v0.12.0
feder-cr/AIHawkv0.12.0Sep 7, 2026by feder-cr
AI Summary
This release introduces OpenRouter attribution headers and switches the default model to a faster, cheaper option with a significantly larger context window.
Key Highlights
- Added HTTP-Referer and X-Title headers for OpenRouter usage tracking.
- Changed default model to z-ai/glm-5.3-flash for better performance and cost.
- Updated documentation with accurate pricing and context window figures for the new model.
New Features
- OpenRouter identification headers
Full Release Notes
**Added.** The package now identifies itself to OpenRouter with the `HTTP-Referer` and `X-Title` headers, which is how the rankings at openrouter.ai/apps group usage. Requests went out anonymous before this, so the traffic counted for nobody. The headers sit on the client, so every request carries them whatever calls it. **Changed.** The default model is `z-ai/glm-5.3-flash`, in place of `z-ai/glm-4.6`. Input runs $0.071 to $0.388 per million tokens against $0.43 to $0.60, output $0.237 to $1.358 against $1.75 to $2.20, and the context window is 1,310,720 tokens against 204,800. Anyone who set `--model` or `AIHAWK_MODEL` sees no change. The wiki pages that quoted the old model and its prices were rewritten with figures retrieved the same day, including the worked cost comparison.