The AI arena is free today

Open Superagent
API Provider5 active models1 organization

ZAI: API pricing, speed & models

ZAI hosts 5 active AI models, with input pricing from $0.15 per 1M tokens, with median throughput of 46 characters/sec, and P95 time to first token of 15.62s, with 98.9% success rate over 7 days. Compare ZAI's API speed, pricing, and reliability against other inference providers.

First-party only
Median throughput46 c/s
Median TTFT6.44s
P95 TTFT15.62s
Success rate (7d)98.9%
From$0.15 /M tok

Catalog

Type
Price
7 models
Model
GLM-5.3-Flashcache pricing
GLM-5.3-Flashcache pricing
GLM-5.3-Flashcache pricing
GLM-5.3cache pricing
GLM-530 QPS
At a glance

ZAIpricing, performance & catalog

The citable facts about ZAI's 5 models — sourced from provider APIs and refreshed continuously.

Lowest price
GLM-5.3-Flash at $0.150 per 1M input tokens
Highest median throughput
GLM-5.3-Flash at 46 chars/s
Lowest median TTFT
GLM-5.3-Flash at 6.44s
Largest context
GLM-5.3-Flash at 1.0M tokens
Catalog
5 active models from 1 organization

Fastest median throughput

  1. 1GLM-5.3-Flash46 c/s

FAQ

Common questions about ZAI.

What is ZAI?

ZAI is an API provider that hosts large language models. Active models: 5; From (input): $0.15 / 1M tok; Median throughput: 46 c/s; Median TTFT: 6.44s; Success rate (7d): 98.9%.

How many models does ZAI offer?

ZAI currently serves 5 active models out of 9 historical offerings on LLM Stats.

What is ZAI's API pricing?

ZAI input pricing starts from $0.15 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 delivers a median throughput of 46 characters per second and P95 time to first token of 15.62s across its model catalog. See the Models tab for per-model throughput and TTFT breakdowns.

Is ZAI reliable?

ZAI has a 98.9% success rate across 275 API calls in the last 7 days, with a 1.1% error rate.

Does ZAI support function calling?

Yes. 7 of 5 models on ZAI support function calling (tool use). The Capabilities tab lists which specific models accept tool definitions.

Does ZAI support JSON mode and structured output?

Yes. 7 of 5 models on ZAI support structured output (JSON mode / schema-constrained generation). The Capabilities tab shows which specific models accept response_format or json_schema parameters.

Does ZAI support multimodal models?

Yes. ZAI's catalog includes 1 vision-capable models. See the Models and Capabilities tabs for the full per-model breakdown.

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. Most clients work out of the box by pointing the OpenAI SDK at ZAI's base URL with your key. Use the Models and Pricing tabs above to pick the right model for your latency, cost, and context-window requirements.