Coding agents

This page points a coding harness at Model APIs. To let an agent operate your Baseten workspace and search these docs, see Connect your coding agent. For Cline, Roo Code, LangChain, and other tools, see Integrations. Point Pi, Droid, or OpenCode at Model APIs models such as zai-org/GLM-5.2 and moonshotai/Kimi-K3. Those harnesses call the OpenAI-compatible endpoint with BASETEN_API_KEY. You keep the harness and workflow you already have. Baseten Switch is a local gateway for Claude Code and Codex CLI. It routes those harnesses to Model APIs, charts spend against a native-provider estimate, and can send a request back to Anthropic or OpenAI. The same CLI installs Pi’s direct Baseten provider without starting the gateway. You can run Switch alongside a harness that calls Model APIs directly.

Agent harnesses

Call Model APIs from Pi, Droid, or OpenCode with BASETEN_API_KEY.

Baseten Switch

Connect Claude Code, Codex CLI, or Pi.

Switch CLI

Command reference for baseten-switch.

Agent harnesses

These harnesses call the OpenAI-compatible Model APIs endpoint with BASETEN_API_KEY. Create a personal API key, export it as BASETEN_API_KEY, then configure the harness. This is an inference key, not the management key used to connect your coding agent. Swap in any supported model.

export BASETEN_API_KEY="paste-your-api-key-here"

setx BASETEN_API_KEY "paste-your-api-key-here"

Pi
Droid
OpenCode

Pi has a built-in Baseten provider. Configure it here when you already have BASETEN_API_KEY and want to pin the endpoint yourself. To load the visible Model APIs catalog into Pi, use Baseten Switch instead.After you set BASETEN_API_KEY, pick a path.

Built-in provider
Config file

To run Pi on Model APIs:

pi --provider baseten --model zai-org/GLM-5.2

To store the key in auth.json:

Run /login in Pi.
Select Baseten and store the key in ~/.pi/agent/auth.json.

Auth-file credentials take priority over the environment variable. The key field can be a literal or "$BASETEN_API_KEY". Pi’s agent directory defaults to ~/.pi/agent. Set PI_CODING_AGENT_DIR to override it.

To pin the Model APIs endpoint:

Add the Baseten provider to ~/.pi/agent/models.json. This merges into Pi’s built-in Baseten provider:

~/.pi/agent/models.json

{
  "providers": {
    "baseten": {
      "baseUrl": "https://inference.baseten.co/v1",
      "api": "openai-completions",
      "apiKey": "$BASETEN_API_KEY",
      "models": [
        { "id": "zai-org/GLM-5.2" }
      ]
    }
  }
}

Run Pi against the pinned model:

pi --provider baseten --model zai-org/GLM-5.2

Add more slugs under models from the supported list. To load the catalog into Pi with the Switch CLI, see Baseten Switch.

Droid has no built-in Baseten catalog. After you set BASETEN_API_KEY, add Model APIs as a custom model.To add Model APIs to Droid:

Add a Model APIs slug under customModels in ~/.factory/settings.json. Droid substitutes ${BASETEN_API_KEY} from the environment:

~/.factory/settings.json

{
  "customModels": [
    {
      "model": "zai-org/GLM-5.2",
      "displayName": "GLM 5.2 [Baseten]",
      "baseUrl": "https://inference.baseten.co/v1",
      "apiKey": "${BASETEN_API_KEY}",
      "provider": "generic-chat-completion-api"
    }
  ]
}

Run /model in Droid.
Select the custom model.

Use provider: "generic-chat-completion-api" so Droid sends OpenAI Chat Completions requests.

OpenCode lists Baseten as a provider. After you set BASETEN_API_KEY, pick a path.

Built-in provider
Config file

To connect OpenCode to Baseten:

Start OpenCode.
Run /connect.
Search for Baseten. Paste the API key if OpenCode prompts for it.
Run /models and select a slug.

To store the credential from the CLI:

opencode auth login

OpenCode also loads provider keys from the environment and from a project .env file on startup.

To pin the Model APIs endpoint:

Add a project opencode.json (or ~/.config/opencode/opencode.json) that sets the Model APIs base URL and a model list:

opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "baseten": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Baseten",
      "options": {
        "baseURL": "https://inference.baseten.co/v1",
        "apiKey": "{env:BASETEN_API_KEY}"
      },
      "models": {
        "zai-org/GLM-5.2": {
          "name": "GLM 5.2"
        }
      }
    }
  }
}

Run /models and select a slug.

@ai-sdk/openai-compatible sends Chat Completions requests. Add more slugs under models from the supported list.

Baseten Switch

Baseten Switch is in beta. Its interfaces, configuration, and behavior can change between releases.

Baseten Switch is a local gateway for Claude Code and Codex CLI. It maps model families to Model APIs slugs, charts Baseten spend against a native-provider estimate, and can send a request back to Anthropic or OpenAI. The same CLI installs Pi’s direct Baseten provider without starting the gateway. It requires macOS 13 or newer on Apple Silicon or Intel. For every command, see the Baseten Switch CLI. To install Baseten Switch:

Trust Baseten’s Homebrew tap:
brew trust basetenlabs/baseten

Install the formula:

brew install basetenlabs/baseten/baseten-switch

The fully qualified formula name adds the tap and installs both Baseten Switch and its Baseten CLI dependency. Switch authenticates with the current Baseten CLI profile, and both browser OAuth and API-key profiles work. To allow Baseten Switch on macOS: The beta build uses an ad hoc signature and isn’t notarized yet, so you might need to allow the app the first time you open it:

Try to open Baseten Switch once, so macOS registers the block.
Open System Settings > Privacy & Security and scroll to Security.
Select Open Anyway next to Baseten Switch.

A managed Mac can prohibit this override.

Connect a coding harness

After baseten-switch up --install, use the menu bar app to toggle routing, map models, and view spend. Pi uses a direct provider that Switch installs, without starting the gateway. For every Switch command, see the Baseten Switch CLI.

Claude Code
Codex CLI
Pi

To route Claude Code through Baseten:

Initialize the configuration and sign in when prompted:
baseten-switch setup
Start the gateway and install the menu bar app:
baseten-switch up --install
Point new Claude Code sessions at the gateway:
baseten-switch claude on
Restart Claude Code.
Verify the request path:
baseten-switch doctor --probe

Install Codex CLI first. Switch writes a managed baseten profile and does not modify ~/.codex/config.toml.To route Codex CLI through Baseten:

Initialize the configuration and sign in when prompted:
baseten-switch setup
Start the gateway and install the menu bar app:
baseten-switch up --install
Create the managed profile, approving the prompt if one appears:
baseten-switch codex on

Set the Baseten model that serves the profile:

baseten-switch codex route zai-org/GLM-5.2

Start Codex with the profile:
codex --profile baseten

Don’t use Codex’s -m flag to pick the Baseten model. It overrides the profile and breaks routing.

Pi uses a direct Baseten provider instead of the gateway. To pin the endpoint yourself, see Agent harnesses.To install Pi’s Baseten provider:

Export a personal API key as BASETEN_API_KEY.
Add the provider from the visible Model APIs catalog:
baseten-switch pi install

Run Pi against a Model APIs slug:

pi --provider baseten --model zai-org/GLM-5.2

Next steps

Connect your coding agent

Install the Baseten skill and MCP servers so your agent can operate your Baseten workspace and search these docs.

Integrations

Call Model APIs from Cline, Roo Code, LangChain, and other tools.

Model APIs pricing

See rates for hosted models and compare spend.

Baseten Switch CLI

Commands for routing, models, spend, and health.

Baseten Switch README

Upgrade, uninstall, and configuration fields for Baseten Switch.

Get started

Model APIs

Inference

Training

Development

Deployment

Engines

Model Labs

Organization

Hosting options

Observability

Troubleshooting

Agent harnesses

Baseten Switch

Switch CLI

Agent harnesses

Baseten Switch

Connect a coding harness

Next steps

Connect your coding agent

Integrations

Model APIs pricing

Baseten Switch CLI

Baseten Switch README

Agent harnesses

Baseten Switch

Switch CLI

​Agent harnesses

​Baseten Switch

​Connect a coding harness

​Next steps

Connect your coding agent

Integrations

Model APIs pricing

Baseten Switch CLI

Baseten Switch README

Agent harnesses

Baseten Switch

Connect a coding harness

Next steps