Keyboard shortcuts

Press or to navigate between chapters

Press S or / to search in the book

Press ? to show this help

Press Esc to hide this help

Providers & model aliases

Supported providers

Provider name--provider valueAPI key env varDefault modelNeeds key
AnthropicanthropicANTHROPIC_API_KEYclaude-sonnet-4-6
OpenAIopenaiOPENAI_API_KEYgpt-4o
Google GeminigeminiGEMINI_API_KEYgemini-flash-latest
GroqgroqGROQ_API_KEYllama-3.3-70b-versatile
Grok / xAIgrokXAI_API_KEYgrok-3
DeepSeekdeepseekDEEPSEEK_API_KEYdeepseek-chat
MistralmistralMISTRAL_API_KEYmistral-large-latest
MiniMaxminimaxMINIMAX_API_KEYminimax-text-01
OpenRouteropenrouterOPENROUTER_API_KEYanthropic/claude-3.5-sonnet
Together AItogetherTOGETHER_API_KEYLlama-3.3-70B-Instruct-Turbo
Fireworks AIfireworksFIREWORKS_API_KEYllama-v3p3-70b-instruct
LM Studiolm-studioauto-detect
Ollamaollamaauto-detect
vLLMvllmauto-detect

Local providers (LM Studio, Ollama, vLLM) are auto-detected on first run and require no API key. The model is discovered from the running server.

Model aliases

Aliases let you switch models without memorising exact IDs. They’re shown in the /model picker and accepted by --model and /model.

AliasProviderExact model ID
gemini-flash-liteGeminigemini-flash-lite-latest
gemini-flashGeminigemini-flash-latest
gemini-proGeminigemini-pro-latest
claude-haikuAnthropicclaude-haiku-4-5-20251001
claude-sonnetAnthropicclaude-sonnet-4-6
claude-opusAnthropicclaude-opus-4-6
localLM Studioauto-detect at runtime

You can also use any literal model ID your provider supports — aliases are just shortcuts. koda --model gpt-4o-mini or /model o3 both work.