LLMKimi K3 API pricing
Kimi K3 by Makora costs $2.55 per 1M input tokens and $12.75 per 1M output tokens (1M in + 1M out = $15.30).
- API model id
Kimi-K3- Input / 1M
- $2.55
- Output / 1M
- $12.75
- Cached input / 1M
- $0.26
- Context window
- 256K
- Notes
- MakoraInference pay-as-you-go (OpenAI-compatible), USD per 1M tokens as listed on the Makora home page model cards. Starter ($20/mo) and Developer ($200/mo) plans were sold out on 2026-10-27; Developer gives 10% off pay-as-you-go.
- Source
- https://makora.com/
- Provider type
- Inference host (HQ: US)
- Regions
- US
- EU data residency
- no — Privacy Policy subprocessor list: inference hosting on AWS and TensorWave in the United States (transient processing for zero-data-retention content). EU/UK representatives are still being appointed.
- Last verified
- 2026-11-12
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Makora | Kimi K3 | $5.74 |
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 Makora models
- DeepSeek V4 Flash 0731: $0.09 / $0.20
- Gemma 4 26B A4B: $0.10 / $0.34
- GLM-5.2 (FP8): $0.94 / $2.80
- GLM-5.2 (NVFP4): $0.72 / $2.38