LLMKimi K3 API pricing
Kimi K3 by Wafer costs $0.60 per 1M input tokens and $15.00 per 1M output tokens (1M in + 1M out = $15.60).
- API model id
Kimi-K3- Input / 1M
- $0.60
- Output / 1M
- $15.00
- Cached input / 1M
- $0.20
- Context window
- 1.05M
- Notes
- Wafer Serverless (OpenAI/Anthropic-compatible, pass.wafer.ai/v1), list price from Wafer's public model catalog (US cents per 1M, shown as USD per 1M); prepaid credits. Wafer reprices often.
- Source
- https://pass.wafer.ai/v1/models
- Provider type
- Inference host (HQ: US)
- Regions
- unknown
- EU data residency
- unknown — Models are self-hosted on the 'Wafer fleet'; serving regions are not published. Zero Data Retention can be required per request.
- Last verified
- 2026-11-12
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Wafer | Kimi K3 | $4.35 |
Uses standard list prices (no caching, batch or off-peak discounts). €, CHF and ₹ rows are priced in that currency by the provider and not converted, so compare them with care. ₹ rows also show ≈ USD at the RBI reference rate of ₹93.8579 per USD (2026-11-09).
Other Wafer models
- GLM-5.2: $0.19 / $4.40
- GLM-5.3: $0.20 / $1.80
- Qwen3.8 27B: $0.06 / $2.30
- GLM-5.3 Flash: $0.05 / $0.20
- DeepSeek V4 Pro: $0.28 / $3.96
- DeepSeek V4.1 Flash: $0.19 / $0.65
- DeepSeek V4 Flash 0423: $0.14 / $0.28
- DeepSeek V4.1 Flash 1017: $0.13 / $0.50