Skip to content
SF·SIX
SF·SIX / DEVELOPER PRICING

Z.ai (Zhipu) API pricing

Live API prices for every Z.ai (Zhipu) model SF·SIX tracks: per 1M tokens at the standard tier from the cheapest provider, or per image, second or character in the provider’s own unit.

By the SF·SIX research desk, ColdAI · Updated · Prices checked · Sources: OpenRouter · Methodology

Z.ai (Zhipu) has 16 models with live API prices on SF·SIX, 16 models priced per 1M tokens. The cheapest is GLM 5.3 Flash at $0.075 per 1M input and $0.25 per 1M output tokens, via DeepInfra (fp4). The most used on OpenRouter is GLM 5.3 Flash (1.73T tokens on 2026-10-16).

Models with live prices
16
Cheapest language model
GLM 5.3 Flash$0.075 / $0.25 per 1M tokens
Most used on OpenRouter (2026-10-16)
GLM 5.3 Flash1.73T tokens
Newest model
GLM 5.3 Prime2026-09-23
Providers serving these models
45

Z.ai (Zhipu) token prices (USD per 1M tokens)

Z.ai (Zhipu) token prices (USD per 1M tokens)
ModelInput / 1MOutput / 1MBlended 3:1Cheapest standard providerProvidersContext (tokens)OpenRouter tokens / day
GLM 5.3$0.50$1.51$0.7513Sail Researchfp8361,048,576942.62B
GLM 5.3 Flash$0.075$0.25$0.1188DeepInfrafp4281,048,5761.73T
GLM 5.2$0.189$0.594$0.2903Baidufp8251,048,576140.87B
GLM 5.1$0.9646$3.03$1.48Baidufp813204,800Not in named rows
GLM 5$0.60$1.92$0.93GMI Cloudfp88204,800Not in named rows
GLM 4.7$0.40$1.75$0.7375DeepInfrafp46204,800Not in named rows
GLM 4.6$0.43$1.75$0.76Venice AIfp44204,800Not in named rows
GLM 4.5 Air$0.13$0.85$0.31Novita AIbf163131,072Not in named rows
GLM 4.7 Flash$0.06$0.40$0.145Venice AIfp82200,000Not in named rows
GLM 4.6V$0.30$0.90$0.45Z.aifp82131,072Not in named rows
GLM 4.5V$0.60$1.80$0.90Z.aifp8265,536Not in named rows
GLM 5.3 Prime$2.80$8.80$4.30Alibaba11,000,000Not in named rows
GLM 5.3 FlashX$0.37$1.25$0.59Z.aifp811,048,576Not in named rows
GLM 5V Turbo$1.20$4.00$1.90Z.aifp81202,752Not in named rows
GLM 5 Turbo$1.20$4.00$1.90Z.ai1202,752Not in named rows
GLM 4.5$0.60$2.20$1.00Z.aifp81131,072Not in named rows

Each model’s headline price: the cheapest qualifying provider at the standard tier in the default region. Most widely served first.

Method

Prices are USD per 1M tokens at the standard service tier in the default region: the cheapest qualifying provider per model, with flex, batch, priority and fast endpoints and unusually low outliers never used as the headline. “Blended” weights input and output 3:1. Missing prices are unknown, not free. OpenRouter tokens per day are the latest full UTC day of OpenRouter’s public rankings (named rows only). Prices move: see AI API price changes for recent cuts and increases.

More on Z.ai (Zhipu)

Related pages