◆ Inference Provider
Choose how to connect to your main chat model.
Guide: https://hermes-agent.nousresearch.com/docs/integrations/providers
Current model: gpt-6-astra
Active provider: ChatGPT or Codex Subscription
Custom OpenAI-compatible endpoint configuration:
API base URL [e.g. https://api.example.com/v1]: https://api.groq.com/openai/v1
API key [optional]: ********************************************************
Verified endpoint via https://api.groq.com/openai/v1/models (11 model(s) visible)
Select API compatibility mode:
1. Auto-detect [current]
Use Hermes URL heuristics; best for standard OpenAI-compatible endpoints.
2. Chat Completions
Use /chat/completions for standard OpenAI-compatible servers.
3. Responses / Codex
Use /responses for Codex-compatible tool-calling backends.
4. Anthropic Messages
Use /v1/messages for Anthropic-compatible endpoints.
Choice [1-4, Enter to keep current/detected]: 2
API mode: chat_completions
Available models:
1. meta-llama/llama-prompt-guard-2-22m
2. canopylabs/orpheus-arabic-saudi
3. whisper-large-v3
4. openai/gpt-oss-safeguard-20b
5. meta-llama/llama-prompt-guard-2-86m
6. qwen/qwen3.8-27b
7. openai/gpt-oss-120b
8. canopylabs/orpheus-v1-english
9. whisper-large-v3-turbo
10. openai/gpt-oss-20b
11. allam-2-7b
Select model [1-11] or type name: 7
Context length in tokens [leave blank for auto-detect]:
Display name [Api.groq.com]: Groq Free
Context length auto-detected: 131.1K tokens
API key saved to .env as HERMES_CUSTOM_API_GROQ_COM_API_KEY
Default model set to: openai/gpt-oss-120b (via https://api.groq.com/openai/v1)
💾 Saved to custom providers as "Groq Free" (edit in config.yaml)
Reasoning effort set to: low
✓ Model & Provider configuration complete!