Release 0.15

Refs #515, #525, #536, #537

docs/changelog.md

@@ -1,5 +1,12 @@
 # Changelog
 
+(v0_15)=
+## 0.15 (2024-07-18)
+
+- Support for OpenAI's [new GPT-4o mini](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) model: `llm -m gpt-4o-mini 'rave about pelicans in French'` [#536](https://github.com/simonw/llm/issues/536)
+- `gpt-4o-mini` is now the default model if you do not {ref}`specify your own default <setup-default-model>`, replacing GPT-3.5 Turbo. GPT-4o mini is both cheaper and better than GPT-3.5 Turbo.
+- Fixed a bug where `llm logs -q 'flourish' -m haiku` could not combine both the `-q` search query and the `-m` model specifier. [#515](https://github.com/simonw/llm/issues/515)
+
 (v0_14)=
 ## 0.14 (2024-05-13)
 

docs/setup.md

@@ -134,14 +134,15 @@ llm 'my prompt' --key $OPENAI_API_KEY
 
 You can configure LLM in a number of different ways.
 
+(setup-default-model)=
 ### Setting a custom default model
 
 The model used when calling `llm` without the `-m/--model` option defaults to `gpt-4o-mini` - the fastest and least expensive OpenAI model.
 
-You can use the `llm models default` command to set a different default model. For GPT-4 (slower and more expensive, but more capable) run this:
+You can use the `llm models default` command to set a different default model. For GPT-4o (slower and more expensive, but more capable) run this:
 
 ```bash
-llm models default gpt-4
+llm models default gpt-4o
 ```
 You can view the current model by running this:
 ```

setup.py

@@ -1,7 +1,7 @@
 from setuptools import setup, find_packages
 import os
 
-VERSION = "0.14"
+VERSION = "0.15"
 
 
 def get_long_description():