AnyModelANYMODEL STATUS
Model status
Hour-by-hour availability of every model in the AnyModel catalogue, built from real request traffic over the last 7 days. No account required.
Model availability
Last 7 days, one bar per hour. Newest on the right.
- 99.97%
GPT-5.6 Sol
OpenAI
99.97% - 95.01%
Claude Opus 5
Anthropic
95.01% - 96.01%
Claude Opus 4.8
Anthropic
96.01% - 54.70%
GLM-5.3-Flash
Zhipu
54.70% - 95.91%
Claude Sonnet 5
Anthropic
95.91% - 65.31%
Kimi K3
Moonshot
65.31% - 99.95%
GPT-5.5
OpenAI
99.95% - 97.86%
GPT-5.6 Luna
OpenAI
97.86% - 97.24%
Claude Opus 4.7
Anthropic
97.24% - 99.85%
GPT-5.6 Terra
OpenAI
99.85% - 86.63%
Grok 4.6
xAI
86.63% - 96.35%
Claude Sonnet 4.6
Anthropic
96.35% - 99.96%
GPT-5.4
OpenAI
99.96% - 97.74%
Claude Opus 4.6
Anthropic
97.74% - 53.55%
GLM-5.3
Zhipu
53.55% - 79.67%
Kimi K2.7 Code
Moonshot
79.67% - 85.98%
Claude Haiku 4.5
Anthropic
85.98% - 95.76%
Free Models Auto Router
AnyModel
95.76% - 99.97%
GPT-5.4 mini
OpenAI
99.97% - 45.73%
MiniMax M3
AnyModel
45.73% - 96.43%
Gemini 3.5 Flash
Google
96.43% - 94.50%
Grok 4.20 Multi-Agent Research
xAI
94.50% - 97.22%
Gemini 3.1 Flash-Lite
Google
97.22% - 83.70%
Nemotron 3 Ultra
AnyModel
83.70% - 34.68%
Qwen3.7 Max
Qwen
34.68% - 11.28%
Gemma 4 31B
AnyModel
11.28% - 96.75%
Kimi K3 1M
AnyModel
96.75% - 93.99%
Gemini 2.5 Flash
Google
93.99% - 98.66%
Gemini 2.5 Flash Lite
Google
98.66% - 0.00%
Gemini 2.5 Pro
Google
0.00% - 96.25%
Gemini 3 Flash
Google
96.25% - 97.11%
Gemini 3.6 Flash
Google
97.11% - 92.17%
Gemini 3.7 Flash
Google
92.17% - 94.64%
Gemini 3.1 Pro
Google
94.64% - 70.08%
GPT-OSS 120B
OpenAI
70.08% - 97.47%
DiffusionGemma 26B A4B IT
AnyModel
97.47% - 96.02%
GPT-OSS 20B
AnyModel
96.02% - 85.23%
Laguna XS 2.1
AnyModel
85.23% - 97.47%
Llama 3.2 11B Vision Instruct
AnyModel
97.47% - 35.98%
Mistral Nemotron
AnyModel
35.98% - 99.90%
Nemotron 3 Nano 30B A3B
AnyModel
99.90% - 81.04%
Nemotron 3 Nano Omni 30B A3B Reasoning
AnyModel
81.04% - 97.68%
Nemotron 3 Super 120B A12B
AnyModel
97.68% - 99.07%
Nemotron 3.5 Content Safety
AnyModel
99.07% - 80.34%
Nemotron 3.5 Lightning 30B A3B
AnyModel
80.34% - 99.88%
Riva Translate 4B Instruct v2
AnyModel
99.88% - 45.05%
DeepSeek V4 Flash
DeepSeek
45.05% - 45.51%
DeepSeek-V4-Pro
DeepSeek
45.51% - 23.12%
GLM 4.6V
Zhipu
23.12% - 69.77%
GLM 4.7
Zhipu
69.77% - 18.38%
GLM 5
Zhipu
18.38% - 28.82%
GLM-5.1
Zhipu
28.82% - 45.96%
GLM-5.2
Zhipu
45.96% - 6.20%
Qwen3.6 Flash
Qwen
6.20% - 8.22%
Qwen 3.7 Plus
Qwen
8.22% - 55.42%
Qwen3.8 Max
Qwen
55.42% - 80.87%
Grok 4.20
xAI
80.87% - 97.22%
Grok 4.3
xAI
97.22% - 93.61%
Grok 4.5
xAI
93.61% - 57.18%
Grok Build 0.1
xAI
57.18%
How status is calculated
Each bar is one hour of real client traffic, and the unit is a request somebody actually sent: green means requests were answered, amber means a noticeable share came back as an error, red means several failed and not one request came back that hour, grey means there was no traffic to judge by, or an hour we can no longer judge honestly. A single failed request in an otherwise empty hour stays amber — one failure is not an outage. A request counts as failed only if the caller received the error: after every account for that model had been tried and every retry spent. What the router had to do to get the answer does not count against the model — rotating to another account, retrying, waiting out a rate limit — because the caller got their answer, and this page publishes their experience rather than ours. A request refused as invalid before it reached any model is not counted either way. Two things to know about the number: a model in a combo that failed while a sibling model answered still counts as failed for itself, since it did not produce that answer; and a reply that broke in the middle after streaming had begun counts as answered, because part of it had already reached the caller. Hours older than the switch to this method were measured the previous way — by upstream calls rather than client requests — and read lower; they leave the window seven days after the change. The page never exposes account names, keys, request content or internal error details.