Models

Configure model providers and parameters for Deep Agents

Deep Agents work with any LangChain chat model that supports tool calling.

Supported models

Specify models in provider:model format (for example, google_genai:gemini-3.1-pro-preview, openai:gpt-5.4, or anthropic:claude-sonnet-4-6). For valid provider strings, see the model_provider parameter of init_chat_model. For provider-specific configuration, see chat model integrations.

Suggested models

These models perform well on the Deep Agents eval suite, which tests basic agent operations. Passing these evals is necessary but not sufficient for strong performance on longer, more complex tasks.

Provider	Models
Google	gemini-3.1-pro-preview, gemini-3-flash-preview
OpenAI	gpt-5.4, gpt-4o, gpt-5.4, o4-mini, gpt-5.2-codex, gpt-4o-mini, o3
Anthropic	claude-opus-4-6, claude-opus-4-5, claude-sonnet-4-6, claude-sonnet-4, claude-sonnet-4-5, claude-haiku-4-5, claude-opus-4-1
Open-weight	GLM-5, Kimi-K2.5, MiniMax-M2.5, qwen3.5-397B-A17B, devstral-2-123B

Open-weight models are available through providers like OpenRouter, Fireworks or Ollama.

Configure model parameters

Pass a model string to createDeepAgent in provider:model format, or pass a configured model instance for full control. Under the hood, model strings are resolved via init_chat_model.

To configure model-specific parameters, use init_chat_model or instantiate a provider model class directly:

initChatModel

import { initChatModel } from "langchain/chat_models/universal";
import { createDeepAgent } from "deepagents";

const model = await initChatModel("google_genai:gemini-3.1-pro-preview", {
    reasoningEffort: "medium",  
});
const agent = createDeepAgent({ model });

Available parameters vary by provider. See the chat model integrations page for provider-specific configuration options.

Provider profiles

A ProviderProfile packages initialization parameters that apply when you provide a provider:model string when creating the deep agent. It does not apply when you pass a preconfigured model with init_chat_model.

You can register at two levels, and both can coexist:

• Provider level — a bare provider key like "openai" applies to every model from the openai provider.
• Model level — a provider:model key like "openai:gpt-5.4" applies only to that specific model, and merges on top of any matching provider-level profile.

from deepagents import ProviderProfile, register_provider_profile

# Provider-wide default: every openai model gets temperature=0.
register_provider_profile(
    "openai",
    ProviderProfile(init_kwargs={"temperature": 0}),
)

# Model-level override: gpt-5.4 additionally gets a specific reasoning effort.
# Inherits temperature=0 from the provider-level profile above.
register_provider_profile(
    "openai:gpt-5.4",
    ProviderProfile(init_kwargs={"reasoning_effort": "medium"}),
)

See Profiles for the full field list, merge semantics, and plugin packaging.

For shaping how the agent behaves once the model is built, use a harness profile.

Select a model at runtime

If your application lets users choose a model (for example using a dropdown in the UI), use middleware to swap the model at runtime without rebuilding the agent.

import { initChatModel, createMiddleware } from "langchain";
import { createDeepAgent } from "deepagents";
import * as z from "zod";

const contextSchema = z.object({
  model: z.string(),
});

const configurableModel = createMiddleware({
  name: "ConfigurableModel",
  wrapModelCall: async (request, handler) => {
    const modelName = request.runtime.context.model;
    const model = await initChatModel(modelName);
    return handler({ ...request, model });
  },
});

const agent = await createDeepAgent({
  model: "google_genai:gemini-3.1-pro-preview",
  middleware: [configurableModel],
  contextSchema,
});

// Invoke with the user's model selection
const result = await agent.invoke(
  { messages: [{ role: "user", content: "Hello!" }] },
  { context: { model: "openai:gpt-5.4" } },
);

For more dynamic model patterns (for example routing based on conversation complexity or cost optimization), see Dynamic model in the LangChain agents guide.

Learn more

• Models in LangChain: chat model features including tool calling, structured output, and multimodality

---

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.