LLMKimi K3 API pricing
Kimi K3 by Relace costs $2.00 per 1M input tokens and $14.00 per 1M output tokens (1M in + 1M out = $16.00).
- API model id
moonshotai/kimi-k3- Input / 1M
- $2.00
- Output / 1M
- $14.00
- Cached input / 1M
- $0.30
- Context window
- 1M
- Notes
- Relace-hosted open model (models.relace.ai, OpenAI-compatible), pay as you go in USD per 1M tokens, no minimum. Relace says it reprices often and the API price at request time applies. Listed as context 1M.
- Source
- https://docs.relace.ai/docs/open-models/quickstart
- Provider type
- Inference host (HQ: US)
- Regions
- unknown
- EU data residency
- unknown — Docs do not publish serving regions; careers page says Relace runs requests 'on our own GPU fleet around the world'. OpenRouter's provider list gives no HQ or datacenters.
- Last verified
- 2026-10-26
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Relace | Kimi K3 | $5.50 |
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 Relace models
- DeepSeek V4 Flash 0423: $0.0277 / $1.28
- DeepSeek V4 Flash 0731: $0.07 / $0.14
- DeepSeek V4 Pro 0423 (Preview): $0.45 / $3.00
- DeepSeek V4 Pro 0813: $0.50 / $2.00
- DeepSeek V4.1 Flash: $0.20 / $0.60
- DeepSeek V4.1 Flash 1017: $0.20 / $0.60
- GLM 5.2: $0.40 / $4.00
- GLM 5.3: $0.75 / $2.40