Docs/Core Concepts/Models & Providers

Models & Providers

Dynamo is provider-agnostic. Use any LLM from any provider.

Switching Models

Use the interactive picker or switch directly:

bash

/model          # Opens interactive picker
/model opus     # Switch to Claude Opus
/model gpt     # Switch to GPT-5.4
/model llama    # Switch to Ollama Llama

Your choice is saved to ~/.config/dynamo/preferences.json and restored on next launch.

Available Aliases

Anthropic

Alias	Model
`opus`	claude-opus-4-6
`sonnet`	claude-sonnet-4-6
`haiku`	claude-haiku-4-5

OpenAI

Alias	Model
`gpt`	gpt-5.4
`mini`	gpt-5.4-mini
`nano`	gpt-5.4-nano

Ollama

Alias	Model
`llama`	llama4
`qwen`	qwen3.5
`qwen-coder`	qwen3.5-coder

Per-Phase Models

Mix providers per workflow phase in dynamo.yaml:

yaml

ai:
  models:
    interactive: "anthropic/claude-sonnet-4-6"
    planning: "anthropic/claude-opus-4-6"
    implementation: "openai/gpt-5.3-codex"
    audit: "openai/gpt-5.4-mini"
    docs: "ollama/llama4"

Custom Providers

Add any OpenAI-compatible endpoint:

yaml

ai:
  providers:
    deepseek:
      type: "openai-compatible"
      base_url: "https://api.deepseek.com/v1"
      api_key_env: "DEEPSEEK_API_KEY"

Token Display

After each response, Dynamo shows token usage:

tokens: 1,234 in · 567 out · 89 reasoning

Commands & Shortcuts Configuration