docs: add Tchavi to AI Endpoints

content/docs/configuration/librechat_yaml/ai_endpoints/index.mdx

@@ -66,6 +66,7 @@ OPENAI_API_KEY=user_provided
   <Cards.Card title="NEAR AI Cloud" href="/docs/configuration/librechat_yaml/ai_endpoints/nearai" arrow />
   <Cards.Card title="NeurochainAI" href="/docs/configuration/librechat_yaml/ai_endpoints/neurochain" arrow />
   <Cards.Card title="Portkey AI" href="/docs/configuration/librechat_yaml/ai_endpoints/portkey" arrow />
+  <Cards.Card title="Tchavi" href="/docs/configuration/librechat_yaml/ai_endpoints/tchavi" arrow />
   <Cards.Card title="TrueFoundry AI Gateway" href="/docs/configuration/librechat_yaml/ai_endpoints/truefoundry" arrow />
   <Cards.Card title="vLLM" href="/docs/configuration/librechat_yaml/ai_endpoints/vllm" arrow />
   <Cards.Card title="Vultr Cloud Inference" href="/docs/configuration/librechat_yaml/ai_endpoints/vultrcloudinference" arrow />

content/docs/configuration/librechat_yaml/ai_endpoints/meta.json

@@ -25,6 +25,7 @@
     "perplexity",
     "portkey",
     "shuttleai",
+    "tchavi",
     "togetherai",
     "truefoundry",
     "vllm",

content/docs/configuration/librechat_yaml/ai_endpoints/tchavi.mdx

@@ -0,0 +1,38 @@
+---
+title: Tchavi
+description: Configure Tchavi as a custom endpoint in LibreChat.
+---
+
+Tchavi serves chat, image, video, audio and embedding models through an OpenAI-compatible API that you can add to LibreChat as a custom endpoint. Accounts run on prepaid credits, topped up by mobile money in twelve African countries.
+
+## Get an API key
+
+Follow the [quickstart](https://tchavi.com/en/docs/quickstart?utm_source=librechat&utm_medium=listing&utm_campaign=integrations-2026-11) to create an account and a key in the dashboard, then add the key to your `.env` file:
+
+```bash filename=".env"
+TCHAVI_API_KEY=your-api-key
+```
+
+## Configuration
+
+Add the endpoint to the `custom` list under `endpoints` in your `librechat.yaml`. If your file already has an `endpoints.custom` list, paste only the `- name:` entry into it, keeping the same indentation:
+
+```yaml filename="librechat.yaml"
+endpoints:
+  custom:
+    - name: "Tchavi"
+      apiKey: "${TCHAVI_API_KEY}"
+      baseURL: "https://tchavi.com/api/v1"
+      models:
+        default: ["deepseek-v4-flash", "claude-sonnet-5-5"]
+        fetch: true
+      titleConvo: true
+      titleModel: "deepseek-v4-flash"
+      modelDisplayLabel: "Tchavi"
+```
+
+## Notes
+
+- `GET /v1/models` is not billed. It returns every model id with its pricing and capabilities, so `fetch: true` lists the whole catalogue. Trim `default` to the models you use.
+- Usage is billed from a prepaid credit balance. An account that has not topped up is limited to the Budget group of models and a small daily request limit; `deepseek-v4-flash` is in that group.
+- Reasoning models spend part of `max_tokens` on reasoning tokens before the visible answer, so leave them room.