Pi - Replicas Docs

Replicas supports Pi as an SDK-backed coding agent. Pi runs inside the workspace VM, uses OpenCode Go, Aster, or OpenRouter for inference, and persists its session and tool history across turns.

Setup

Pi and Opencode share OpenCode Go and Aster credentials. DeepSeek Harness, Pi, and Opencode share OpenRouter credentials. Authentication priority is OpenCode Go, Aster, then OpenRouter.

Create an OpenCode Go API key in OpenCode Zen, an Aster key in the Aster console, or an OpenRouter key on the OpenRouter keys page.
Paste it under Pi → OpenCode Go, Pi → Aster API Key, or Pi → OpenRouter API Key in Organization → Coding Agents. The credentials are shared with the other supported harnesses.
Set organization credentials for the team, or add a personal key under Personal to override the organization default.

See Credentials for credential scope and fallback behavior. The workspace info panel shows Pi’s configured provider alongside its authentication method, such as OpenCode Go · API Key.

Models

OpenCode Go starts with the same four default models as Opencode. Organization admins can add or remove models under Pi → OpenCode Go models in Coding Agents settings; changes apply to both harnesses. With Aster connected, Pi provides kimi-k3, glm-5.2, gpt-oss-120b-fast, and gpt-oss-120b. With OpenRouter, Pi offers the models enabled under Pi → OpenRouter models in Coding Agents settings. Organization admins pick these from the connected OpenRouter account, and the selection is shared with DeepSeek Harness and Opencode. Until it is changed, Pi provides:

Model ID	Label	Notes
`z-ai/glm-5.3`	GLM 5.3	Default
`deepseek/deepseek-v4-pro-0813`	DeepSeek V4 Pro	Flagship V4 coding model
`moonshotai/kimi-k3`	Kimi K3	Multimodal coding model
`google/gemini-3.8-flash`	Gemini 3.8 Flash	Fast multimodal Google model

Enable additional models under OpenRouter models in Coding Agents settings. Saved organization selections take precedence over these defaults. Choose an organization default under Defaults, a personal default in account preferences, or a model for the active chat from the workspace composer.

Using Pi in Workspaces

Choose Pi from the composer’s harness/model picker when creating a chat. Pi can:

Read, write, and edit repository files
Run shell commands with Replicas command protection
Accept image attachments
Persist sessions and tool history across workspace sleep
Use MCP servers configured for the organization
Discover provisioned and repository skills through Pi’s global .agents/skills directory
Run skills explicitly with /skill:<name>

Pi does not currently provide native plan-mode, fast-mode, or goal-mode support. Ask Pi for a read-only implementation plan in the prompt when you want planning without changes.

Provider errors

When inference fails upstream, the chat reports the provider, model, HTTP status, and any response detail the provider returned. Transient server errors add a retry hint; Pi already retries them automatically before the turn fails. OpenCode Go’s RegionError and DataPolicyError require separate opt-ins for China-hosted models and model-training data sharing. Check the workspace linked in the error; it must match the workspace that issued your connected API key. See OpenCode Go.

Programmatic Use

Select Pi anywhere Replicas accepts a coding agent:

Surface	How to choose Pi
CLI	`-a pi` on `replicas create` and `replicas send`
API	`"coding_agent": "pi"` on create and message requests
MCP	`"coding_agent": "pi"` on `create_replica` and `send_replica_message`
Automations	Set Coding agent to Pi in the automation editor
Defaults	Select Pi as the organization or personal default coding agent

replicas create fix-tests \
  -e backend \
  -a pi \
  -m "Inspect the repository and fix the failing tests"

curl -X POST "https://api.replicas.dev/v1/replica" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "fix-tests",
    "environment_id": "ENVIRONMENT_UUID",
    "message": "Inspect the repository and fix the failing tests",
    "coding_agent": "pi",
    "model": "z-ai/glm-5.3"
  }'

Get started

Workspaces

Coding agents

Integrations

Build and automate

Apps

Admin

Updates

Pi

Setup

Models

Using Pi in Workspaces

Provider errors

Programmatic Use

​Setup

​Models

​Using Pi in Workspaces

​Provider errors

​Programmatic Use

Setup

Models

Using Pi in Workspaces

Provider errors

Programmatic Use