DeepSeek, Kimi and GLM are live — one endpoint, one bill.
Voyai

Pricing

Prices are in USD per million tokens. Billing is per request, metered to the token.

The more you top up, the less you pay

Your tier is applied automatically to every model below — no contract, no negotiation.

StandardYour tier
Standard pricing

Everyone starts here

VIP
10% off

Top up $100 in total

SVIP
20% off

Top up $500 in total

Tiers are permanent — we never downgrade you.

Text

ModelInput / 1MOutput / 1MCached input / 1M
deepseek-ai/DeepSeek-V3.2128K context$0.4200$0.6300$0.0420
deepseek-ai/DeepSeek-R1128K context$0.8250$3.2850$0.2100
moonshotai/Kimi-K2128K context$0.9000$3.7500$0.2250
moonshotai/Kimi-K2-Turbo128K context$1.7250$12.0000$0.4350
zai-org/GLM-4.6200K context$0.9000$3.3000$0.1650
zai-org/GLM-4.5-Air128K context$0.3000$1.6500not billed separately

Vision

ModelInput / 1MOutput / 1M
zai-org/GLM-4.6V64K context$0.9000$2.7000

Cached input applies when a request reuses a prefix the upstream has already processed. It is billed at the cached rate automatically — nothing to enable.