Richard Feldman a4cc10c3fa Add GPT-5.4 and GPT-5.4-pro BYOK models (#50858) ...

Add GPT-5.4 and GPT-5.4-pro as Bring Your Own Key model options for the
OpenAI provider.

**GPT-5.4** (`gpt-5.4`):
- 1,050,000 token context window, 128K max output
- Supports chat completions, images, parallel tool calls
- Default reasoning effort: none

**GPT-5.4-pro** (`gpt-5.4-pro`):
- 1,050,000 token context window, 128K max output
- Responses API only (no chat completions)
- Default reasoning effort: medium (supports medium/high/xhigh)

Also fixes context window sizes for GPT-5 mini and GPT-5 nano (272K →
400K) to match current OpenAI docs.

Closes AI-78

Release Notes:

- Added GPT-5.4 and GPT-5.4-pro as available models when using your own
OpenAI API key.

2026-03-05 23:40:03 -05:00

..

src

Add GPT-5.4 and GPT-5.4-pro BYOK models (#50858)

2026-03-05 23:40:03 -05:00

Cargo.toml

ep: Use rejected_output for DPO training + OpenAI support (#47697)

2026-01-27 13:02:40 +00:00

LICENSE-GPL

Fix licensing errors

2024-03-20 15:52:02 +01:00