Model/deployment not found for: `llama3.1-405b`

[goekce]

Before submitting your bug report

• I've tried using the "Ask AI" feature on the Continue docs site to see if the docs have an answer
• I believe this is a bug. I'll try to join the Continue Discord for questions
• I'm not able to find an open issue that reports the same bug
• I've seen the troubleshooting guide on the Continue Docs

Relevant environment info

- OS:Archlinux
- Continue version: 1.0.37-eap
- IDE version: Rider 2025.2
- Model: Llama3.1 405b Chat
- config: default

Description

I get the following error if I set up Groq with default settings.

Model/deployment not found for: `llama3.1-405b`

Ask AI mentions the following

The error "Model/deployment not found for: llama3.1-405b" indicates the model name is incorrect. Based on the Groq documentation, the correct model name is llama-3.3-70b-versatile, not llama3.1-405b.

I also noticed: Using Autodetect in the model selects meta-llama/llama-prompt-guard-2-86m which cannot be used for programming due to its narrow window.

It would be great to fix the template so that the plugin is more beginner-friendly 🙂.

To reproduce

1. Install Continue plugin
2. add more providers -> select Groq as provider
3. leave Model as default (Llama3.1 405b Chat)
4. provide API key
5. connect
6. use chat

[github-actions]

This issue hasn't been updated in 90 days and will be closed after an additional 10 days without activity. If it's still important, please leave a comment and share any new information that would help us address the issue.

[github-actions]

This issue was closed because it wasn't updated for 10 days after being marked stale. If it's still important, please reopen + comment and we'll gladly take another look!

[RomneyDa]

Groq deprecated this model. See available models here!
https://console.groq.com/docs/models