Skip to content

Update recommended model names in docs #808

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
klieret merged 1 commit into from
May 20, 2026
+8 −8
Merged

Update recommended model names in docs #808

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 3 additions & 3 deletions docs/models/quickstart.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,9 +93,9 @@ There are several ways to set your API keys:
Here's a few examples of popular models:

```
anthropic/claude-sonnet-4-5-20250929
openai/gpt-5
openai/gpt-5-mini
anthropic/claude-opus-4-6-20260205
openai/gpt-5.4
openai/gpt-5.4-mini
gemini/gemini-2.5-pro
deepseek/deepseek-chat
```
Expand Down
4 changes: 2 additions & 2 deletions docs/quickstart.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,6 +129,6 @@

!!! success "Which model to use?"

We recommend using `anthropic/claude-sonnet-4-5-20250929` for most tasks.
For openai models, we recommend using `openai/gpt-5` or `openai/gpt-5-mini`.
We recommend using `anthropic/claude-opus-4-6-20260205` for most tasks.
For openai models, we recommend using `openai/gpt-5.4` or `openai/gpt-5.4-mini`.
You can check scores of different models at our [SWE-bench (bash-only)](https://swebench.com) leaderboard.
6 changes: 3 additions & 3 deletions src/minisweagent/run/utilities/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,8 +39,8 @@ def _reload_config():

Here's a few popular models and the required API keys:

[bold green]anthropic/claude-sonnet-4-5-20250929[/bold green] ([bold green]ANTHROPIC_API_KEY[/bold green])
[bold green]openai/gpt-5[/bold green] or [bold green]openai/gpt-5-mini[/bold green] ([bold green]OPENAI_API_KEY[/bold green])
[bold green]anthropic/claude-opus-4-6-20260205[/bold green] ([bold green]ANTHROPIC_API_KEY[/bold green])
[bold green]openai/gpt-5.4[/bold green] or [bold green]openai/gpt-5.4-mini[/bold green] ([bold green]OPENAI_API_KEY[/bold green])
[bold green]gemini/gemini-3-pro-preview[/bold green] ([bold green]GEMINI_API_KEY[/bold green])

[bold]Note: Please always include the provider (e.g., "openai/") in the model name.[/bold]
Expand Down Expand Up @@ -71,7 +71,7 @@ def setup():
"""Setup the global config file."""
console.print(_SETUP_HELP.format(global_config_file=global_config_file))
default_model = prompt(
"Enter your default model (e.g., anthropic/claude-sonnet-4-5-20250929): ",
"Enter your default model (e.g., anthropic/claude-opus-4-6-20260205): ",
default=os.getenv("MSWEA_MODEL_NAME", ""),
).strip()
if default_model:
Expand Down