Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.langchain.com/llms.txt

Use this file to discover all available pages before exploring further.

Private beta: The LLM Gateway is in private beta. Sign up for the waitlist to get access.
Configure coding agents to route LLM calls through the LLM Gateway, giving your organization cost controls, observability, and audit trails on developer LLM usage without changing agent code. Most coding agents let you override the LLM provider endpoint via environment variables or configuration files. By pointing them at the LLM Gateway instead of the provider directly, all LLM calls flow through the gateway. The gateway authenticates the caller, resolves the actual provider key from workspace secrets, enforces policies, and traces the call. No agent code changes required.

​
Prerequisites

​
Supported clients

  • Claude Code CLI
  • Codex CLI
  • Gemini CLI
  • Deep Agents

​
Claude Code CLI

No extra configuration beyond the environment variables. Run: 
claude
Claude Code will use ANTHROPIC_BASE_URL and ANTHROPIC_API_KEY from your environment automatically.
Claude Desktop desktop plugins break when the gateway is configured. Claude users on a paid plan (Plus, Max) are not yet supported.

​
Codex CLI

Codex requires a TOML configuration file in addition to environment variables. Add this to ~/.codex/config.toml: 
model_provider = "langsmith-gateway"

[model_providers.langsmith-gateway]
name = "LangSmith Gateway"
base_url = "https://gateway.smith.langchain.com/openai/v1"
env_key = "LANGSMITH_API_KEY"
supports_websockets = false
Make sure the LANGSMITH_API_KEY environment variable is set, then run: 
codex
Codex Desktop plugins break when the gateway is configured. The TOML configuration forces authentication through the gateway, so OpenAI no longer handles plugin auth directly.

​
Gemini CLI

No extra configuration beyond the environment variables. Run: 
gemini
Gemini CLI will use GOOGLE_GEMINI_BASE_URL and GEMINI_API_KEY from your environment automatically.

​
Deep Agents

No extra configuration beyond the environment variables. For details, refer to the provider selection docs. Run: 
deepagents

​
Python SDK usage

If you call LLM providers from Python scripts rather than through a coding agent, swap the base_url: 
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.smith.langchain.com/openai/v1",
    api_key=os.environ["LANGSMITH_API_KEY"],
)
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Say hello!"}],
)
print(response.choices[0].message.content)

​
Company-wide deployment

For organizations rolling the gateway out to all developers, distribute the configuration through MDM (mobile device management) or a shared shell profile. The key pieces to distribute are:
  1. The gateway base URL (https://gateway.smith.langchain.com).
  2. A workspace-scoped LangSmith API key per user (or per team, depending on your policy granularity).
  3. The Codex config.toml if your organization uses Codex.
Provider API keys stay centralized in LangSmith workspace secrets.

​
Verify the setup

After configuring a coding agent, make a test call and confirm that:
  1. The call succeeds (the agent gets a response).
  2. A trace appears in the gateway and gateway-<short_api_key>-<api_key_id> tracing projects in your LangSmith workspace.
If the call fails with a 403, check that your API key’s role includes gateway:invoke and workspaces:read. If it fails with a 400 mentioning a missing provider key, ask your org admin to add the provider’s key to workspace secrets.

​
Next steps

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.
Edit this page on GitHub or file an issue.