Moonshot AI · Open weight · TEE variant available

Kimi K3 API pricing

The largest discount in the SayGM catalogue: 67.5 percent below Moonshot's list price on the open tier. A sealed -tee variant runs inside a TEE for prompts that must stay confidential.

Snapshot October 2026 · USD per million tokens · Best for: open-weight coding and agent workloads

SayGM, in / out: $0.98 / $4.88; No top-up fee
OpenRouter, in / out: $0.42 / $9.50; Cheapest OpenRouter provider including the 5.5 percent fee
Output to input price: 5.0x; On SayGM
Per 100M tokens, 80/20: $176; $224 on OpenRouter

§ 01

What a month costs

The same three workloads used across the index. At every level the SayGM bill is about 21% lower.

Fig. 1Monthly bill at three usage levels, Kimi K3

OpenRouter, fee included
SayGM

Side project5M in · 1M out

$12

$9.78

Production app50M in · 15M out

$164

$122

High volume500M in · 100M out

$1,160

$978

Show data as a table

	OpenRouter, fee included	SayGM
Side project (5M in · 1M out)	$12	$9.78
Production app (50M in · 15M out)	$164	$122
High volume (500M in · 100M out)	$1,160	$978

Usage is millions of input and output tokens per month. No caching discount applied. Source: published rate cards, October 2026 snapshot. Current prices on saygm.com.

§ 02

Where the money goes

Output tokens cost 5.0 times more than input on Kimi K3. At an 80/20 mix they make up 55% of the bill.

Fig. 2Share of the bill from output tokens at an 80/20 token mix

Input tokens (80% of volume)
Output tokens (20% of volume)

Kimi K3

DeepSeek V4.1 Flash

Show data as a table

Model	Share of bill from input	Share of bill from output
Kimi K3	45%	55%
DeepSeek V4.1 Flash	50%	50%

Output tokens are a fifth of the volume but most of the cost on every frontier model. Trimming output length saves more than trimming prompts. Source: published rate cards, October 2026 snapshot. Current prices on saygm.com.

§ 03

Estimate a Kimi K3 bill

Model

Input tokens per month50M

Output tokens per month10M

Monthly bill by provider

OpenRouter, fee included$116
Moonshot AI direct, list price$300
SayGM$98

A year, vs the cheapest alternative: $218; 16% lower than OpenRouter
A year, vs OpenRouter: $218; Fee included

Uncached prices from the October 2026 snapshot. Prompt caching lowers every provider's bill; batch jobs bought direct cost half of list. Requesty and Vercel are not priced for open-weight models here. Current SayGM rates are on saygm.com (opens in a new tab).

§ 04

Other open-weight models

USD per million tokens, input and output. OpenRouter includes its 5.5% top-up fee. Snapshot from October 2026.
Model	SayGMin / out	OpenRouterin / out, fee incl.	SayGM vs OpenRouter80/20 blend
Kimi K3Moonshot AI · TEE variant	$0.98 / $4.88	$0.42 / $9.50Cheapest provider	21% lower
DeepSeek V4.1 FlashDeepSeek · TEE variant	$0.18 / $0.72	$0.03 / $0.53Cheapest provider	122% higher

§ 06

Kimi K3 questions

How much does Kimi K3 cost on SayGM?

As of October 2026, $0.98 per million input tokens and $4.88 per million output tokens, with no top-up fee. Prices are set per epoch and capped at list, so check saygm.com for the live rate.

Is Kimi K3 cheaper on SayGM or OpenRouter?

SayGM is about 21 percent cheaper at an 80/20 input to output mix once OpenRouter's 5.5 percent fee is included.

Which API does SayGM use for Kimi K3?

The model's native API. Moonshot AI features such as caching, tool use and structured output work unchanged. Any OpenAI-compatible SDK works by changing the base URL.