GPT-4 Vision - I need lots of requests

At my current usage tier, I am limited to 1,500 requests per day. The project I am working on would benefit to upwards to 100,000.

What are my options here?

1: Read

The models gpt-4-1106-preview and gpt-4-vision-preview are currently under preview with restrictive rate limits that make them suitable for testing and evaluations, but not for production usage. We plan to increase these limits gradually in the coming weeks with an intention to match current gpt-4 rate limits once the models graduate from preview. As these models are adopted for production workloads we expect latency to increase modestly compared to this preview phase.

2: Strategize:

Higher rate tiers for gpt-4-vision-preview

Model RPM RPD TPM TPD
Tier 4 150 2,000 150,000 -
Tier 5 200 10,000 300,000 -

3: Feed:

Once the following criteria are met, you’ll automatically move to Tier 5:

  • At least $1,000 spent on the API since account creation (credits purchased)
  • At least 30 days passed since first successful payment.

4: Request

Very bottom of this account page you find “request exception”

5: Parallelize

6: Wait

“We plan to increase these limits”

5 Likes

This :eyes: :

This iteration is for development, not Production.

Develop your product with the current version and aim to roll it out and scale when Open AI has scaled their end (and added functions … hint hint!)

Simple!

1 Like