi K3 available packages and multipliers
| Package | Channel | Billing unit | Quota multiplier | Final discount |
|---|---|---|---|---|
| Lite | Kimi | USD / 1M | 48.4545x | 1.17× official |
| Plus | Kimi | USD / 1M | 48.4545x | 1.05× official |
| Pro | Kimi | USD / 1M | 48.4545x | 2% off |
| Max | Kimi | USD / 1M | 48.4545x | 15.9% off |
| Super Ultra | Kimi | USD / 1M | 48.4545x | 31.5% off |
| Ultra | Kimi | USD / 1M | 48.4545x | 29.9% off |
| SU500 | Kimi | USD / 1M | 48.4545x | 35.3% off |
| SU750 | Kimi | USD / 1M | 48.4545x | 36.2% off |
| SU1000 | Kimi | USD / 1M | 48.4545x | 35.3% off |
Kimi K3 OpenAI-compatible API access
After creating a key in the console, call this model with the unified model name kimi-k3. When package and pay-as-you-go balance are both available, package quota is used first.
model: "kimi-k3"
- Not ideal for legacy integrations that only accept OpenAI-compatible APIs.
- Not ideal when you need dedicated SLA terms, private capacity, or a fixed-cost enterprise commitment.
This model is available through the public catalog and unified gateway pricing configuration.
Open this model in the console
The public model page is for discovery and comparison. Actual API access, key creation, and model scopes are managed after sign-in.