Kimi K3 API pricing
Kimi K3 by Lyceum costs $3.00 per 1M input tokens and $15.00 per 1M output tokens (1M in + 1M out = $18.00).
- API model id
Kimi K3- Input / 1M
- $3.00
- Output / 1M
- $15.00
- Cached input / 1M
- $0.75
- Context window
- —
- Notes
- Lyceum serverless inference (EU), USD per 1M tokens, no base fee.
- Source
- https://lyceum.technology/pricing
- Provider type
- Inference host (HQ: Germany)
- Regions
- Europe
- EU data residency
- yes — Trust page: prompts and outputs not stored, never used for training, European data centres; service run by Lyceum Technology Germany GmbH (Berlin) and Lyceum Switzerland GmbH (Zurich). GPU capacity listed in Central and Western Europe. Prices published in USD.
- Last verified
- 2026-10-16
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Lyceum | Kimi K3 | $6.75 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Other Lyceum models
- GLM-5.3 Flash: $0.20 / $0.50
- DeepSeek V4 Flash: $0.25 / $0.30
- MiniMax M3: $0.40 / $2.00
- Qwen3.8 27B: $0.40 / $2.40
- DeepSeek V4.1 Flash: $0.50 / $1.50
- Kimi K2.7 Code: $1.25 / $4.50
- GLM-5.3: $1.40 / $4.40
- GLM-5.2: $1.50 / $4.50