Kimi K2 Thinking API pricing on OpenRouter
Every OpenRouter Kimi K2 Thinking rate we track, compared against 5 providers serving the same model.
The cheapest Kimi K2 Thinking input price we currently track is $0.600/1M on Amazon AWS.
The cheapest Kimi K2 Thinking output price is $1.20/1M on GMI Cloud.
OpenRouter Kimi K2 Thinking rates
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Standard | $0.600/1M | $2.50/1M |
About Kimi K2 Thinking
- Creator
- Moonshot AI
- Modalities
- text
- Open weights
- Yes
Kimi K2 Thinking on other providers
About OpenRouter
OpenRouter provides a unified API for accessing hundreds of AI models from multiple providers. It aggregates models from OpenAI, Anthropic, Google, Meta, Mistral, and many others, offering a single endpoint with automatic fallback routing and provider optimization.
Frequently Asked Questions
How much does Kimi K2 Thinking cost on OpenRouter?
OpenRouter serves Kimi K2 Thinking from $0.600 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 OpenRouter the cheapest way to run Kimi K2 Thinking?
OpenRouter ranks #1 of 5 providers we track serving Kimi K2 Thinking on input price. The cheapest input price right now is on Amazon AWS. The lowest output price is $1.20/1M on GMI Cloud. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.
Does OpenRouter offer batch or cached pricing for Kimi K2 Thinking?
We track 1 Kimi K2 Thinking offering from OpenRouter. 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.