• Your API key never leaves your browser. Memory only — gone when you close the tab.
  • Direct browser → LLM calls. No TokenEyes server in the API path.
  • Nothing logged or stored on our end.
  • Use a free restricted key where available — providers have trial/free options.
  • LLM providers may log requests per their own policies.
  • Fun project disclaimer: model responses are generated by third-party AI systems. This interface only sends your prompt/image and displays returned output.
  • No guarantees: outputs can be wrong, biased, or unexpected. Responsibility for model behavior belongs to the AI provider.
Settings
Connection
Provider
Model
Quips
API Key
Get a free key → aistudio.google.com/apikey
Advanced ▾
Paste image URL
You can also drag an image onto the camera frame, or paste one from the clipboard with Ctrl/Cmd+V.
Token math
Privacy
  • Your API key never leaves your browser.
  • Direct browser → LLM calls. No TokenEyes server in the API path.
  • Nothing logged or stored on our end.
  • LLM providers may log requests per their own policies.
Captured
Analyzing…
Analyzing…
TOKENS
—
All models breakdown ▾
ModelInputCachedOutput ReasoningTotal~Req

Pick a workload profile in settings, or set your own split. Cached input bills at ~10% of the normal rate, which is why a coding agent stretches a dollar so much further than chat. Thinking tokens bill at the output rate. A dash means the model has no cached or thinking tier.

·