智谱 AI

open.bigmodel.cn

Zhipu AI provides the GLM series of large language models including GLM-4, ChatGLM, and CodeGeeX for text, code, and multimodal tasks.

Models: 35 models
From: --
Speed: 79 tok/s
Updated: 7/8/2026

Latency: 0.00 s
Created At: 8/13/2025

API Endpoints

Endpoint 1
open.bigmodel.cn

Claim this provider

Verify ownership to unlock provider management features:

Edit provider name, content, and links
Get featured with priority traffic and visibility boost
Display a verified badge to build user trust

Leaderboard Rankings

Health

1.0%#201/717

Data as of Jul 8, 2026, 03:11 PMRankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.

About 智谱 AI

智谱AI提供一系列大型语言模型和AI开发工具。主要模型包括GLM-4.6，这是一个旗舰文本模型，拥有3550亿参数和20万上下文长度，专为推理、编码和智能体应用优化；GLM-4.5-Air，轻量级文本模型；GLM-4.5V，视觉模型，适用于视频理解和GUI等任务；GLM-4-Voice用于语音处理；CogView用于图像生成；CogVideoX用于视频生成。平台支持智能体，用于翻译、绘图、职位匹配和作业批改等用例。开发工具包括微调、模型部署、评估、知识库集成和智能体开发。新用户注册可获得2000万免费令牌。

Health Check

99%Recent availability

History (72 pts)

PastNow

API Benchmarks & Pricing

Compare 26 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.

View all 26 models

Model	Speed	Latency
glm-5.3-flash	245.5 t/s	43.59 s
GLM-5.3	420.4 t/s	27.86 s
glm-5.2	44.7 t/s	9.68 s
glm-4v-flash	66.6 t/s	0.39 s
GLM-4-FlashX-250414	27.5 t/s	0.43 s
glm-5.1	34.9 t/s	17.51 s
glm-5-turbo	58.1 t/s	14.60 s
glm-5	36.7 t/s	26.39 s
GLM-4.7-FlashX	44.7 t/s	22.27 s
glm-4.7-flash	69.0 t/s	12.70 s
GLM-4.6V-Flash	137.1 t/s	9.86 s
glm-4.7	41.6 t/s	24.44 s
glm-4-flash	28.0 t/s	0.51 s
GLM-4-Flash-250414	46.3 t/s	0.36 s
GLM-4-FlashX	65.3 t/s	0.43 s
glm-4.1v-thinking-flash	95.7 t/s	7.10 s
glm-4.5-airx	70.7 t/s	11.56 s
glm-4.5-flash	40.1 t/s	16.54 s
glm-4.5-x	69.3 t/s	12.39 s
glm-z1-air	52.7 t/s	0.30 s
glm-z1-airx	168.2 t/s	0.34 s
glm-z1-flash	125.1 t/s	0.34 s
glm-4.6v	35.9 t/s	37.31 s
GLM-4.6	68.5 t/s	2.58 s
glm-4.5	51.6 t/s	9.63 s

Showing 25 of 26 model rows

Recent Test Records

Time	Model	Speed	Latency
Sep 6, 05:34 AM	glm-5.3-flash	170.73 tok/s	45.38s
Sep 6, 05:34 AM	glm-5.3-flash	334.06 tok/s	59.91s
Sep 5, 03:48 AM	GLM-5.3	332.51 tok/s	23.98s
Sep 5, 03:47 AM	GLM-5.3	379.44 tok/s	41.95s
Aug 28, 10:35 PM	glm-5.3-flash	216.83 tok/s	39.60s
Aug 28, 09:54 PM	glm-5.3-flash	262.55 tok/s	33.74s
Aug 27, 07:07 AM	glm-5.3-flash	235.34 tok/s	22.31s
Aug 14, 06:31 PM	glm-5.3	420.40 tok/s	27.86s
Aug 7, 10:22 PM	GLM-4-Flash-250414	43.99 tok/s	1.02s
Aug 1, 11:49 PM	glm-4.7-flash	99.16 tok/s	7.32s

Similar API Provider Alternatives to Compare

Compare 智谱 AI alternatives against 6 nearby API providers using 175 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.

Provider	Why compare	Models	Free	Avg price	Speed	30d uptime
智谱 AI zhipu-ai Zhipu AI provides the GLM series of large language models including GLM-4, ChatGLM, and CodeGeeX for text, code, and multimodal tasks.	Current provider baseline	35	0	N/A	79 tok/s	9950%
10dian-API api-10dian-ai-top A multi-model aggregation platform providing unified, stable, and high-performance AI API services for developers.	Faster measured speed More free-model options Broader model coverage Same provider category	119	4	$0.000003/M	130 tok/s	0%
百度千帆 baidu-qianfan Baidu Qianfan is Baidu Intelligent Clouds enterprise AI platform, providing access to ERNIE series models and other LLM capabilities through developer APIs.	Faster measured speed Broader model coverage Same provider category	184	0	N/A	81 tok/s	6850%
GLM BigModel Relay glm-bigmodel-relay A third-party API relay providing access to GLM/ChatGLM models through OpenAI-compatible endpoints.	Higher 30-day availability Broader model coverage Same provider category	149	0	$0.104/M	52 tok/s	9960%
xAI xai xAI provides the Grok series of AI models through its API, offering text generation and multimodal capabilities.	Faster measured speed Higher 30-day availability Same provider category	13	0	N/A	114 tok/s	9980%
Mistral AI mistral-ai-api Mistral AI API provides access to frontier AI models including Mistral Large, Medium, Small, and Codestral for chat, code, and embeddings.	Faster measured speed Higher 30-day availability Same provider category	11	0	N/A	132 tok/s	9980%
DeepSeek deepseek DeepSeek provides API access to its latest large language models for text generation and coding tasks.	Faster measured speed Higher 30-day availability Same provider category	8	0	N/A	111 tok/s	9980%

Notes

Health checks: Scope: the 72-hour chart and recent availability measure API connectivity only. Each bar summarizes one hour of checks. Targets: LMSpeed tries the configured health check URL and provider status URL first, then API endpoints derived from known API hosts and recent speed-test base URLs. A website host is considered only when it looks like an API endpoint. Probe steps: each candidate goes through DNS lookup, TCP connection, TLS handshake for HTTPS, and an HTTP HEAD request with redirects followed. Probing stops after the first reachable candidate. Reachable criteria: every required network step must succeed. An HTTP response below 500 is treated as reachable, including 401 because it confirms that an authenticated API endpoint responded, except for statuses classified as blocked. Blocked results: HTTP 403, 429, 521, 525, and 530, plus detected WAF or Cloudflare challenges, are shown as blocked and excluded from availability calculations because LMSpeed cannot determine whether the API itself is down. Model availability: when a dedicated test key is configured, LMSpeed sends an authenticated GET request to a derived /models endpoint and compares returned model IDs with this provider's listed models. These per-model results appear in Models & Pricing and are not included in the provider connectivity percentage. Timeouts: TCP connection, TLS handshake, HTTP connectivity, and model requests each use a 20-second timeout. A full run can take longer when several candidates are tried. Frequency: a background worker checks all providers every 5 minutes by default. The 72-hour chart combines those samples into hourly bars, and the schedule may be changed by the service operator. Limit: automated samples are not an SLA and do not guarantee account quota, every model, every region, or successful completion requests. Check the provider's own status page before making operational decisions.
Domain Rating data is sourced from Ahrefs. It is a 0–100 backlink-based domain strength signal and does not measure API speed or reliability.
Announcements and FAQ are read from this provider's NewAPI status snapshot when available. LMSpeed stores the original content and optional English translations from the provider status source, then shows the localized fields on this page.