Zai Models

haimaker.ai provides API access to all 16 Zai models, with context windows up to 1M tokens, priced from $0.06 to $2.20 per 1M input tokens. Access each model through its haimaker.ai API endpoint.

Models
16
Max context
1M
From
$0.06
/1M input
Modes
Chat

GLM 5.3 Flash

Zai

zai/glm-5.3-flash

Chat1M ctxIn: $0.15/1MOut: $0.50/1MCached in: $0.050/1M
function callingvisionreasoning

GLM 5.3

Zai

zai/glm-5.3

Chat1M ctxIn: $0.65/1MOut: $2.05/1MCached in: $0.12/1MPromo rate
function callingreasoning

GLM 5.2

Zai

zai/glm-5.2

Chat1M ctxIn: $0.65/1MOut: $2.04/1MCached in: $0.12/1M
function callingreasoning

GLM 5.1

Zai

zai/glm-5.1

Chat205K ctxIn: $0.97/1MOut: $3.04/1MCached in: $0.18/1MCache write: Free/1M
function callingreasoning

GLM 5 Code

Zai

zai/glm-5-code

Chat200K ctxIn: $1.20/1MOut: $5.00/1MCached in: $0.30/1MCache write: Free/1M
function callingreasoning

GLM 5

Zai

zai/glm-5

Chat205K ctxIn: $0.60/1MOut: $1.92/1MCached in: $0.12/1M
function callingreasoning

GLM 4.7 Flash

Zai

zai/glm-4.7-flash

Chat200K ctxIn: $0.06/1MOut: $0.40/1MCached in: $0.010/1MCache write: Free/1M
function callingreasoning

GLM 4.7

Zai

zai/glm-4.7

Chat205K ctxIn: $0.40/1MOut: $1.75/1MCached in: $0.080/1MCache write: Free/1M
function callingreasoning

GLM 4.6

Zai

zai/glm-4.6

Chat205K ctxIn: $0.43/1MOut: $1.75/1MCached in: $0.080/1M
function callingreasoning

GLM 4.5v

Zai

zai/glm-4.5v

Chat66K ctxIn: $0.60/1MOut: $1.80/1MCached in: $0.11/1M
function callingvisionreasoning

GLM 4.5 X

Zai

zai/glm-4.5-x

Chat128K ctxIn: $2.20/1MOut: $8.90/1M
function calling

GLM 4.5 Flash

Zai

zai/glm-4.5-flash

Chat128K ctxIn: FreeOut: Free
function calling

GLM 4.5 Airx

Zai

zai/glm-4.5-airx

Chat128K ctxIn: $1.10/1MOut: $4.50/1M
function calling

GLM 4.5 Air

Zai

zai/glm-4.5-air

Chat131K ctxIn: $0.13/1MOut: $0.85/1MCached in: $0.025/1M
function callingreasoning

GLM 4.5

Zai

zai/glm-4.5

Chat131K ctxIn: $0.60/1MOut: $2.20/1MCached in: $0.11/1M
function callingreasoning

GLM 4 32B 0414 128k

Zai

zai/glm-4-32b-0414-128k

Chat128K ctxIn: $0.10/1MOut: $0.10/1M
function calling