API Provider2 active models1 organizationzai.com

ZAI: API pricing, performance & models

ZAI hosts 2 active AI models, with input pricing from $1.00 per 1M tokens, averaging 30 tok/s output throughput, with up to 200K context window. Compare ZAI's API pricing, latency, and feature support against other LLM providers.

First-party only
2Active
Pricing
$1.00/MFrom
$1.20/MAvg
Performance
30tok/sThroughput
3.00sLatency
200KMax

Catalog

Type
Price
2 models
Model
GLM-5.1
GLM-5

FAQ

Common questions about ZAI.

What is ZAI?

ZAI is an API provider that hosts large language models. Active models: 2; From (input): $1.00 / 1M tok; Avg throughput: 30 tok/s; Avg latency: 3.00 s; Max context: 200K.

How many models does ZAI offer?

ZAI currently serves 2 active models out of 6 historical offerings on LLM Stats.

What is ZAI's API pricing?

ZAI input pricing starts from $1.00 per 1M tokens, with the most expensive offering at $1.4 per 1M tokens. See the Pricing tab above for the full per-model breakdown.

How fast is ZAI?

ZAI averages 30 output tokens per second across its catalog, with average latency of 3.00s. Per-model performance is shown in the Performance tab.

Whose models does ZAI host?

ZAI hosts models from Zhipu AI. See the Models tab for the full catalog grouped by creator.

How do I start using ZAI?

Sign up at https://zai.com to get an API key, then call ZAI's API directly from your application. Use the Pricing and Performance tabs above to pick the right model for your latency, cost, and context-window requirements.