diff --git a/api-reference/chat/workflow.mdx b/api-reference/chat/workflow.mdx
index ed1c1c09..6e6b7804 100644
--- a/api-reference/chat/workflow.mdx
+++ b/api-reference/chat/workflow.mdx
@@ -1,4 +1,4 @@
 ---
-title: 'Stream Chat (Workflow + Sandbox)'
-openapi: 'POST /api/chat/workflow'
+title: 'Stream Chat'
+openapi: 'POST /api/chat'
 ---
diff --git a/api-reference/openapi/research.json b/api-reference/openapi/research.json
index 277003b7..397d0999 100644
--- a/api-reference/openapi/research.json
+++ b/api-reference/openapi/research.json
@@ -753,7 +753,7 @@
         }
       }
     },
-    "/api/chat/workflow": {
+    "/api/chat": {
       "post": {
         "summary": "Stream sandbox-driven chat (Vercel Workflow)",
         "description": "Streams an agent loop running as a durable [Vercel Workflow](https://vercel.com/docs/workflow) against the session's sandbox. The agent uses sandbox-only tools (`bash`, `read`, `write`, `grep`, `glob`, `todo`, `task`, `ask_user_question`, `skill`, `fetch`) — no MCP or Composio. Requires a sandbox provisioned via [POST /api/sandbox](/api-reference/sandbox/create).",
diff --git a/credits.mdx b/credits.mdx
index 3a1409e7..c1ae93c7 100644
--- a/credits.mdx
+++ b/credits.mdx
@@ -13,7 +13,7 @@ Some Recoup endpoints are billed in **credits** — primarily endpoints that hit
 |--------|---------|-------|
 | **Research** ([`/api/research/*`](/api-reference/research/search)) | Yes | Each successful call deducts credits. Costs vary by endpoint and parameters (e.g. [`enrich`](/api-reference/research/enrich) charges by processor tier; [`extract`](/api-reference/research/extract) charges by URL count). |
 | **Content generation** ([`/api/image/generate`](/api-reference/image/generation)) | Yes | Image generation is priced per call. |
-| **AI Chat — streaming** ([`POST /api/chat/workflow`](/api-reference/chat/workflow)) | Yes | Variable cost based on model token usage, with a per-request minimum. |
+| **AI Chat — streaming** ([`POST /api/chat`](/api-reference/chat/workflow)) | Yes | Variable cost based on model token usage, with a per-request minimum. |
 | **Everything else** | Free at the API layer | [Artist CRUD](/api-reference/artists/list), [sandboxes](/api-reference/sandboxes/list), [sessions](/api-reference/sessions/get), [scheduled tasks](/api-reference/tasks/get), [social integrations](/api-reference/social/scrape), [account/org management](/api-reference/accounts/id), [agent signup](/api-reference/agents/signup), [Spotify proxies](/api-reference/spotify/search), etc. Subscription gating may still apply. |
 
 Failed calls (4xx / 5xx) do **not** deduct credits. Deduction happens only after the upstream call succeeds.
@@ -175,7 +175,7 @@ Current as of this revision of the page. The authoritative source is the per-end
 
 | Endpoint | Cost |
 |----------|------|
-| [`POST /api/chat/workflow`](/api-reference/chat/workflow) (streaming) | ≥1 credit per turn — variable based on model token usage |
+| [`POST /api/chat`](/api-reference/chat/workflow) (streaming) | ≥1 credit per turn — variable based on model token usage |
 | [`GET /api/research/*`](/api-reference/research/search) (artist & non-artist research) | 5 credits per call |
 | [`POST /api/research/people`](/api-reference/research/people) | 5 credits per call |
 | [`POST /api/research/web`](/api-reference/research/web) | 5 credits per call |