Providers & API Keys
Every supported LLM provider, its default model, and its API-key variable.
NevoFlux supports many LLM providers. Select one in
Settings → AI Models or by setting provider in
config.toml.
Supported providers
| Provider | provider value | Default model | API key env var |
|---|---|---|---|
| Anthropic | anthropic | claude-sonnet-4-20250514 | ANTHROPIC_API_KEY |
| OpenAI | openai | gpt-4o-mini | OPENAI_API_KEY |
| OpenRouter | openrouter | anthropic/claude-3-haiku | OPENROUTER_API_KEY |
| DeepSeek | deepseek | deepseek-chat | DEEPSEEK_API_KEY |
| Qwen (DashScope) | qwen | qwen-turbo | DASHSCOPE_API_KEY |
| Google Gemini | gemini | gemini-3-flash-preview | GEMINI_API_KEY |
| Groq | groq | llama-3.3-70b-versatile | GROQ_API_KEY |
| Ollama (local) | ollama | llama3.2 | OLLAMA_API_KEY |
| Mistral | mistral | mistral-small-latest | MISTRAL_API_KEY |
| xAI / Grok | xai (alias grok) | grok-2-latest | XAI_API_KEY |
| Cohere | cohere | command-r-plus | COHERE_API_KEY |
| Perplexity | perplexity | llama-3.1-sonar-small-128k-online | PERPLEXITY_API_KEY |
| Together | together | meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | TOGETHER_API_KEY |
| Claude Code (CLI) | claude-code | sonnet | ANTHROPIC_API_KEY |
| Gemini CLI | gemini-cli | gemini-2.5-pro | GEMINI_API_KEY |
| Kimi Agent | kimi-agent (alias kimi) | kimi-latest | MOONSHOT_API_KEY |
| OpenClaw | openclaw | default | OPENCLAW_API_KEY |
Provider types. The AI Models tab groups these as service (cloud APIs), local (Ollama), CLI (
claude-code,gemini-cli,kimi-agent— these run a local command-line agent and manage their own auth), and agent (openclaw). CLI/agent providers stream their output; a couple of providers (notably Ollama) do not support streaming.
Supplying API keys
There are two ways to give a provider its key; the agent checks them in this order:
-
In
config.toml—api_keyunder[llm.<provider>]:[llm.anthropic] api_key = "sk-ant-..." -
Environment variable — the variable from the table above, e.g.:
export ANTHROPIC_API_KEY="sk-ant-..."
NevoFlux does not store keys in an OS keychain. Use the config file or an environment variable.
Custom endpoints
Set base_url under a provider to point at a proxy or an OpenAI-compatible server:
[llm.openai]
model = "my-model"
base_url = "https://my-gateway.example.com/v1"Switching the active model
Change the active provider in Settings → AI Models, edit
provider in config.toml, or ask the agent to switch models mid-conversation
(it has a switch_model capability).