​
Models

When using any of these models, you have access to the full context window by default

​
For general everyday use

  • Claude-4 Sonnet
  • Claude-3.7 Sonnet
  • Claude-3.5 Sonnet
  • Gemini 2.5 Pro
  • OpenAI-o4-mini
  • OpenAI-o3
  • GPT-4.1
  • OpenAI-o3-mini
  • GPT-4o
  • Grok-4
  • Grok-3
  • Deepseek v3
  • Deepseek r1

​
Research models

  • Claude-4 Opus
  • Claude-4.1 Opus
  • OpenAI-o3-pro
Free users do not have access to Claude-4 Opus/Sonnet, OpenAI-o3(-pro), or Grok-4

​
How do rate limits work?

For research models like Claude-4 Opus and OpenAI-o3-pro, limits reset weekly.
  • Business plans have roughly 5x the limit for research models compared to Developer plans
  • Max plans have 20x the limit for research models compared to Developer plans.
For general use models:
  • The limits on these models range from 20-100x that of the research models. We only limit usage for specific models in the cases where compute used far exceeds reasonable amounts of usage.

​
What if I hit a limit?

You’ll be notified explicitly that a rate limit is hit and when the rate limit will reset for that model. You can:
  • Use another model
  • Wait for the rate limit to reset
  • Upgrade to a higher tier
The next best model will be used automatically (e.g Opus converts to Sonnet) to avoid disruption, based on the given context, overall acceptance rates for each model, and speed.