Alexey Shurov.
Free tool

GLM API pricing, every Z.ai model per million tokens

On 25 September 2026, Z.ai models on this list cost from $0.045 per million input tokens (GLM 5.3 Flash) to $2.80 (GLM 5.3 Prime), and from $0.14 per million output tokens (GLM 5.3 Flash) to $8.80 (GLM 5.3 Prime).

Prices checked 25 September 2026 at 06.00 UTC . Source OpenRouter public model list . US dollars per million tokens
ModelInputOutputCached inputBatch in / outContextYour monthListed
GLM 5.3 Prime$2.80$8.80$0.561M$300.002026-09-23
GLM 5.3 FlashX$0.37$1.25$0.091.04858M$40.952026-09-18
GLM 5.3 Flash$0.045$0.14$0.01$0.06 / $0.201.31072M$4.802026-08-26
GLM 5.3$1.40$4.40$0.26$0.45 / $2.001.31072M$150.002026-08-18
GLM 5.2
free tier on OpenRouter
$0.6496$2.04$0.12061.04858M$69.602026-06-16
GLM 5.1$0.9646$3.03$0.1791205K$103.352026-04-07
GLM 5V Turbo$1.20$4.00$0.24203K$132.002026-04-01
GLM 5 Turbo$1.20$4.00$0.24203K$132.002026-03-15
GLM 5$0.60$1.92$0.12205K$64.802026-02-11
GLM 4.7 Flash$0.0605$0.40200K$9.632026-01-19
GLM 4.7$0.60$2.20$0.11205K$69.002025-12-22
GLM 4.6V$0.30$0.90$0.055131K$31.502025-12-08
GLM 4.6$0.43$1.75$0.08205K$52.052025-09-30
GLM 4.5V$0.60$1.80$0.1166K$63.002025-08-11
GLM 4.5$0.60$2.20$0.11131K$69.002025-07-25
GLM 4.5 Air$0.13$0.85$0.025131K$20.552025-07-25

Compare Z.ai with every other provider

Common questions

How much does the GLM API cost?

On 25 September 2026, Z.ai models on this list cost from $0.045 per million input tokens (GLM 5.3 Flash) to $2.80 (GLM 5.3 Prime), and from $0.14 per million output tokens (GLM 5.3 Flash) to $8.80 (GLM 5.3 Prime).

What is the cheapest GLM model?

For a typical mix of three input tokens to every output token, the cheapest is GLM 5.3 Flash at $0.045 per million input tokens and $0.14 per million output tokens.

What is the newest GLM model on the list?

GLM 5.3 Prime, listed on 23 September 2026, at $2.80 per million input tokens and $8.80 per million output tokens.

Which GLM model has the largest context window?

GLM 5.3 Flash, with 1.31072M tokens of context.

Does Z.ai offer batch pricing?

Yes, 2 of its models on this list show a batch price, with batch input at a median of 83 percent of the standard price. Batch suits work that can wait for its answer.

Choosing a model for a production agent

Price is one input. Quality on your own cases, latency and the cost of retries decide the rest. Tell me what you are building.

shurco.aiGuidesFree toolsSolutionsInsightsRSSllms.txt