Question 1

What is GLM 4.5?

Accepted Answer

GLM 4.5 is a model from Z.ai, released on Jul 28, 2025. GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. $0.60 per million input tokens, $2.20 per million output tokens. 131,072 token context window, maximum output of 98,304 tokens. Includes independent benchmarks from Artificial Analysis.

Question 2

How much does GLM 4.5 cost?

Accepted Answer

On the Respan gateway, input starts at $0.60 per 1M tokens on every provider, and output starts at $2.20 per 1M tokens on every provider, after gateway discounts.

Question 3

Which providers serve GLM 4.5 on Respan?

Accepted Answer

2 providers serve GLM 4.5: OpenRouter and Z.ai.

Question 4

What is GLM 4.5's context window?

Accepted Answer

GLM 4.5 accepts up to 131K tokens of context on its largest provider route.

Question 5

How do I use GLM 4.5 with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "zai/glm-4.5". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is GLM 4.5?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 30 tokens per second, and the lowest response latency was 7.8 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

How does GLM 4.5 score on benchmarks?

Accepted Answer

GLM 4.5 has 3 published benchmark scores, including WeirdML 40.6%, AIME 2025 93.3%, and LMArena Elo 1411. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output	Capabilities
OpenRouter`openrouter/z-ai/glm-4.5`	131K	$0.60/M	$2.20/M
Z.ai`zai/glm-4.5`	128K	$0.60/M	$2.20/M

GLM 4.5

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Coding1

Math1

Arena1

Apps

GLM 4.5 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.