gpudiff the public record of change in GPU cloud pricing
Follow the diffs: RSS · Free API · Sponsor this site

kimi-k2-thinking API price — 3 gateways compared

from $0.60 per million input tokens · same price on every gateway · updated hourly

Gateway$ in /MTok$ out /MTok ContextInput price historyModel ID
OpenRouter fees$0.60$2.50262,144moonshotai/kimi-k2-thinking
Glama$0.60$2.50262,144since 2026-08-20moonshot/kimi-k2-thinking
Novita$0.60$2.50262,144since 2026-08-20moonshotai/kimi-k2-thinking

Fees beyond the token price

Changelog for kimi-k2-thinking

kimi-k2-thinking pricing FAQ

How much does kimi-k2-thinking cost per million tokens?

The cheapest tracked gateway charges $0.60 per million input tokens and $2.50 per million output tokens (Glama). Prices refresh hourly.

Which gateway is cheapest for kimi-k2-thinking?

Glama for input tokens and Glama for output tokens, among the 3 gateways we track.

Do kimi-k2-thinking prices differ between gateways?

No — every tracked gateway currently charges the same per-token price, so the difference between them is fees and routing, not token cost.

← All LLM prices · API