---
title: "Per-subagent model selection"
canonical: "https://canmyagentuse.com/features/subagent-model-selection"
contentKind: "feature"
locale: "en"
description: "Choose or constrain the model used by an individual child agent independently of its parent."
llmSummary: "Per-subagent model selection means a child can use a documented model choice or constraint distinct from its parent; a global conversation model picker is insufficient."
publishedAt: "2026-08-28T00:00:00.000Z"
updatedAt: "2026-08-28T00:00:00.000Z"
verifiedAt: "2026-08-28"
tags: ["runtime","subagents","models","routing"]
---

# Per-subagent model selection

Per-subagent model selection means a child can use a documented model choice or constraint distinct from its parent; a global conversation model picker is insufficient.

- HTML: https://canmyagentuse.com/features/subagent-model-selection
- JSON: https://canmyagentuse.com/api/v1/features/subagent-model-selection.json
- Markdown: https://canmyagentuse.com/features/subagent-model-selection.md

Terminology basis: **Common product term** — https://code.claude.com/docs/en/sub-agents.

## Current support at a glance

Per-subagent model selection: 7 supported, 0 partial, 0 unsupported, 24 unreviewed across 31 cataloged products.

- Reviewed current products: 7 of 31
- Supported: 7
- Partial: 0
- Unsupported: 0
- Unreviewed: 24
- Not applicable: 0

Unknown or unreviewed means insufficient published evidence; it does not mean unsupported.

This row requires a per-child model selection, role default, or enforceable model constraint. A model chosen once for the whole conversation does not establish independent sub-agent choice.

Evidence should record which actors can select the model, allowed models and reasoning modes, fallbacks, plan restrictions, tool and media compatibility, cost attribution, and whether nested agents inherit or override the selection.

## Catalog context

- Category: [runtime](/categories/runtime.md)
- Terminology basis: Common product term
- Aliases: child model choice, subagent model, delegated model routing
- Family: [Subagents](/features/subagents.md)
- Siblings: [Concurrent subagents](/features/subagent-concurrency.md), [Nested subagents](/features/nested-subagents.md), [Subagent context](/features/subagent-context-isolation.md), [Subagent delegation](/features/subagent-delegation.md), [Subagent management](/features/subagent-lifecycle-controls.md), [Subagent MCP access](/features/subagent-mcp-access.md), [Subagent permissions](/features/subagent-approval-boundaries.md), [Subagent results](/features/subagent-result-handoff.md), [Subagent write access](/features/subagent-write-access.md)

## Compatibility assertions

Unknown means insufficient published evidence; it does not mean unsupported.

### ChatGPT (web)

- Harness: [ChatGPT](/harnesses/chatgpt-web.md)
- current: **Unknown**
- preview: **Unknown**

### Claude (web)

- Harness: [Claude](/harnesses/claude-web.md)
- current: **Unknown**
- preview: **Unknown**

### Gemini (web)

- Harness: [Gemini](/harnesses/gemini-web.md)
- current: **Unknown**
- preview: **Unknown**

### Copilot (web)

- Harness: [Copilot](/harnesses/copilot-web.md)
- current: **Unknown**
- preview: **Unknown**

### Grok (web)

- Harness: [Grok](/harnesses/grok-web.md)
- current: **Unknown**
- preview: **Unknown**

### Grok Bot (desktop)

- Harness: [Grok Bot](/harnesses/grok-bot-desktop.md)
- current: **Unknown**

### Perplexity (web)

- Harness: [Perplexity](/harnesses/perplexity-web.md)
- current: **Unknown**
- preview: **Unknown**

### Le Chat (web)

- Harness: [Le Chat](/harnesses/le-chat.md)
- current: **Unknown**
- preview: **Unknown**

### Devin (web)

- Harness: [Devin](/harnesses/devin-web.md)
- current: **Unknown**
- preview: **Unknown**

### Replit Agent (web)

- Harness: [Replit Agent](/harnesses/replit-agent.md)
- current: **Unknown**
- preview: **Unknown**

### ChatGPT (desktop)

- Harness: [ChatGPT](/harnesses/chatgpt-desktop.md)
- current: **Supported**
  - Target: dated-documentation — current ChatGPT desktop documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): local Codex allows explicit child model/reasoning values, agents defaults, or custom-agent file settings; explicit values have highest precedence
  - Evidence: [OpenAI — Subagents in ChatGPT and Codex](https://learn.chatgpt.com/docs/agent-configuration/subagents) — documented; observed 2026-08-28
  - Qualification note 2: Evidence checked 2026-08-28: Local Codex supports explicit spawn values, global subagent model/reasoning defaults, and per-custom-agent model and reasoning settings with documented precedence.
- preview: **Unknown**

### Claude (desktop)

- Harness: [Claude](/harnesses/claude-desktop.md)
- current: **Unknown**
- preview: **Unknown**

### Cursor (desktop)

- Harness: [Cursor](/harnesses/cursor.md)
- current: **Supported**
  - Target: dated-documentation — current Cursor subagent documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (plan): team policy, plan eligibility, or legacy Max Mode requirements may override an explicit child model
  - Evidence: [Cursor — Subagents](https://cursor.com/docs/subagents) — documented; observed 2026-08-28
  - Qualification note 4: Evidence checked 2026-08-28: Cursor subagents accept inherit or an explicit model ID plus per-model parameters such as speed, reasoning effort, and context window.
- preview: **Unknown**

### OpenWork Desktop (desktop)

- Harness: [OpenWork Desktop](/harnesses/openwork-desktop.md)
- current: **Unknown**

### Copilot Chat (desktop)

- Harness: [Copilot Chat](/harnesses/vscode-copilot.md)
- current: **Supported**
  - Target: dated-documentation — current VS Code subagent documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (plan): the requested child model cannot exceed the cost tier of the parent model and must be available to the current Copilot plan
  - Evidence: [Visual Studio Code — Subagents in Visual Studio Code](https://code.visualstudio.com/docs/agents/run/subagents) — documented; observed 2026-08-28
  - Qualification note 6: Evidence checked 2026-08-28: VS Code resolves a child model from an explicit invocation parameter, a custom agent's model or fallback list, or the parent model, in that priority order.
- preview: **Unknown**

### Chrome WebMCP origin trial (desktop)

- Harness: [Chrome WebMCP origin trial](/harnesses/chrome-webmcp-preview.md)
- current: **Unknown**

### Windsurf (desktop)

- Harness: [Windsurf](/harnesses/windsurf.md)
- current: **Unknown**
- preview: **Unknown**

### Zed Agent (desktop)

- Harness: [Zed Agent](/harnesses/zed-agent.md)
- current: **Unknown**
- preview: **Unknown**

### Continue (desktop)

- Harness: [Continue](/harnesses/continue.md)
- current: **Unknown**
- preview: **Unknown**

### Cline (desktop)

- Harness: [Cline](/harnesses/cline.md)
- current: **Unknown**
- preview: **Unknown**

### JetBrains AI (desktop)

- Harness: [JetBrains AI](/harnesses/jetbrains-ai.md)
- current: **Unknown**
- preview: **Unknown**

### Warp (desktop)

- Harness: [Warp](/harnesses/warp.md)
- current: **Unknown**
- preview: **Unknown**

### Claude CLI (cli)

- Harness: [Claude CLI](/harnesses/claude-cli.md)
- current: **Supported**
  - Target: dated-documentation — current Claude Code subagent documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): available model aliases and effort levels depend on the account and current model catalog
  - Evidence: [Anthropic — Create custom subagents](https://code.claude.com/docs/en/sub-agents) — documented; observed 2026-08-28
  - Qualification note 1: Evidence checked 2026-08-28: Claude Code subagent definitions accept a `model` field with aliases or a full model ID and can separately set child reasoning `effort`; omitted values inherit session defaults.
- preview: **Unknown**

### ChatGPT CLI (cli)

- Harness: [ChatGPT CLI](/harnesses/chatgpt-cli.md)
- current: **Unknown**
- preview: **Unknown**

### Codex CLI (cli)

- Harness: [Codex CLI](/harnesses/codex-cli.md)
- current: **Supported**
  - Target: dated-documentation — current Codex CLI documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): explicit child values override agents defaults, which override inherited parent values; custom-agent files can then set model and reasoning effort
  - Evidence: [OpenAI — Subagents in ChatGPT and Codex](https://learn.chatgpt.com/docs/agent-configuration/subagents) — documented; observed 2026-08-28
  - Qualification note 2: Evidence checked 2026-08-28: Local Codex supports explicit spawn values, global subagent model/reasoning defaults, and per-custom-agent model and reasoning settings with documented precedence.
- preview: **Unknown**

### OpenCode (cli)

- Harness: [OpenCode](/harnesses/opencode.md)
- current: **Unknown**
- preview: **Unknown**

### Gemini CLI (cli)

- Harness: [Gemini CLI](/harnesses/gemini-cli.md)
- current: **Supported**
  - Target: dated-documentation — current Gemini CLI documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): agent definitions and overrides can select a child model; /model and --model do not override child models
  - Evidence: [Google — Gemini CLI subagents](https://geminicli.com/docs/core/subagents/) — documented; observed 2026-08-28
  - Qualification note 3: Evidence checked 2026-08-28: Gemini CLI custom subagents accept an independent model setting; the main /model selection does not override subagent models.
- preview: **Unknown**

### Aider (cli)

- Harness: [Aider](/harnesses/aider.md)
- current: **Unknown**
- preview: **Unknown**

### Goose (cli)

- Harness: [Goose](/harnesses/goose.md)
- current: **Unknown**
- preview: **Unknown**

### Copilot CLI (cli)

- Harness: [Copilot CLI](/harnesses/copilot-cli.md)
- current: **Supported**
  - Target: dated-documentation — current GitHub Copilot CLI documentation; observed 2026-08-28
  - Environment: local-default
  - Constraint (runtime): per-call values override subagents settings, agent model/reasoning fields, and finally the parent session
  - Evidence: [GitHub — Copilot CLI command reference](https://docs.github.com/en/copilot/reference/copilot-cli-reference/cli-command-reference) — documented; observed 2026-08-28
  - Qualification note 5: Evidence checked 2026-08-28: GitHub Copilot CLI resolves subagent model and reasoning values from per-call overrides, subagent settings, agent definitions, then the parent session.
- preview: **Unknown**

### Amp (cli)

- Harness: [Amp](/harnesses/amp-cli.md)
- current: **Unknown**
- preview: **Unknown**