# Changelog

> Changes to ai-tally that affect how you connect or what you see, newest first.

Changes that affect how you connect or what you see, newest first.

## 2026-09-14

**The Python SDK and OpenTelemetry send to `https://ingest.ai-tally.com`.** Both use your API key. The SDK sends there by default, so `tally.init()` needs no endpoint. For OpenTelemetry, set `OTEL_EXPORTER_OTLP_TRACES_ENDPOINT` to `https://ingest.ai-tally.com/v1/otlp/traces` with `http/json`. The SDK is installed from GitHub; `pip install tally` installs an unrelated package. See the [Quickstart](https://ai-tally.com/docs/get-started/quickstart).

**Dated model names are priced.** A model name that ends in a release date, like `gpt-4o-2024-08-06`, is now priced at the rate for its base model. Before, those calls showed a blank cost. See [Prices and blanks](https://ai-tally.com/docs/cost/prices-and-blanks).

**The proxy records compressed answers.** Some AI providers send compressed answers. The proxy now reads token counts from them too. Before, those calls were recorded with no model and no tokens, so their cost was blank. Your app still receives the answer uncompressed. See [Proxy](https://ai-tally.com/docs/connect/proxy).

## Next

- New to ai-tally? Start with the [Quickstart](https://ai-tally.com/docs/get-started/quickstart).