every-other-token (devel/every-other-token) Updated: 18 hours ago Add to my watchlist
Watch an LLM answer token by token with per-token confidenceWatch an LLM answer token by token with per-token confidence. every-other-token streams a reply from OpenAI, Anthropic, Gemini, OpenRouter or a local OpenAI-compatible server (Ollama and others), shows each token's confidence and perplexity from logprobs, and can rewrite every other token live. It runs as a CLI, a terminal UI or a local web UI. The mock provider needs no API key.
Version: 5.0.2 License: MIT
GitHub
Statistics for selected duration
2026-Oct-18 to 2026-Nov-17
No stats available for this selection.
Try changing the range of days. Alternatively visit statistics page to have an overall look at the submitted statistics.