It keeps showing ”You’ve reached your rate limit. Please try again later.“
I also met the same problem.
Hey everyone,
Rate limit for experimental 1206 model is “5 RPM / 1M TPM / 100 RPD”, so you might be hitting the limit.
It does not show the limit in AI STUDIO
Yeah, unfortunately it’s not there, also not mentioned in doc. I have raised a request with the team for update.
Thanks.
1 Like
I’m noticing a discrepancy here - if the model has a 1M token per minute rate limit, how can we effectively utilize its 2M token context window? The rate limit essentially prevents using the model’s full capacity, since any API call exceeding 1M tokens would hit the TPM limit. This seems to make the 2M context window capability theoretical rather than practical.
1 Like