Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
53 changes: 50 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ This plugin **is a preview**. LLM currently ships with OpenAI models as part of

This plugin implements those same models using the new [Responses API](https://platform.openai.com/docs/api-reference/responses).

Currently the only reason to use this plugin over the LLM defaults is to access [o1-pro](https://platform.openai.com/docs/models/o1-pro), which can only be used via the Responses API.
Use this plugin when you want direct access to the Responses API from LLM, including newer model IDs, reasoning controls, server-side conversation chaining, and OpenAI-hosted tools such as web search.

## Installation

Expand All @@ -21,10 +21,10 @@ llm install llm-openai-plugin
```
## Usage

To run a prompt against `o1-pro` do this:
To run a prompt against `gpt-5.4` do this:

```bash
llm -m openai/o1-pro "Convince me that pelicans are the most noble of birds"
llm -m openai/gpt-5.4 "Convince me that pelicans are the most noble of birds"
```

Run this to see a full list of models - they start with the `openai/` prefix:
Expand All @@ -46,14 +46,24 @@ cog.out(
)
]]] -->
```
OpenAI: openai/gpt-4
OpenAI: openai/gpt-4-turbo
OpenAI: openai/gpt-4-turbo-2024-04-09
OpenAI: openai/gpt-4o
OpenAI: openai/gpt-4o-2024-05-13
OpenAI: openai/gpt-4o-2024-08-06
OpenAI: openai/gpt-4o-2024-11-20
OpenAI: openai/gpt-4o-mini
OpenAI: openai/gpt-4o-mini-2024-07-18
OpenAI: openai/gpt-4.5-preview
OpenAI: openai/gpt-4.5-preview-2025-02-27
OpenAI: openai/o3-mini
OpenAI: openai/o3-mini-2025-01-31
OpenAI: openai/o1-mini
OpenAI: openai/o1
OpenAI: openai/o1-2024-12-17
OpenAI: openai/o1-pro
OpenAI: openai/o1-pro-2025-03-19
OpenAI: openai/gpt-4.1
OpenAI: openai/gpt-4.1-2025-04-14
OpenAI: openai/gpt-4.1-mini
Expand All @@ -68,7 +78,9 @@ OpenAI: openai/o4-mini
OpenAI: openai/o4-mini-2025-04-16
OpenAI: openai/codex-mini-latest
OpenAI: openai/o3-pro
OpenAI: openai/o3-pro-2025-06-10
OpenAI: openai/gpt-5
OpenAI: openai/gpt-5-chat-latest
OpenAI: openai/gpt-5-mini
OpenAI: openai/gpt-5-nano
OpenAI: openai/gpt-5-2025-08-07
Expand All @@ -77,12 +89,47 @@ OpenAI: openai/gpt-5-nano-2025-08-07
OpenAI: openai/gpt-5-codex
OpenAI: openai/gpt-5-pro
OpenAI: openai/gpt-5-pro-2025-10-06
OpenAI: openai/gpt-5.1
OpenAI: openai/gpt-5.1-2025-11-13
OpenAI: openai/gpt-5.1-chat-latest
OpenAI: openai/gpt-5.1-codex
OpenAI: openai/gpt-5.1-codex-mini
OpenAI: openai/gpt-5.1-codex-max
OpenAI: openai/gpt-5.2
OpenAI: openai/gpt-5.2-2025-12-11
OpenAI: openai/gpt-5.2-chat-latest
OpenAI: openai/gpt-5.2-codex
OpenAI: openai/gpt-5.2-pro
OpenAI: openai/gpt-5.2-pro-2025-12-11
OpenAI: openai/gpt-5.3-chat-latest
OpenAI: openai/gpt-5.3-codex
OpenAI: openai/gpt-5.4
OpenAI: openai/gpt-5.4-2026-03-05
OpenAI: openai/gpt-5.4-pro
OpenAI: openai/gpt-5.4-pro-2026-03-05
```
<!-- [[[end]]] -->
Add `--options` to see a full list of options that can be provided to each model.

The `o3-streaming` model ID exists because o3 currently requires a verified organization in order to support streaming. If you have a verified organization you can use `o3-streaming` - everyone else should use `o3`.

## Web Search

Enable OpenAI's hosted `web_search` tool like this:

```bash
llm -m openai/gpt-5.4 \
-o openai_tools web_search \
"Top 3 OpenAI stories from this week"
```

Optional search controls:

- `-o web_search_domains openai.com,wikipedia.org`
- `-o web_search_live false`
- `-o web_search_context_size high`
- `-o web_search_sources true`

## Development

To set up this plugin locally, first checkout the code. Then create a new virtual environment:
Expand Down
Loading