GLM-5.1
Z.ai
System
Service Status
Public gateway health, catalog visibility, and signed-in operator telemetry
Gateway status
Gateway probe unavailable
Latest probe latency
76ms
Public models listed
33
The latest public probe could not confirm gateway health. Treat the model grid below as catalog visibility until the next successful check.
Endpoint: http://localhost:8000/health
Latency: 76ms
Checked at: 04/18/2026, 03:05:45 AM
Detail: network error
Status scope: Single public /health probe plus the public model catalog
Operator view
Live routing telemetry
The public section above stays anonymous and cacheable. Sign in to inspect live provider health, circuit state, and local GPU telemetry from the protected /v1/status surface.
Model availability
33 public models are listed below. This section reflects catalog visibility, not per-model runtime probes.
Listed
GLM-5
Z.ai
GLM-4.7
Z.ai
DeepSeek R1
DeepSeek
DeepSeek V3.2
DeepSeek
DeepSeek V3.1 Terminus
DeepSeek
DeepSeek V3
DeepSeek
Qwen3-32B
Alibaba
Qwen3.5-397B-A17B
Alibaba
Qwen3.5-122B-A10B
Alibaba
Qwen3.5-35B-A3B
Alibaba
Qwen3.5-27B
Alibaba
Qwen3.5-4B
Alibaba
MiniMax M2.5
MiniMax
Kimi K2.5
Moonshot
GPT-OSS-120B
OpenAI OSS
GPT-OSS-20B
OpenAI OSS
ERNIE 4.5-300B
Baidu
Hunyuan-A13B
Tencent
PaddleOCR-VL-1.5
Baidu
Step-3.5-Flash
StepFun
MiMo-V2-Flash
Xiaomi
Devstral 2
Mistral
Nemotron 3 Super
NVIDIA
Llama 4 Maverick
Meta
Qwen3.5-9B
Alibaba
FLUX.1-dev
Black Forest Labs
Wan2.2-T2V
Wan
Wan2.2-I2V
Wan
CosyVoice2-0.5B
CosyVoice
Fish-Speech-1.5
Fish Audio
IndexTTS-2
IndexTTS
Qwen3-TTS
Alibaba