diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.json b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.json
index c46fe3dfd..51c957dd3 100644
--- a/content/docs/configuration/librechat_yaml/ai_endpoints/meta.json
+++ b/content/docs/configuration/librechat_yaml/ai_endpoints/meta.json
@@ -26,6 +26,7 @@
     "portkey",
     "shuttleai",
     "togetherai",
+    "topxai",
     "truefoundry",
     "vllm",
     "vultrcloudinference",
diff --git a/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx
new file mode 100644
index 000000000..6aefc4b51
--- /dev/null
+++ b/content/docs/configuration/librechat_yaml/ai_endpoints/topxai.mdx
@@ -0,0 +1,47 @@
+---
+title: TopxAI
+icon: Plug
+description: Configure TopxAI as a custom endpoint in LibreChat.
+---
+
+TopxAI serves Claude, GPT, Grok, GLM, Kimi, DeepSeek and Jev models through one OpenAI-compatible endpoint with one prepaid key. Every model has a fixed USD price per route, listed at [ai.topxea.com/pricing](https://ai.topxea.com/pricing).
+
+## Get an API key
+
+Sign in at [ai.topxea.com](https://ai.topxea.com/) and create a key on the **Keys** page; pick **Auto route** so one key covers every model. Add it to your `.env` file:
+
+```bash filename=".env"
+TOPXAI_API_KEY=sk-your-key-here
+```
+
+## Configuration
+
+Add the endpoint under `endpoints.custom` in your `librechat.yaml`:
+
+```yaml filename="librechat.yaml"
+    - name: "TopxAI"
+      apiKey: "${TOPXAI_API_KEY}"
+      baseURL: "https://ai.topxea.com/v1"
+      models:
+        default: ["claude-sonnet-5-5", "gpt-6.1-sol", "grok-4.7"]
+        fetch: true
+      titleConvo: true
+      titleModel: "gpt-6.1-sol"
+      modelDisplayLabel: "TopxAI"
+```
+
+To pin a fixed model list instead of fetching the catalog, set `fetch: false` and list the models yourself:
+
+```yaml filename="librechat.yaml"
+      models:
+        default: ["claude-sonnet-5-5", "claude-opus-5-5", "gpt-6-astra", "gpt-6.1-sol", "grok-4.7", "kimi-k3", "deepseek-v4-pro"]
+        fetch: false
+```
+
+To let each user supply their own key through the LibreChat UI instead of reading one from `.env`, set `apiKey: "user_provided"`.
+
+## Notes
+
+- Model ids are the plain names from the [price list](https://ai.topxea.com/api/pricing) (`claude-sonnet-5-5`, `gpt-6.1-sol`, `grok-4.7` and so on), with no provider prefix.
+- A key can be pinned to one route (for example `claude-shared`) or set to Auto route; a model the key's route does not sell answers `403` with "Model is not available on this API key route". See [routes and prices](https://ai.topxea.com/docs/shared-pool-official-line-and-auto-route).
+- The [API reference](https://ai.topxea.com/docs/api-reference) lists the endpoints; the Claude models are also served on an Anthropic Messages endpoint, which LibreChat's custom endpoints do not use.