How Token Plans Work

Geoff uses a unified token-based billing system. Every API call consumes tokens based on the type and complexity of the request. Your token balance is shared across all capabilities — text, speech, video, image, music, code, and file operations.

Plans

BasicProMaxTurbo
Price$19/mo$99/mo$499/mo$999/mo
Tokens150M1B7B15B
Chat on web, iOS, Android, desktopYesYesYesYes
Create music, videos, and imagesYesYesYesYes
Generate code and visualize dataYesYesYesYes
Write, edit, and create contentYesYesYesYes
Analyze text and imagesYesYesYesYes
Search the webYesYesYesYes
Create files and execute codeYesYesYesYes
Extended thinking for complex workYesYesYesYes
End-to-end encryptionYesYesYesYes
Memory across conversationsYesYesYes
Extended creation abilitiesYesYesYes
Train your own modelsYesYes
Mixture of Models (MOM)YesYes
Maximum deep research and agent modeYesYes
Maximum memory and contextYesYes
Multi agent modeYes
Unfiltered model accessYes

Rate Limits

Rate limits are applied per API key and vary by plan.
PlanRPMInput TPMOutput TPM
Basic60100K50K
Pro125500K200K
Max2002M800K
Turbo4505M2M
  • RPM — Requests per minute
  • Input TPM — Input tokens per minute
  • Output TPM — Output tokens per minute
When you exceed a rate limit, the API returns a 429 Too Many Requests response with Retry-After header.

Token Estimates by Capability

Approximate output if you spend your entire monthly token balance on a single capability.
Estimated ~150K tokens per image
PlanTokensImages
Basic150M~1,000
Pro1B~6,600
Max7B~46,000
Turbo15B~100,000
Unfiltered requests such as NSFW use 10x tokens
These are estimates. Actual token consumption varies based on resolution, duration, complexity, and model used.

Manage Your Plan

Visit Settings > Billing to view your current plan, upgrade, or purchase additional tokens.