Kimi K3 API pricing
Kimi K3 by DigitalOcean 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
- $0.30
- Context window
- —
- Notes
- DigitalOcean Inference (Gradient AI) serverless, standard mode. Also resells Anthropic/OpenAI models (not listed here).
- Source
- https://docs.digitalocean.com/products/gradient-ai-platform/details/pricing/
- Provider type
- Cloud (HQ: US)
- Regions
- unknown
- EU data residency
- unknown — Serverless inference regions are not listed; the availability page lists Dedicated Inference in NYC2, TOR1, ATL1 and RIC1 only. DigitalOcean-hosted models run entirely on DigitalOcean infrastructure and inputs/outputs are not stored (Data Privacy page).
- Last verified
- 2026-10-16
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| DigitalOcean | 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 DigitalOcean models
- gpt-oss-120b: $0.10 / $0.70
- gpt-oss-20b: $0.05 / $0.45
- Qwen3.8-Max: $2.00 / $6.00
- Qwen 3.5 397B A17B: $0.55 / $3.50
- DeepSeek V4.1 Flash: $0.30 / $1.20
- DeepSeek V4 Pro 0813: $1.32 / $3.96
- DeepSeek V4 Flash 0731: $0.14 / $0.28
- Llama 4 Maverick 17B 128E Instruct: $0.25 / $0.87