Custom model providers

Configure any LangChain-compatible model provider for the Deep Agents CLI

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:

   # Quick install with chosen providers (OpenAI included automatically)
   DEEPAGENTS_EXTRAS="anthropic,groq" curl -LsSf https://raw.githubusercontent.com/langchain-ai/deepagents/main/scripts/install.sh | bash
   
   # Or install directly with uv
   uv tool install 'deepagents-cli[anthropic,groq]'
   
   # Add additional packages at a later date
   uv tool upgrade deepagents-cli --with langchain-ollama
   
   # All providers
   uv tool install 'deepagents-cli[anthropic,bedrock,cohere,deepseek,fireworks,google-genai,groq,huggingface,ibm,mistralai,nvidia,ollama,openai,openrouter,perplexity,vertexai,xai]'
   

2. Set credentials

   Most providers require an API key. Set the appropriate environment variable listed in the table below. Some providers use other credentials (for example, Vertex AI uses GOOGLE_CLOUD_PROJECT plus ADC). Refer to each integration package’s docs for details.

Provider reference

Using a provider not listed here? See Arbitrary providers — any LangChain-compatible provider can be used in the CLI with some additional setup.

Provider	Package	Credential env var	Model profiles
OpenAI	langchain-openai	OPENAI_API_KEY	✅
Azure OpenAI	langchain-openai	AZURE_OPENAI_API_KEY	✅
Anthropic	langchain-anthropic	ANTHROPIC_API_KEY	✅
Google Gemini API	langchain-google-genai	GOOGLE_API_KEY	✅
Google Vertex AI	langchain-google-vertexai	GOOGLE_CLOUD_PROJECT	✅
AWS Bedrock	langchain-aws	AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY	✅
AWS Bedrock Converse	langchain-aws	AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY	✅
Hugging Face	langchain-huggingface	HUGGINGFACEHUB_API_TOKEN	✅
Ollama	langchain-ollama	Optional	❌
Groq	langchain-groq	GROQ_API_KEY	✅
Cohere	langchain-cohere	COHERE_API_KEY	❌
Fireworks	langchain-fireworks	FIREWORKS_API_KEY	✅
Together	langchain-together	TOGETHER_API_KEY	❌
Mistral AI	langchain-mistralai	MISTRAL_API_KEY	✅
DeepSeek	langchain-deepseek	DEEPSEEK_API_KEY	✅
IBM (watsonx.ai)	langchain-ibm	WATSONX_APIKEY	❌
Nvidia	langchain-nvidia-ai-endpoints	NVIDIA_API_KEY	❌
xAI	langchain-xai	XAI_API_KEY	✅
Perplexity	langchain-perplexity	PPLX_API_KEY	✅
OpenRouter	langchain-openrouter	OPENROUTER_API_KEY	✅

A model profile is a bundle of metadata (model name, default parameters, capabilities, etc.) that ships with a provider package, largely powered by the models.dev project. Providers that include model profiles have their models listed automatically in the interactive /model switcher. Providers without model profiles require you to specify the model name directly.

Switching models

To switch models in the CLI, either:

1. Use the interactive model switcher with the /model command. This displays a hardcoded list of known model profiles sourced from each LangChain provider package.

   Note that these profiles are not an exhaustive list of available models. If the model you want isn’t shown, use option 2 instead (useful for newly released models that haven’t been added to the profiles yet).

2. Specify a model name directly as an argument, e.g. /model openai:gpt-4o. 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-4o
   

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).

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:

Router	Package	Config
OpenRouter	langchain-openrouter	openrouter:<model> (built-in, see Provider reference)

OpenRouter is a built-in provider — install the package and use it directly:

uv tool install 'deepagents-cli[openrouter]'

---

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.