Token Forecaster puts a range on an LLM reply before you press Enter: the usual length, and a worst case that held for 90.6% of 4,146 unseen calls. While the reply streams, it shows whether it is running long. It only watches and never changes the request. Learns from your local history. Open source, MIT.
We started with one question: can you tell how long an LLM reply will run before generation starts?
Within a range, yes. On 4,146 calls the model had never seen, 90.6% came in under our worst-case line. Extended thinking stretched the tail 2.5x. Prompt wording was worth about 1%. The real driver is how long the agent loop runs, and nothing visible before the call knows that. An oracle for loop length would cut forecast error by 63%.
Token Forecaster is what we built from those findings. Before you press Enter, it shows the usual length and a worst case. While the reply streams, it says typical, running long or very long. It runs in the terminal status line, a macOS menu bar app, a local dashboard and a Chrome extension.
It only watches. It never changes the request, never sets max_tokens, and cannot save tokens or money on its own. It is for reserving context room, catching a loop that is running away, and deciding when a task is worth splitting.
Scope today: calibrated on Claude Code history, with Codex ingestion experimental. The bundled profile comes from one developer's 16,687 calls. The daemon fits a personal profile from your own history and swaps it in only when it beats the bundled one. A second user reached 88.3% worst-case coverage on their own held-out calls. Everything runs locally: history is read, never modified, never uploaded. There is no installer yet. It builds from source on macOS (Apple silicon) and Windows.
Every experiment that failed our gate sits in the README next to the ones that passed. Tell us where the forecast misses on your workload.
Built by Eduardo Nunes at Sumcap Research.
Cool idea! Do you have insights how the prediction performs on more complex coding tasks where context and edits is scattered in multiple files?
About Token Forecaster on Product Hunt
“Forecast how long an LLM reply will run, before Enter”
Token Forecaster launched on Product Hunt on September 25th, 2026 and earned 65 upvotes and 2 comments, placing #32 on the daily leaderboard. Token Forecaster puts a range on an LLM reply before you press Enter: the usual length, and a worst case that held for 90.6% of 4,146 unseen calls. While the reply streams, it shows whether it is running long. It only watches and never changes the request. Learns from your local history. Open source, MIT.
Token Forecaster was featured in Open Source (68.9k followers), Developer Tools (520.1k followers), Artificial Intelligence (479.5k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 254.4k products, making this a competitive space to launch in.
Who hunted Token Forecaster?
Token Forecaster was hunted by Luis Pinto. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how Token Forecaster stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Luis Pinto