Skip to content

Conversation

@devin-ai-integration
Copy link
Contributor

Summary

Updates the hardcoded model lists in the CLI's crewai create crew command to include the latest models from major providers. This addresses issue #4317 where users reported seeing outdated models (like GPT-4 and Claude 3 Sonnet) when creating new projects.

Changes:

  • OpenAI: Added gpt-4-turbo, o1, o3, o3-mini, o4-mini; reordered to put gpt-4o first
  • Anthropic: Updated to latest Claude models including claude-sonnet-4-5, claude-3-7-sonnet, claude-3-5-sonnet-20241022, claude-3-5-haiku-20241022
  • Groq: Added Llama 3.3 models, updated to current available models
  • Ollama: Added llama3.2, llama3.3, deepseek-r1

Added tests to verify latest models are included for major providers.

Review & Testing Checklist for Human

  • Verify model names are correct - The model identifiers need to match exactly what each provider expects. Recommend testing crewai create crew test-project and selecting each provider to confirm models work.
  • Check removed models - Some older models were removed (e.g., gpt-4, claude-3-sonnet-20240229, groq/llama-3.1-405b-reasoning). Verify this is acceptable or if they should be kept for backward compatibility.
  • Validate Anthropic model dates - Model names like claude-sonnet-4-5-20250514 and claude-3-7-sonnet-20250219 should be verified against Anthropic's current API documentation.

Recommended test plan:

  1. Run crewai create crew test-project
  2. Select OpenAI provider and verify the model list looks correct
  3. Select Anthropic provider and verify the model list looks correct
  4. Optionally test creating a project with one of the new models to confirm it works

Notes

Fixes #4317

Link to Devin run: https://app.devin.ai/sessions/f81e36ee11b142e0aceb914dfa203d5c
Requested by: João

- Update OpenAI models: add gpt-4-turbo, o1, o3, o3-mini, o4-mini
- Update Anthropic models: add claude-sonnet-4-5, claude-3-7-sonnet, claude-3-5-sonnet-20241022, claude-3-5-haiku-20241022
- Update Groq models: add llama-3.3-70b-versatile, llama-3.2 variants, mixtral-8x7b-32768
- Update Ollama models: add llama3.2, llama3.3, deepseek-r1
- Add tests to verify latest models are included for major providers

Fixes #4317

Co-Authored-By: João <joao@crewai.com>
@devin-ai-integration
Copy link
Contributor Author

🤖 Devin AI Engineer

I'll be helping with this pull request! Here's what you should know:

✅ I will automatically:

  • Address comments on this PR. Add '(aside)' to your comment to have me ignore it.
  • Look at CI failures and help fix them

Note: I can only respond to comments from users who have write access to this repository.

⚙️ Control Options:

  • Disable automatic comment and CI monitoring

@cursor
Copy link

cursor bot commented Jan 31, 2026

You have run out of free Bugbot PR reviews for this billing cycle. This will reset on February 28.

To receive reviews on all of your PRs, visit the Cursor dashboard to activate Pro and start your 14-day free trial.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[FEATURE] seeing really old models when creating project via "crewai create crew <your_project_name>"

0 participants