Skip to main content
The Deep Agents CLI supports any chat model provider compatible with LangChain, unlocking use for virtually any LLM that supports tool calling. Any service that exposes an OpenAI-compatible or Anthropic-compatible API also works out of the box—see Compatible APIs.

​
Quick start

The CLI integrates automatically with the following model providers: no extra configuration needed beyond installing the relevant provider package.
  1. Install provider packages Each model provider requires installing its corresponding LangChain integration package. These are available as optional extras when installing the CLI, done intentionally to keep the application lightweight: 
    # Quick install with chosen providers
# OpenAI, Anthropic, and Gemini are included by default
DEEPAGENTS_EXTRAS="baseten,groq" curl -LsSf https://raw.githubusercontent.com/langchain-ai/deepagents/refs/heads/main/libs/cli/scripts/install.sh | bash

# Or install directly with uv
uv tool install 'deepagents-cli[baseten,groq]'

# Add additional packages at a later date
uv tool install deepagents-cli --with langchain-ollama

# All providers
uv tool install 'deepagents-cli[anthropic,baseten,bedrock,cohere,deepseek,fireworks,google-genai,groq,huggingface,ibm,litellm,mistralai,nvidia,ollama,openai,openrouter,perplexity,vertexai,xai]'
  2. Set credentials Store API keys in ~/.deepagents/.env so they’re available across all projects, or export them in your shell: 
    ANTHROPIC_API_KEY=sk-ant-...
OPENAI_API_KEY=sk-...
    Some providers use other credentials (for example, Vertex AI uses GOOGLE_CLOUD_PROJECT plus ADC). See the table below for the required variable per provider. You can also scope credentials to the CLI with the DEEPAGENTS_CLI_ prefix.

​
Provider reference

The Deep Agents CLI is built in Python, please use the Python provider reference docs.

​
Model routers and proxies

Model routers like OpenRouter and LiteLLM provide access to models from multiple providers through a single endpoint. Use the dedicated integration packages for these services:
RouterPackage
OpenRouterlangchain-openrouter
OpenRouter is a built-in provider—install the package and use it directly: 
uv tool install 'deepagents-cli[openrouter]'
LiteLLM is also a built-in provider: 
uv tool install 'deepagents-cli[litellm]'

​
Switching models

To switch models in the CLI, either:
  1. Use the interactive model switcher with the /model command. This displays available models sourced from each installed LangChain provider package’s model profiles.
    Not all models appear here. If yours is missing, pass the model name directly (e.g. /model gpt-5.4). See Which models appear in the switcher for details.
  2. Specify a model name directly as an argument, e.g. /model gpt-5.4. You can use any model supported by the chosen provider, regardless of whether it appears in the list from option 1. The model name will be passed to the API request.
  3. Specify the model at launch via --model, e.g. 
    deepagents --model openai:gpt-5.4

​
Which models appear in the switcher

The /model selector dynamically builds its list from installed provider packages. Expand below for the full criteria and troubleshooting.
The interactive /model selector builds its list dynamically—it is not a hardcoded list baked into the CLI. A model appears in the switcher when all of the following are true:
  1. The provider package is installed. Each provider (e.g. langchain-anthropic, langchain-openai) must be installed alongside deepagents-cli—either as an install extra (e.g. uv tool install 'deepagents-cli[ollama]') or added later with uv tool install deepagents-cli --with <package>. If a package is missing, its entire provider section is absent from the switcher.
  2. The model has a profile with tool_calling enabled. The CLI requires tool-calling support, so models without tool_calling: true in their profile are excluded. This is the most common reason a model is missing from the list. For providers that don’t bundle profiles (see the Provider reference table), you can define one in config.toml: 
    [models.providers.ollama.profile."qwen3:4b"]
tool_calling = true
max_input_tokens = 32768
max_output_tokens = 8192
    This is not strictly required for the model to appear in the switcher — adding it to the models list also works and is simpler. A profile is useful when you want the CLI to know the model’s context window and capabilities for features like auto-summarization. See Profile overrides for all overridable fields.
  3. The model accepts and produces text. Models whose profile explicitly sets text_inputs or text_outputs to false (e.g. embedding or image-generation models) are excluded.
Models defined in config.toml under [models.providers.<name>].models bypass the profile filter—they always appear in the switcher regardless of profile metadata. This is the recommended way to add models that are missing from the list.
Credential status does not affect whether a model is listed. The switcher shows all qualifying models and displays a credential indicator next to each provider header: a checkmark for confirmed credentials, a warning for missing credentials, or a question mark when credential status is unknown. You can still select a model with missing credentials—the provider will report an authentication error at request time.

​
Troubleshooting missing models

SymptomLikely causeFix
Entire provider missing from switcherProvider package not installedInstall the package (e.g. uv tool install deepagents-cli --with langchain-groq)
Provider shown but specific model missingModel profile has tool_calling: false or no profile existsAdd the model to [models.providers.<name>].models in config.toml, or use /model <provider>:<model> directly
Provider shows ⚠ “missing credentials”API key env var not setSet the credential env var from the Provider reference table
Provider shows ? “credentials unknown”Provider uses non-standard auth that the CLI can’t verifyCredentials may still work—try switching to the model. If auth fails, check the provider’s docs

​
Setting a default model

You can set a persistent default model that will be used for all future CLI launches:
  • Via model selector: Open /model, navigate to the desired model, and press Ctrl+S to pin it as the default. Pressing Ctrl+S again on the current default clears it.
  • Via command: /model --default provider:model (e.g., /model --default anthropic:claude-opus-4-6)
  • Via config file: Set [models].default in ~/.deepagents/config.toml (see Configuration).
  • From the shell: 
    deepagents --default-model anthropic:claude-opus-4-6
To view the current default: 
deepagents --default-model
To clear the default:
  • From the shell: 
    deepagents --clear-default-model
  • Via command: /model --default --clear
  • Via model selector: Press Ctrl+S on the currently pinned default model.
Without a default, the CLI will default to the most recently used model.

​
Model resolution order

When the CLI launches, it resolves which model to use in the following order:
  1. --model flag always wins when provided.
  2. [models].default in ~/.deepagents/config.toml—The user’s intentional long-term preference.
  3. [models].recent in ~/.deepagents/config.toml—The last model switched to via /model. Written automatically; never overwrites [models].default.
  4. Environment auto-detection: Falls back to the first available startup credential, checked in order: OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY, GOOGLE_CLOUD_PROJECT (Vertex AI).
This startup fallback intentionally checks only those four credentials. Other supported providers (for example, Groq) are still available via --model, /model, and saved defaults ([models].default / [models].recent).

​
Advanced configuration

For detailed configuration of provider params, profile overrides, custom base URLs, compatible APIs, arbitrary providers, and lifecycle hooks, see Configuration.
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.