diff --git a/docs/gateway/cli-backends.md b/docs/gateway/cli-backends.md
index 3c733680d..4db4556ce 100644
--- a/docs/gateway/cli-backends.md
+++ b/docs/gateway/cli-backends.md
@@ -35,7 +35,7 @@ moltbot agent --message "hi" --model codex-cli/gpt-5.2-codex
 GitHub Copilot CLI works the same way (requires GitHub CLI auth):
 
 ```bash
-moltbot agent --message "hi" --model copilot-cli/gpt-4o
+moltbot agent --message "hi" --model copilot-cli/gpt-4.1
 ```
 
 If your gateway runs under launchd/systemd and PATH is minimal, add just the
diff --git a/docs/providers/github-copilot-cli.md b/docs/providers/github-copilot-cli.md
index e5f30c6e6..c16b5ed42 100644
--- a/docs/providers/github-copilot-cli.md
+++ b/docs/providers/github-copilot-cli.md
@@ -12,9 +12,12 @@ GitHub Copilot CLI (`copilot`) is GitHub's terminal-based AI assistant. Moltbot
 
 ## Prerequisites
 
-- **GitHub Copilot subscription** (Individual, Business, or Enterprise)
+- **GitHub account** (free tier works for `gpt-4.1`)
 - **GitHub CLI** (`gh`) authenticated with your GitHub account
 
+Note: `gpt-4.1` is available on the free GitHub tier. Other models like `gpt-4o`, `claude-sonnet-4-5`,
+and `claude-opus-4-5` require a paid GitHub Copilot subscription.
+
 ## Installation
 
 Install the Copilot CLI via npm:
@@ -48,7 +51,7 @@ gh copilot --help
 Use Copilot CLI directly with Moltbot:
 
 ```bash
-moltbot agent --message "hi" --model copilot-cli/gpt-4o
+moltbot agent --message "hi" --model copilot-cli/gpt-4.1
 ```
 
 ## Configuration
@@ -80,14 +83,14 @@ Add `copilot-cli` to your fallback list so it only runs when primary models fail
   agents: {
     defaults: {
       model: {
-        primary: "github-copilot/gpt-4o",
+        primary: "github-copilot/gpt-4.1",
         fallbacks: [
-          "copilot-cli/gpt-4o"
+          "copilot-cli/gpt-4.1"
         ]
       },
       models: {
-        "github-copilot/gpt-4o": { alias: "Copilot" },
-        "copilot-cli/gpt-4o": {}
+        "github-copilot/gpt-4.1": { alias: "Copilot" },
+        "copilot-cli/gpt-4.1": {}
       }
     }
   }
@@ -96,11 +99,14 @@ Add `copilot-cli` to your fallback list so it only runs when primary models fail
 
 ## Supported models
 
-Copilot CLI supports these models (availability depends on your plan):
+Copilot CLI supports these models (availability depends on your GitHub plan):
 
-- `gpt-4o`
-- `gpt-4.1`
+**Free tier (GitHub Free):**
+- `gpt-4.1` ← recommended default
 - `gpt-4.1-mini`
+
+**Paid tier (GitHub Copilot subscription):**
+- `gpt-4o`
 - `gpt-4-turbo`
 - `claude-sonnet-4-5`
 - `claude-opus-4-5`
@@ -108,8 +114,9 @@ Copilot CLI supports these models (availability depends on your plan):
 Example model refs:
 
 ```
-copilot-cli/gpt-4o
 copilot-cli/gpt-4.1
+copilot-cli/gpt-4.1-mini
+copilot-cli/gpt-4o
 copilot-cli/claude-sonnet-4-5
 ```
 
diff --git a/docs/providers/github-copilot.md b/docs/providers/github-copilot.md
index c7b68d1bd..c5e461f60 100644
--- a/docs/providers/github-copilot.md
+++ b/docs/providers/github-copilot.md
@@ -50,21 +50,21 @@ moltbot models auth login-github-copilot --yes
 ## Set a default model
 
 ```bash
-moltbot models set github-copilot/gpt-4o
+moltbot models set github-copilot/gpt-4.1
 ```
 
 ### Config snippet
 
 ```json5
 {
-  agents: { defaults: { model: { primary: "github-copilot/gpt-4o" } } }
+  agents: { defaults: { model: { primary: "github-copilot/gpt-4.1" } } }
 }
 ```
 
 ## Notes
 
 - Requires an interactive TTY; run it directly in a terminal.
-- Copilot model availability depends on your plan; if a model is rejected, try
-  another ID (for example `github-copilot/gpt-4.1`).
+- `gpt-4.1` is available on the free GitHub tier. Other models like `gpt-4o` and
+  Claude models require a paid GitHub Copilot subscription.
 - The login stores a GitHub token in the auth profile store and exchanges it for a
   Copilot API token when Moltbot runs.
diff --git a/docs/testing.md b/docs/testing.md
index ce81be194..fa01cb4a6 100644
--- a/docs/testing.md
+++ b/docs/testing.md
@@ -188,7 +188,7 @@ CLAWDBOT_LIVE_SETUP_TOKEN=1 CLAWDBOT_LIVE_SETUP_TOKEN_PROFILE=anthropic:setup-to
 - Overrides (optional):
   - `CLAWDBOT_LIVE_CLI_BACKEND_MODEL="claude-cli/claude-opus-4-5"`
   - `CLAWDBOT_LIVE_CLI_BACKEND_MODEL="codex-cli/gpt-5.2-codex"`
-  - `CLAWDBOT_LIVE_CLI_BACKEND_MODEL="copilot-cli/gpt-4o"`
+  - `CLAWDBOT_LIVE_CLI_BACKEND_MODEL="copilot-cli/gpt-4.1"`
   - `CLAWDBOT_LIVE_CLI_BACKEND_COMMAND="/full/path/to/claude"`
   - `CLAWDBOT_LIVE_CLI_BACKEND_ARGS='["-p","--output-format","json","--permission-mode","bypassPermissions"]'`
   - `CLAWDBOT_LIVE_CLI_BACKEND_CLEAR_ENV='["ANTHROPIC_API_KEY","ANTHROPIC_API_KEY_OLD"]'`
@@ -210,11 +210,12 @@ CLAWDBOT_LIVE_CLI_BACKEND=1 \
 
 ```bash
 CLAWDBOT_LIVE_CLI_BACKEND=1 \
-  CLAWDBOT_LIVE_CLI_BACKEND_MODEL="copilot-cli/gpt-4o" \
+  CLAWDBOT_LIVE_CLI_BACKEND_MODEL="copilot-cli/gpt-4.1" \
   pnpm test:live src/gateway/gateway-cli-backend.live.test.ts
 ```
 
 Note: Copilot CLI requires GitHub CLI auth (`gh auth status`). Output is text-only (no JSON).
+`gpt-4.1` is available on GitHub Free tier; other models require a paid subscription.
 
 ### Recommended live recipes