https://openai-status.llm-utils.org/

 Unofficial OpenAI Status

Why does this exist?

I've found myself checking the official OpenAI status dashboard when
I'm experiencing either a slow model or model errors, but the status
dashboard normally shows all green even when I'm experiencing API/
Playground/ChatGPT issues. So the official status doesn't seem to
capture non-catastrophic but still elevated rates of errors or
slowness. This unofficial OpenAI status page fixes that.

At a Glance

Compare current model performance with previous data. Colors reflect
two day percentiles: lower values and greener shades indicate better
performance.

                 Last updated less than a minute ago
                     7/13/2023, 11:00:30 PM UTC
                          Time / 256                         Hourly
        Model               Tokens      Difference  2 Day  Error Rate
                        (Performance,              Average  (Status)
                         Percentile)
gpt-4                  19.31s (Slightly -3.18s     22.50s  0.00 / hr
                       Faster, 24^th)                      (Low)
gpt-3.5-turbo          7.71s (Normal,   +0.61s     7.09s   0.00 / hr
                       74^th)                              (Low)
gpt-3.5-turbo-16k      5.26s (Normal,   +0.49s     4.77s   0.00 / hr
                       72^th)                              (Low)
                       23.12s                              0.00 / hr
text-davinci-003       (Significantly   +11.21s    11.91s  (Low)
                       Slower, 94^th)
text-curie-001         3.04s (Normal,   -0.05s     3.09s   0.00 / hr
                       58^th)                              (Low)
text-babbage-001       2.26s (Normal,   -0.06s     2.31s   0.00 / hr
                       64^th)                              (Low)
text-ada-001           2.78s (Slightly  +0.07s     2.71s   0.00 / hr
                       Slower, 83^th)                      (Low)
gpt-4-0613             22.20s (Normal,  +0.12s     22.09s  0.00 / hr
                       54^th)                              (Low)
                       8.29s                               0.00 / hr
gpt-3.5-turbo-0613     (Significantly   +1.42s     6.88s   (Low)
                       Slower, 92^th)
gpt-3.5-turbo-16k-0613 4.26s (Normal,   -0.47s     4.73s   0.00 / hr
                       36^th)                              (Low)

Completion Time / 256 Tokens

The time it takes for a model to generate 256 tokens. Lower values
indicate better performance.

[]

Errors

[]

Latency

The response time for the OpenAI API's models call, indicating base
latency independent of the model's response time, as called from
US-West. Shorter durations are preferable.

[]