Service status
How popular models performed on each group's line over the last 24 hours. For any other model, open its detail page and check the Availability tab.
17 lines were below 95% success in the last 24 hours — see the affected models and groups below
43 lines monitored · 19 normal · 7 fluctuating · 17 disrupted
Updated 11/12, 22:01 (UTC+8)
API gatewayOperational· 49 ms response
Popular model lines
- ≥ 99% success
- 95% – 99%
- Below 95%
- No data
- Details
kimi-k3.1-pro
Moonshot Kimi
Standard
No data
China Models
100%First token 10.1 s
- Details
claude-haiku-5-5
Anthropic
Official · Enterprise
No data
Claude Direct
100%First token 181.3 s
Claude List Price
No data
Claude Plus
99.1%First token 3.46 s
- Details
claude-sonnet-5-5
Anthropic
Standard
98.6%First token 5.38 s
Official · Enterprise
100%Latency 1.55 s
Claude Direct
28.5%Latency 8.80 s
Claude List Price
No data
- Details
gpt-6.1-sol
OpenAI
Standard
95.1%First token 10.6 s
Azure
100%First token 9.82 s
Azure Plus
0.0%Latency 281.7 s
OpenAI Direct
91.6%Latency 29.9 s
- Details
claude-opus-5-5
Anthropic
Standard
95.5%First token 8.84 s
Official · Enterprise
No data
Claude Direct
No data
Claude List Price
100%Latency 5.12 s
Claude Plus
- Details
deepseek-v4.1-flash
DeepSeek
Standard
95.8%First token 4.46 s
China Models
100%First token 1.38 s
- Details
deepseek-v4-pro
DeepSeek
Standard
100%First token 2.92 s
China Models
95.2%First token 4.93 s
- Details
gemini-3.8-flash
Google
Standard
31.0%First token 19.0 s
Official · Enterprise
No data
Gemini Plus
56.4%First token 65.8 s
Gemini High Tier
43.9%First token 25.4 s
- Details
gpt-5.5
OpenAI
Standard
83.9%First token 5.88 s
Azure
100%First token 18.2 s
Azure Plus
75.0%Latency 38.2 s
OpenAI Direct
No data
- Details
gpt-image-2
OpenAI
Standard
99.5%First token 35.6 s
- Details
gpt-5.4-mini
OpenAI
Standard
0.0%Latency 611 ms
Azure
0.0%Latency 230 ms
Azure Plus
No data
OpenAI Direct
0.0%Latency 266 ms
- Details
gemini-3.1-pro-preview
Google
Standard
35.1%First token 31.4 s
Official · Enterprise
No data
Gemini Plus
77.1%First token 20.8 s
Gemini High Tier
99.4%First token 27.0 s
- Details
qwen3.5-plus
Qwen
Standard
No data
China Models
87.6%Latency 48.1 s
- Details
nano-banana-pro
Google
Standard
100%Latency 32.9 s
Official · Enterprise
No data
Gemini Plus
97.7%Latency 41.5 s
Gemini High Tier
No data
- Details
text-embedding-3-large
OpenAI
Standard
99.9%Latency 464 ms
Azure
99.5%Latency 517 ms
Azure Plus
100%Latency 902 ms
OpenAI Direct
100%Latency 329 ms
Line monitoring over the last 24 hours, refreshed about every 5 minutes. Lines without traffic show as “no data”.