Kimi K3.1 Pro API pricing on Liquid Inference
Every Liquid Inference Kimi K3.1 Pro rate we track, compared against 20 providers serving the same model.
The cheapest Kimi K3.1 Pro input price we currently track is $0.240/1M on OpenRelay.
Liquid Inference also has the cheapest Kimi K3.1 Pro output price.
Liquid Inference Kimi K3.1 Pro rates
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Standard | $1.60/1M | $2.40/1M |
About Kimi K3.1 Pro
- Creator
- Moonshot AI
- Modalities
- text
Kimi K3.1 Pro on other providers
- OpenRelay$0.240/1M
- OpenRouter$0.253/1M
- IteraCompute$1.60/1M
- AkashML$1.75/1M
- Deep Infra$1.90/1M
- Baseten$2.00/1M
- DigitalOcean$2.00/1M
- Empirio Labs$2.00/1M
- Fireworks AI$2.00/1M
- GMI Cloud$2.00/1M
- Lyceum$2.00/1M
- Morse$2.00/1M
- Novita AI$2.00/1M
- PopNow$2.00/1M
- Prime Intellect$2.00/1M
- Runpod$2.00/1M
- Together AI$2.00/1M
- HiAPI$2.15/1M
- RouterPlus$2.50/1M
About Liquid Inference
Liquid Inference is an AI exchange platform allowing model providers to compete to fulfill user prompts. Users set their requirements and receive offers from multiple providers.
Frequently Asked Questions
How much does Kimi K3.1 Pro cost on Liquid Inference?
Liquid Inference serves Kimi K3.1 Pro from $1.60 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.
Is Liquid Inference the cheapest way to run Kimi K3.1 Pro?
Liquid Inference ranks #3 of 20 providers we track serving Kimi K3.1 Pro on input price. The cheapest input price right now is on OpenRelay. Liquid Inference also has the lowest Kimi K3.1 Pro output price. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.
Does Liquid Inference offer batch or cached pricing for Kimi K3.1 Pro?
We track 1 Kimi K3.1 Pro offering from Liquid Inference. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.