# Kimi K3.1 Pro pricing: $2 input, $10 output per million tokens

> Moonshot's flagship costs a third less than Kimi K3, with a flat rate across its 1M-token context window and cached input at $0.20.

URL: https://claudegpt.si/news/kimi-k3-1-pro-pricing  
Published: 2026-10-27T06:52:10.863Z  
Author: ClaudeGPT Si Newsroom  
Section: AI Models  
Topics: Moonshot AI, Kimi, Kimi K3.1 Pro, API pricing, Open-weight models  
Publisher: ClaudeGPT Si

## Key takeaways

- As of October 27, 2026, Kimi K3.1 Pro costs $2.00 per million input tokens and $10.00 per million output tokens on Moonshot's API.
- Cached input is $0.20 per million tokens, and the 1,048,576-token context window has no price tiers.
- Kimi K3 is listed at $3.00 input and $15.00 output, and K3.1 Pro Highspeed at $4.00 and $20.00.

Kimi K3.1 Pro pricing is $2.00 per million input tokens and $10.00 per million output tokens, as of October 27, 2026, according to [Moonshot's pricing page](https://platform.kimi.ai/docs/pricing/chat). Cached input costs $0.20 per million tokens. The price is flat across the model's full 1,048,576-token context window.

That makes K3.1 Pro cheaper than its predecessor. Moonshot's page lists Kimi K3 at $3.00 input and $15.00 output as of the same date. The model launched on October 23, and we covered the [open-weights plan](https://claudegpt.si/news/kimi-k3-1-pro-open-weights-nov-4) at the time.

## How much Kimi K3.1 Pro costs on Moonshot's API

All prices are per million tokens (MTok), as of October 27, 2026, and exclude taxes.

| Model | Input | Output | Cached input | Cache write, 5 min | Cache write, 1 hour |
| --- | --- | --- | --- | --- | --- |
| kimi-k3.1-pro | $2.00 | $10.00 | $0.20 | $2.00 | $4.00 |
| kimi-k3.1-pro-highspeed | $4.00 | $20.00 | $0.20 | $4.00 | $8.00 |
| kimi-k3 | $3.00 | $15.00 | $0.30 | $3.00 | $6.00 |

The Highspeed variant, which Moonshot says runs 2 to 3 times faster than K3.1 Pro, costs exactly double on input and output. Its cached-input price is the same as the standard model's.

Moonshot's quickstart says there is no tiering by context length. A prompt that fills the million-token window is billed at the same per-token rate as a short one.

## What OpenRouter charges

OpenRouter's model listing for `moonshotai/kimi-k3.1-pro` shows the same numbers as of October 27, 2026: $2 per million input tokens, $10 per million output tokens, and $0.20 per million for cache reads. It reports a context length of 1,048,576 tokens. Prices on a third-party router can change independently of Moonshot's, so check the listing before you commit to a budget.

## How context caching changes the bill

Caching is automatic. When a request repeats a prompt prefix that Moonshot has already stored, the repeated part is billed at the cached rate, one tenth of the normal input price. Writing a prefix into the cache is billed once, at $2.00 per million tokens for the default 5-minute lifetime or $4.00 for a 1-hour lifetime.

The cache is stored in blocks, and a partial block that doesn't fill a whole block can't be cached. It is billed as a miss. If your requests arrive more than 5 minutes apart, Moonshot suggests the 1-hour setting so the cache isn't rewritten after it expires.

## Access, limits and what to watch

Moonshot treats K3.1 Pro as a flagship model. It becomes available after a successful top-up of at least $1, and your cumulative top-ups set your account tier and rate limits. K3.1 Pro always runs with thinking on. The `reasoning_effort` setting accepts `low`, `high` or `max`, with `max` as the default, so output tokens, which cost five times as much as input, can add up on hard prompts.

Moonshot also says the K2 models will close to newly registered users on October 31, 2026, and are planned for retirement by the end of December 2026.

Two things are still open. Moonshot says full weights arrive by November 4, so self-hosting costs can't be compared yet. And we couldn't read the South China Morning Post's report that Moonshot apologised on October 26 over a rollout that limited customer use, because the page returned an access error. Treat availability as something to check on the day you build.

## Frequently asked questions

### How much does Kimi K3.1 Pro cost?

As of October 27, 2026, Moonshot's API charges $2.00 per million input tokens and $10.00 per million output tokens. Cached input is $0.20 per million tokens.

### What does Kimi K3.1 Pro Highspeed cost?

Moonshot lists kimi-k3.1-pro-highspeed at $4.00 per million input tokens and $20.00 per million output tokens as of October 27, 2026. Moonshot says it runs 2 to 3 times faster than K3.1 Pro.

### What is the Kimi K3.1 Pro context window?

1,048,576 tokens. Moonshot says pricing is flat and does not change with context length.

### Is Kimi K3.1 Pro on OpenRouter?

Yes, as moonshotai/kimi-k3.1-pro. As of October 27, 2026 the listing shows $2 per million input tokens, $10 per million output tokens and $0.20 per million for cache reads.

## Sources

- [Model pricing](https://platform.kimi.ai/docs/pricing/chat), Moonshot AI
- [Kimi K3.1 Pro quickstart](https://platform.kimi.ai/docs/guide/kimi-k3-1-pro-quickstart.md), Moonshot AI
- [Kimi K3.1 Pro](https://kimi.ai/blog/kimi-k3-1-pro), Moonshot AI
- [MoonshotAI: Kimi K3.1 Pro](https://openrouter.ai/moonshotai/kimi-k3.1-pro), OpenRouter