Providers

HelixMind supports 7 LLM providers through a unified provider abstraction.

Anthropic (Default, Recommended)

helixmind config set provider anthropic
helixmind config set apiKey sk-ant-...

Model	Best For
claude-opus-4-6	Complex analysis, architecture, multi-step tasks
claude-sonnet-4-6	General coding, balanced speed/quality (default)
claude-haiku-4-5	Fast responses, simple tasks

OpenAI

helixmind config set provider openai
helixmind config set apiKey sk-...

Model	Best For
gpt-4o	General coding (default)
gpt-4o-mini	Fast, cost-effective
o1 / o1-mini / o3-mini	Advanced reasoning tasks

Ollama (Offline)

helixmind config set provider ollama

No API key needed. See Ollama & Offline for setup.

Model	Best For
qwen2.5-coder:32b	Best local coding model (default)
qwen3-coder:30b	Latest Qwen coding model
deepseek-r1	Reasoning-focused tasks

Groq

helixmind config set provider groq
helixmind config set apiKey gsk_...

Model	Best For
llama-3.3-70b-versatile	General purpose (default)
llama-3.1-8b-instant	Fast, simple tasks

DeepSeek

helixmind config set provider deepseek
helixmind config set apiKey sk-...

Model	Best For
deepseek-chat	General coding (default)
deepseek-reasoner	Complex reasoning

Together AI

helixmind config set provider together
helixmind config set apiKey ...

Model	Best For
meta-llama/Llama-3.3-70B-Instruct-Turbo	General purpose (default)

OpenRouter

helixmind config set provider openrouter
helixmind config set apiKey sk-or-...

Access multiple providers through a single API key.

Switching Models

helixmind config set model claude-opus-4-6   # Via config
/model                                        # Interactive picker in chat

Feature Comparison

Feature	Anthropic	OpenAI	Ollama	Groq	DeepSeek	Together	OpenRouter
Streaming	✅	✅	✅	✅	✅	✅	✅
Tool Calling	✅	✅	✅	Limited	✅	✅	✅
Rate Limit Retry	✅	✅	N/A	✅	✅	✅	✅
Offline	❌	❌	✅	❌	❌	❌	❌

All providers implement the same LLMProvider interface (stream() + chatWithTools()). Switching providers doesn't change your workflow.