diff --git a/api_endpoints.json b/api_endpoints.json
new file mode 100644
index 000000000..026ba886f
--- /dev/null
+++ b/api_endpoints.json
@@ -0,0 +1,15 @@
+{
+  "ova-debate": {
+    "model_name": "ova-debate",
+    "api_type": "openai",
+    "api_base": "https://ovamind-production.up.railway.app/api/v1",
+    "api_key": "sk_ova_arena_lmarena2026",
+    "anony_only": false,
+    "recommended_config": {
+      "temperature": 0.3,
+      "top_p": 1.0
+    },
+    "text-arena": true,
+    "vision-arena": false
+  }
+}
diff --git a/fastchat/model/model_registry.py b/fastchat/model/model_registry.py
index 2eed9649e..86dca5c3d 100644
--- a/fastchat/model/model_registry.py
+++ b/fastchat/model/model_registry.py
@@ -1000,3 +1000,14 @@ def get_model_info(name: str) -> ModelInfo:
     "https://huggingface.co/cllm",
     "consistency-llm is a new generation of parallel decoder LLMs with fast generation speed.",
 )
+
+# ── OVA (Multi-Model Debate) ─────────────────────────────────────────────────
+register_model_info(
+    ["ova-debate", "ova-arena"],
+    "OVA (Multi-Model Debate)",
+    "https://ovamind.ai",
+    "OVA is a meta-reasoning system that runs structured multi-agent debate "
+    "across Claude, GPT, Grok, Gemini, and Perplexity before synthesizing a "
+    "final answer. Confidence-adaptive: 3 rounds for standard queries, up to 9 "
+    "rounds with axiom decomposition and frame-breaking for hard problems.",
+)