Prompt Buddy logoPrompt Buddy

openai · OpenAI Platform Docs

Rate limits

Explains how OpenAI rate limits function across different metrics like RPM and TPM, how usage tiers affect limits, and how to implement error mitigation strategies such as exponential backoff.

Import to Prompt Buddy

Derived skill

Files assembled from official documentation

Viewing SKILL.md

Rate limits

Explains how OpenAI rate limits function across different metrics like RPM and TPM, how usage tiers affect limits, and how to implement error mitigation strategies such as exponential backoff.

When To Use

Use when you need to implement error handling for rate limit exceptions or need to calculate how to scale request volume within specific usage tiers and token constraints.

Reference Files

FileContainsUse For
SKILL.mdEntry point: scope, routing table, and workflow.Start here.
docs/rate-limits-workflow-guide.mdA guide explaining OpenAI API rate limit mechanics, usage tiers, and header information.Questions about a guide explaining OpenAI API rate limit mechanics, usage tiers, and header information.
examples/rate-limits-openai-api-get-model-limits-curl.bashA curl command to retrieve fine-tuning model rate limits from the OpenAI API.Exact payloads, commands, or snippets shown in A curl command to retrieve fine-tuning model rate limits from the OpenAI API.
examples/rate-limits-openai-api-rate-limits-python-exponential-backoff.pythonA Python script demonstrating how to implement exponential backoff using the tenacity library to handle OpenAI API rate limit errors.Exact payloads, commands, or snippets shown in A Python script demonstrating how to implement exponential backoff using the tenacity library to handle OpenAI API ra...
examples/rate-limits-openai-rate-limits-python-backoff-implementation.pythonA Python script demonstrating how to use the backoff library to handle OpenAI RateLimitError exceptions using exponential backoff.Exact payloads, commands, or snippets shown in A Python script demonstrating how to use the backoff library to handle OpenAI RateLimitError exceptions using exponen...
examples/rate-limits-openai-rate-limits-python-exponential-backoff-retry.pythonA Python implementation of a retry decorator using exponential backoff to handle OpenAI RateLimitError exceptions.Exact payloads, commands, or snippets shown in A Python implementation of a retry decorator using exponential backoff to handle OpenAI RateLimitError exceptions.

What This Skill Covers

  • Rate limits are restrictions that our API imposes on the number of times a user or client can access our services within a specified period of time.
  • Main sections: Why do we have rate limits?, How do these rate limits work?, Usage tiers, Rate limits in headers, Fine-tuning rate limits.

Workflow

  1. Open the most relevant file under docs/ for the exact documented workflow and wording.
  2. Open schemas/ files for exact structured contracts.
  3. Open examples/ files for concrete requests, commands, snippets, and manifests.
  4. Do not add behavior or configuration that is not present in the attached source files.

Canonical source: https://developers.openai.com/api/docs/guides/rate-limits.md