AnyModelAnyModel
Get started

ANYMODEL 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.

  • GPT-6 Astra

    OpenAI

    96.74%

  • Claude Opus 5

    Anthropic

    90.51%

  • GPT-5.6 Sol

    OpenAI

    86.89%

  • Claude Opus 4.8

    Anthropic

    95.72%

  • Claude Sonnet 5

    Anthropic

    96.24%

  • Kimi K3

    Moonshot

    98.13%

  • GPT-5.5

    OpenAI

    90.17%

  • GPT-5.6 Luna

    OpenAI

    89.37%

  • Grok 4.6

    xAI

    86.06%

  • GPT-5.6 Terra

    OpenAI

    83.09%

  • GLM-5.3

    Zhipu

    73.24%

  • GLM-5.3-Flash

    Zhipu

    74.84%

  • Claude Sonnet 4.6

    Anthropic

    91.75%

  • Free Models Auto Router

    AnyModel

    99.57%

  • Claude Haiku 4.5

    Anthropic

    98.35%

  • Nemotron 3 Ultra

    AnyModel

    77.91%

  • Claude Fable 5

    Anthropic

    0.00%

  • Grok 4.20 Multi-Agent Research

    xAI

    97.80%

  • Claude Opus 4.6

    Anthropic

    92.39%

  • Claude Opus 4.7

    Anthropic

    96.39%

  • Kimi K2.7 Code

    Moonshot

    98.02%

  • Gemini 3.1 Flash-Lite

    Google

    91.31%

  • Qwen3.7 Max

    Qwen

    2.39%

  • Kimi K3 1M

    AnyModel

    87.56%

  • Gemini 2.5 Flash

    Google

    85.58%

  • Gemini 2.5 Flash Lite

    Google

    86.77%

  • Gemini 3 Flash

    Google

    73.62%

  • Gemini 3.6 Flash

    Google

    86.14%

  • Gemini 3.7 Flash

    Google

    81.17%

  • Gemini 3.1 Pro

    Google

    82.36%

  • GPT-OSS 120B

    OpenAI

    50.01%

  • DiffusionGemma 26B A4B IT

    AnyModel

    90.26%

  • GPT-OSS 20B

    AnyModel

    90.91%

  • Laguna XS 2.1

    AnyModel

    66.05%

  • Llama 3.2 11B Vision Instruct

    AnyModel

    97.61%

  • Mistral Nemotron

    AnyModel

    48.13%

  • Nemotron 3 Nano Omni 30B A3B Reasoning

    AnyModel

    86.23%

  • Nemotron 3 Super 120B A12B

    AnyModel

    94.39%

  • Nemotron 3.5 Content Safety

    AnyModel

    96.59%

  • Nemotron 3.5 Lightning 30B A3B

    AnyModel

    92.30%

  • Riva Translate 4B Instruct v2

    AnyModel

    99.72%

  • DeepSeek V4 Flash

    DeepSeek

    34.23%

  • DeepSeek-V4-Pro

    DeepSeek

    32.70%

  • GLM 4.6V

    Zhipu

    74.72%

  • GLM 4.7

    Zhipu

    69.28%

  • GLM 5

    Zhipu

    74.01%

  • GLM-5.1

    Zhipu

    73.04%

  • GLM-5.2

    Zhipu

    41.46%

  • Qwen3.6 Flash

    Qwen

    3.84%

  • Qwen 3.7 Plus

    Qwen

    7.38%

  • Qwen3.8 Max

    Qwen

    36.38%

  • Grok 4.20

    xAI

    99.62%

  • Grok 4.3

    xAI

    98.50%

  • Grok 4.5

    xAI

    98.78%

  • Grok Build 0.1

    xAI

    98.74%

  • Gemini 3.1 Flash

    Google· Images

    29.47%

  • FLUX.1 Dev

    AnyModel· Images

    54.87%

  • FLUX.2 Klein 4B

    AnyModel· Images

    97.74%

  • GPT Image 1.5

    OpenAI· Images

    99.30%

  • GPT Image 2

    OpenAI· Images

    95.13%

  • Grok Imagine

    xAI· Images

    97.47%

  • Grok Imagine Quality

    xAI· Images

    95.16%

  • Grok Imagine Video

    xAI· Video

    92.28%

  • Grok Imagine Video 1.5

    xAI· Video

    95.47%

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. Image and video models are on this page too, and one thing about them is not obvious: a video, and any generation queued in a studio, is recorded as a request the moment the provider accepts the job, so a job that dies later would otherwise stay counted as an answer. When such a generation's charge is returned — the provider produced nothing usable, the job never arrived — that request counts as failed here rather than as served. Refunds that are not the model's fault are not counted against it: a job our own restart or dispatcher interrupted before the provider answered, one that never reached the provider, and an attempt the studio resubmitted, where the retry delivered the result. A generation the provider refused over the caller's own prompt is not counted either way, like a text request rejected as invalid. 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.