` (built-in, see [Provider reference](#provider-reference)) |
**OpenRouter** is a built-in provider—install the extra and use it directly:
```txt In session theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
/install openrouter
```
```bash Shell theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
dcode --install openrouter
```
**LiteLLM** is also a built-in provider:
```txt In session theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
/install litellm
```
```bash Shell theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
dcode --install litellm
```
## Switch models
To switch models in Deep Agents Code, either:
1. **Use the interactive model switcher** with the `/model` command.
Not all models appear here. If yours is missing, pass the model name directly (e.g. `/model gpt-5.5`) or add it to `config.toml`.
2. **Specify a model name directly** as an argument, e.g. `/model gpt-5.5`. 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.
```txt theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
dcode --model openai:gpt-5.5
```
When Deep Agents Code 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`).
### 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 from installed provider packages and models configured in `config.toml`.
A model appears when:
1. The provider package is installed.
2. The model is available from the provider package, a local provider, or your `config.toml`.
3. The model profile does not mark text input or output as unsupported.
If a model is missing, use `/model :` directly or add it to [`[models.providers.].models`](/oss/python/deepagents/code/configuration#adding-models-to-the-interactive-switcher).
Credential status does **not** affect whether a model is listed. You can still select a model with missing credentials. The provider reports an authentication error at request time.
### Open weights models
If you want to use an open weights model, there are two common paths depending on whether you prefer local or cloud-hosted inference.
**Local inference with Ollama** is the easiest way to get started for free, with no API key required:
1. [Install Ollama](https://ollama.com/) and pull a model, for example:
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
ollama pull qwen3:4b
```
2. Install the Ollama extra:
```txt In session theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
/install ollama
```
```bash Shell theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
dcode --install ollama
```
3. Select the model:
```txt In session theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
/model
```
```bash Shell theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
dcode --model ollama:qwen3:4b
```
Use the interactive switcher, or pass the model directly with `/model ollama:qwen3:4b`.
**Cloud-hosted open weights via Groq** gives you fast inference without running anything locally:
1. Get a free API key at [console.groq.com](https://console.groq.com/).
2. Install the Groq extra:
```txt In session theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
/install groq
```
```bash Shell theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
dcode --install groq
```
3. Select a model:
```txt In session theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
/model
```
```bash Shell theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
GROQ_API_KEY="your-api-key" dcode --model groq:openai/gpt-oss-120b
```
Use the interactive switcher, or pass the model directly with `/model groq:openai/gpt-oss-120b`.
**Fireworks** is another popular cloud provider for open weights models:
```txt In session theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
/install fireworks
/model
```
```bash Shell theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
dcode --install fireworks
FIREWORKS_API_KEY="your-api-key" dcode --model fireworks:accounts/fireworks/models/deepseek-v4-pro
```
Use the interactive switcher, or pass the model directly with `/model fireworks:accounts/fireworks/models/deepseek-v4-pro`.
**Baseten** is another cloud provider for open weights models:
```txt In session theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
/install baseten
/model
```
```bash Shell theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
dcode --install baseten
BASETEN_API_KEY="your-api-key" dcode --model baseten:moonshotai/Kimi-K2.7-Code
```
Use the interactive switcher, or pass the model directly with `/model baseten:moonshotai/Kimi-K2.7-Code`.
If you want a provider preinstalled at the same time as the CLI itself, use `DEEPAGENTS_CODE_EXTRAS` during the initial install:
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
DEEPAGENTS_CODE_EXTRAS="fireworks" curl -LsSf https://langch.in/dcode | bash
```
You can combine multiple providers: `DEEPAGENTS_CODE_EXTRAS="groq,fireworks,ollama"`. If Deep Agents Code is already installed, use `/install ` in a session or `dcode --install ` from the shell instead.
**Together**, **OpenRouter**, and **Hugging Face** (`langchain-huggingface`) are other options for cloud-hosted open weights. See the [Provider reference](#provider-reference) for credentials and package names.
### Set a default model
You can set a persistent default model that applies to 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-4-8`)
* **Via config file:** Set `[models].default` in `~/.deepagents/config.toml` (see [Configuration](/oss/python/deepagents/code/configuration)).
* **From the shell:**
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
dcode --default-model anthropic:claude-opus-4-8
```
To view the current default:
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
dcode --default-model
```
To clear the default:
* **From the shell:**
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
dcode --clear-default-model
```
* **Via command:** `/model --default --clear`
* **Via model selector:** Press `Ctrl+S` on the currently pinned default model.
Without a default, Deep Agents Code uses the most recently used model.
### Model parameters
Pass extra constructor kwargs to the model—sampling controls, reasoning/thinking budgets, context window sizes, request timeouts, and anything else the underlying chat-model class accepts. Three places to set them, in priority order (highest first):
1. **One-off at launch with `--model-params`.** JSON string, session-only:
```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# OpenAI reasoning effort
dcode --model openai:gpt-5.5 --model-params '{"reasoning": {"effort": "high"}}'
# Anthropic extended thinking
dcode --model anthropic:claude-opus-4-8 --model-params '{"thinking": {"type": "enabled", "budget_tokens": 10000}, "max_tokens": 16000}'
```
2. **Mid-session via `/model --model-params`.** Same JSON syntax—swaps params (and optionally the model) without restarting:
```txt theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
/model --model-params '{"temperature": 0.7}' anthropic:claude-opus-4-8
/model --model-params '{"num_ctx": 16384}' # opens selector, applies params to choice
```
3. **Persistent in `config.toml`.** Provider-level defaults (with optional per-model sub-tables) that apply on every launch:
```toml theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
[models.providers.anthropic.params]
thinking = { type = "enabled", budget_tokens = 10000 }
max_tokens = 16000
[models.providers.openai.params]
reasoning = { effort = "high", summary = "auto" }
output_version = "responses/v1"
[models.providers.ollama.params]
num_ctx = 16384
temperature = 0
# Per-model override—wins over provider-level keys
[models.providers.ollama.params."qwen3:4b"]
temperature = 0.5
```
CLI flags override config-file `params` and are session-only (mid-session changes are not persisted). Per-model sub-tables in `config.toml` override provider-level keys (shallow merge—see [Model constructor params](/oss/python/deepagents/code/configuration#model-constructor-params) for full semantics). `--model-params` cannot be combined with `--default`.
For retry counts, prefer `--max-retries` or the top-level [`[retries]` config](/oss/python/deepagents/code/configuration#retries).
Any kwarg accepted by the underlying chat-model constructor is valid. Refer to the provider's reference docs for the full list—e.g. [`ChatAnthropic`](https://reference.langchain.com/python/langchain-anthropic/langchain_anthropic/chat_models/ChatAnthropic), [`ChatOpenAI`](https://reference.langchain.com/python/langchain-openai/langchain_openai/chat_models/base/ChatOpenAI), [`ChatOllama`](https://reference.langchain.com/python/langchain-ollama/langchain_ollama/chat_models/ChatOllama). Unknown kwargs are forwarded to the upstream API request, so newly released parameters work without a CLI update.
Don't put credentials (`api_key`) in `params`—use [`api_key_env`](/oss/python/deepagents/code/configuration#provider-configuration) to point at an environment variable instead.
To override fields on the model's runtime *profile* (`max_input_tokens`, `tool_calling`, capability flags)—distinct from constructor params—see [Profile overrides](/oss/python/deepagents/code/configuration#profile-overrides-advanced).
## Advanced configuration
For detailed configuration of provider params, profile overrides, custom base URLs, compatible APIs, arbitrary providers, and lifecycle hooks, see [Configuration](/oss/python/deepagents/code/configuration).
***
[Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
[Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/deepagents/code/providers.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).