coder · mattvollmer · Aug 11, 2026 · Aug 7, 2026 · Aug 7, 2026 · Aug 7, 2026
diff --git a/docs/ai-coder/agents/getting-started.md b/docs/ai-coder/agents/getting-started.md
@@ -1,13 +1,8 @@
 # Getting Started

 This guide walks platform teams and administrators through setting up Coder
 Agents, preparing your deployment, and running your first Coder Agent.
 
-> [!NOTE]
-> Coder Agents is in Beta. APIs, behavior, and configuration may change
-> between releases without notice; pin a release before broad rollout.
-> Use **Coder version 2.33.1 or greater**.
-
 ## Prerequisites
 
 Before you begin, confirm the following:
@@ -167,10 +162,9 @@
 
 ### Plan for change between releases
 
-Coder Agents is under active development. APIs, behavior, and
-configuration may change between releases without notice. Pin a
-specific release before broad rollout and review the release notes
-before upgrading so changes do not surprise developers in production.
+Coder Agents is generally available.
+However, APIs, behavior, and configuration may change between releases.
+As always, you should review [release notes](https://github.com/coder/coder/releases) and the [changelog](https://coder.com/changelog) before upgrading, so changes do not affect production.
 
 ### Use HTTPS for push notifications
 
@@ -196,7 +190,7 @@
 - Any guardrails specific to your environment.
 
 Configure the system prompt from **AI Settings** > **Coder Agents** > **Instructions**
-or via the API at `PUT /api/experimental/chats/config/system-prompt`.
+or via the API at `PUT /api/v2/chats/config/system-prompt`.
 See [Platform Controls](./platform-controls/index.md) for details.
 
 ### Understand the security model
@@ -256,7 +250,7 @@
 **Quick example — create a Coder Agent via the API:**
 
 ```sh
-curl -X POST https://coder.example.com/api/experimental/chats \
+curl -X POST https://coder.example.com/api/v2/chats \
   -H "Coder-Session-Token: $CODER_SESSION_TOKEN" \
   -H "Content-Type: application/json" \
   -d '{
@@ -269,18 +263,14 @@
 Stream updates in real time by connecting to the WebSocket endpoint:
 
 ```txt
-GET /api/experimental/chats/{chat}/stream
+GET /api/v2/chats/{chat}/stream
 ```
 
 For service-to-service automation, use
 [API keys](../../admin/users/sessions-tokens.md)
 rather than developer session tokens. Keep automation credentials
 narrowly scoped.
 
-> [!NOTE]
-> The Chats API is in beta and may change without notice.
-> See [Chats API](../../reference/api/chats.md) for the full endpoint reference.
-
 ### Add workspace context with AGENTS.md
 
 Create an `AGENTS.md` file in the home directory (`~/.coder/AGENTS.md`) or
@@ -304,7 +294,7 @@
 to maintain a pool of ready-to-use workspaces. The agent gets assigned an
 already-running workspace instead of provisioning from scratch.

 ## Providing feedback

 Coder Agents is a collaborative evaluation between your team and Coder.
 Share feedback — workflow observations, feature requests, bugs, performance
@@ -319,7 +309,7 @@
 - **Context** — screenshots, `chat_id` values, or links to the Agents page help
   the team investigate quickly.
 
-Your input directly influences product direction during Beta.
+Your input directly influences product direction.
 
 ## Next steps
 

diff --git a/docs/ai-coder/agents/index.md b/docs/ai-coder/agents/index.md
@@ -321,8 +321,3 @@ Coder Agents is a new approach that differs from
 | Workspace selection | Automatic, based on task description | Manual, user selects template                                  |
 | Sub-agents          | Built-in parallel delegation         | Not supported                                                  |
 | Modern chat UI      | Native chat with diffs, queuing      | Terminal-based interface                                       |
-
-## Product status
-
-Coder Agents is in Beta. The feature is under active development and
-available for evaluation.
diff --git a/docs/ai-coder/agents/models.md b/docs/ai-coder/agents/models.md
@@ -297,9 +297,9 @@
 reject explicit model selection.
 
 > [!NOTE]
-> Both override layers are experimental and may change between releases.
-> The same values are available through the experimental chat
-> configuration API under `/api/experimental/chats/config/`.
+> Both override layers may change between releases.
+> The same values are available through the chat
+> configuration API under `/api/v2/chats/config/`.
 
 ## User API keys (BYOK)
 
@@ -307,7 +307,7 @@
 enabled, developers can supply personal API keys for any enabled AI provider
 from the Agents settings page.

 ### Managing personal API keys

 1. Navigate to the **Agents** page in the Coder dashboard.
 1. Open **Settings** and select the **API Keys** tab.
@@ -324,14 +324,14 @@
 used for deployment-managed provider secrets. The dashboard never displays a
 saved key, only whether one is set.

 ### Removing a personal key

 Click **Remove** on the provider card in the API Keys settings tab. Subsequent
 requests use deployment-managed credentials when they are configured for that
 provider. If no deployment-managed credential is available, add a new personal
 key before you use models from that provider.

 ## Using an LLM proxy

 Organizations that route LLM traffic through a centralized proxy, such as
 LiteLLM or an internal gateway, can point a provider's **Endpoint** or **Base

diff --git a/docs/ai-coder/agents/platform-controls/advisor.md b/docs/ai-coder/agents/platform-controls/advisor.md
@@ -44,5 +44,5 @@ Failed advisor invocations refund the per-turn budget.
 
 The same configuration is available at:
 
-- `GET /api/experimental/chats/config/advisor`
-- `PUT /api/experimental/chats/config/advisor`
+- `GET /api/v2/chats/config/advisor`
+- `PUT /api/v2/chats/config/advisor`
diff --git a/docs/ai-coder/agents/platform-controls/chat-auto-archive.md b/docs/ai-coder/agents/platform-controls/chat-auto-archive.md
@@ -78,8 +78,8 @@ enable auto-archiving.
 
 Use the admin API to read or update the value:
 
-    GET  /api/experimental/chats/config/auto-archive-days
-    PUT  /api/experimental/chats/config/auto-archive-days
+    GET  /api/v2/chats/config/auto-archive-days
+    PUT  /api/v2/chats/config/auto-archive-days
 
 ## Rollout advice
 

diff --git a/docs/ai-coder/agents/platform-controls/chat-debug-logging.md b/docs/ai-coder/agents/platform-controls/chat-debug-logging.md
@@ -12,11 +12,11 @@ Off by default. Three layers control whether it runs for a given chat:
 1. **Runtime admin gate.** With the deployment override unset, the
    *Let users record chat debug logs* toggle decides whether users can opt
    in. Configure it under **AI Settings** > **Lifecycle**, or at
-   `GET/PUT /api/experimental/chats/config/debug-logging`.
+   `GET/PUT /api/v2/chats/config/debug-logging`.
 1. **Per-user toggle.** Users with the admin gate enabled can turn debug
    logging on for their own chats from **Agents** > **Settings** > **General**
    under *Record debug logs for my chats*. The endpoint
-   `PUT /api/experimental/chats/config/user-debug-logging` returns
+   `PUT /api/v2/chats/config/user-debug-logging` returns
    `409 Conflict` if the deployment override is active and `403 Forbidden`
    if the admin has not enabled user opt-in.
 
@@ -49,11 +49,11 @@ the newest runs.
 
 ### API access
 
-The same data is available through the experimental API:
+The same data is available through the API:
 
-- `GET /api/experimental/chats/{chat}/debug/runs` lists the most recent runs
+- `GET /api/v2/chats/{chat}/debug/runs` lists the most recent runs
   for a chat (up to 100, newest first).
-- `GET /api/experimental/chats/{chat}/debug/runs/{debugRun}` returns a single
+- `GET /api/v2/chats/{chat}/debug/runs/{debugRun}` returns a single
   run with all of its steps, including normalized request and response bodies.
 
 Fetch a single run and save it as JSON:
@@ -66,7 +66,7 @@ export RUN_ID="11111111-1111-1111-1111-111111111111"
 
 curl -fsS \
   -H "Coder-Session-Token: $CODER_SESSION_TOKEN" \
-  "$CODER_URL/api/experimental/chats/$CHAT_ID/debug/runs/$RUN_ID" \
+  "$CODER_URL/api/v2/chats/$CHAT_ID/debug/runs/$RUN_ID" \
   | jq . > "coder-agents-debug-run-$RUN_ID.json"
 ```
 
@@ -77,7 +77,7 @@ from above:
 ```sh
 RUN_IDS=$(curl -fsS \
   -H "Coder-Session-Token: $CODER_SESSION_TOKEN" \
-  "$CODER_URL/api/experimental/chats/$CHAT_ID/debug/runs" \
+  "$CODER_URL/api/v2/chats/$CHAT_ID/debug/runs" \
   | jq -r '.[].id') || {
   echo "Failed to list debug runs" >&2
   exit 1
@@ -89,7 +89,7 @@ trap 'rm -f "$RUN_EXPORTS"' EXIT
 for RUN_ID in $RUN_IDS; do
   curl -fsS \
     -H "Coder-Session-Token: $CODER_SESSION_TOKEN" \
-    "$CODER_URL/api/experimental/chats/$CHAT_ID/debug/runs/$RUN_ID" \
+    "$CODER_URL/api/v2/chats/$CHAT_ID/debug/runs/$RUN_ID" \
     >> "$RUN_EXPORTS" || {
       echo "Failed to fetch debug run $RUN_ID" >&2
       exit 1

diff --git a/docs/ai-coder/agents/platform-controls/chat-debug-retention.md b/docs/ai-coder/agents/platform-controls/chat-debug-retention.md
@@ -25,11 +25,11 @@ Navigate to the **Agents** page, open **Settings**, and select the
 Set the value to `0` to disable debug data retention entirely. The maximum value
 is `3650` days.
 
-Use the experimental admin API to read or update the value:
+Use the admin API to read or update the value:
 
 ```txt
-GET  /api/experimental/chats/config/debug-retention-days
-PUT  /api/experimental/chats/config/debug-retention-days
+GET  /api/v2/chats/config/debug-retention-days
+PUT  /api/v2/chats/config/debug-retention-days
 ```
 
 ## Interaction with conversation retention

diff --git a/docs/ai-coder/agents/platform-controls/chat-retention.md b/docs/ai-coder/agents/platform-controls/chat-retention.md
@@ -28,11 +28,11 @@ Navigate to the **Agents** page, open **Settings**, and select the **Behavior**
 tab to configure the conversation retention period. The default is 30 days. Use the toggle to
 disable retention entirely.
 
-Use the experimental admin API to read or update the value:
+Use the admin API to read or update the value:
 
 ```txt
-GET  /api/experimental/chats/config/retention-days
-PUT  /api/experimental/chats/config/retention-days
+GET  /api/v2/chats/config/retention-days
+PUT  /api/v2/chats/config/retention-days
 ```
 
 ## What gets deleted

diff --git a/docs/ai-coder/agents/platform-controls/index.md b/docs/ai-coder/agents/platform-controls/index.md
@@ -63,10 +63,10 @@ plan sections, approval checkpoints, or review workflows.
 
 This setting is available under **AI Settings** > **Coder Agents** > **Instructions**. Developers do not edit it directly.
 
-The same value is exposed over the experimental chat configuration API:
+The same value is exposed over the chat configuration API:
 
-- `GET /api/experimental/chats/config/plan-mode-instructions`
-- `PUT /api/experimental/chats/config/plan-mode-instructions`
+- `GET /api/v2/chats/config/plan-mode-instructions`
+- `PUT /api/v2/chats/config/plan-mode-instructions`
 
 ### Template routing
 

diff --git a/docs/ai-coder/agents/platform-controls/spend-management.md b/docs/ai-coder/agents/platform-controls/spend-management.md
@@ -28,9 +28,9 @@ $1,000,000 per member per period.
 > Configured per-model prices and historical native cost totals are also not migrated to AI Gateway.
 > Before upgrading, record any per-model prices you need from **Admin settings** > **AI** > **Models**.
 > The old cost endpoints default `start_date` to 30 days before the request and `end_date` to the request time, so choose explicit RFC 3339 UTC values that cover all history you need.
-> Fetch `/api/experimental/chats/cost/users?start_date=<start>&end_date=<end>&limit=100&offset=0` and save the response.
+> Fetch `/api/v2/chats/cost/users?start_date=<start>&end_date=<end>&limit=100&offset=0` and save the response.
 > After each page, stop when `offset + users.length >= count`; otherwise, increase `offset` by 100 and fetch the next page.
-> For every `users[].user_id` across those pages, save `/api/experimental/chats/cost/{user_id}/summary?start_date=<start>&end_date=<end>` with the same dates.
+> For every `users[].user_id` across those pages, save `/api/v2/chats/cost/{user_id}/summary?start_date=<start>&end_date=<end>` with the same dates.
 > Each summary contains the user's totals plus `by_model` and `by_chat` breakdowns.
 > After upgrading, the native **Spend** page, per-model pricing fields, and aggregate cost endpoints are unavailable.
 > Historical `chat_messages.total_cost_micros` values remain in the database temporarily for rolling upgrade compatibility, but AI Gateway reports do not include or reconstruct them.

diff --git a/docs/ai-coder/agents/platform-controls/virtual-desktop.md b/docs/ai-coder/agents/platform-controls/virtual-desktop.md
@@ -39,5 +39,5 @@ provider is set.
 
 The same configuration is available at:
 
-- `GET /api/experimental/chats/config/computer-use-provider`
-- `PUT /api/experimental/chats/config/computer-use-provider`
+- `GET /api/v2/chats/config/computer-use-provider`
+- `PUT /api/v2/chats/config/computer-use-provider`