diff --git a/litellm/__init__.py b/litellm/__init__.py
index ff901ede512..ca64627ae89 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -724,6 +724,7 @@ transcribe_models: Set = set()
 gigachat_models: Set = set()
 llamagate_models: Set = set()
 coralbricks_models: Set[str] = set()
+aiand_models: Set[str] = set()
 reducto_models: Set = set()
 bedrock_mantle_models: Set = set()
 
@@ -1017,6 +1018,8 @@ def _populate_provider_model_sets(model_cost_map: Mapping[str, Mapping[str, obje
             llamagate_models.add(key)
         elif value.get("litellm_provider") == "coralbricks":
             coralbricks_models.add(key)
+        elif value.get("litellm_provider") == "aiand":
+            aiand_models.add(key)
         elif value.get("litellm_provider") == "reducto":
             reducto_models.add(key)
         elif value.get("litellm_provider") == "bedrock_mantle":
@@ -1152,6 +1155,7 @@ model_list = list(
     | reducto_models
     | bedrock_mantle_models
     | coralbricks_models
+    | aiand_models
     | set(clarifai_models)
 )
 
@@ -1272,6 +1276,7 @@ def _build_models_by_provider() -> dict:
         "gigachat": gigachat_models,
         "llamagate": llamagate_models,
         "coralbricks": coralbricks_models,
+        "aiand": aiand_models,
         "reducto": reducto_models,
         "bedrock_mantle": bedrock_mantle_models,
     }
diff --git a/litellm/provider_endpoints_support_backup.json b/litellm/provider_endpoints_support_backup.json
index 9ff477f168e..aec94d01fbc 100644
--- a/litellm/provider_endpoints_support_backup.json
+++ b/litellm/provider_endpoints_support_backup.json
@@ -125,7 +125,7 @@
       "url": "https://docs.aiand.com/api/chat-completions/",
       "endpoints": {
         "chat_completions": true,
-        "messages": false,
+        "messages": true,
         "responses": true,
         "embeddings": false,
         "image_generations": false,
diff --git a/provider_endpoints_support.json b/provider_endpoints_support.json
index 93223876d28..8d65f17d8cd 100644
--- a/provider_endpoints_support.json
+++ b/provider_endpoints_support.json
@@ -126,7 +126,7 @@
       "url": "https://docs.aiand.com/api/chat-completions/",
       "endpoints": {
         "chat_completions": true,
-        "messages": false,
+        "messages": true,
         "responses": true,
         "embeddings": false,
         "image_generations": false,
diff --git a/tests/unit/llms/openai_like/test_aiand_provider.py b/tests/unit/llms/openai_like/test_aiand_provider.py
index aaff5a7d96a..51586546ca9 100644
--- a/tests/unit/llms/openai_like/test_aiand_provider.py
+++ b/tests/unit/llms/openai_like/test_aiand_provider.py
@@ -1,4 +1,5 @@
 import json
+from typing import Final
 
 import httpx
 import pytest
@@ -7,6 +8,7 @@ import respx
 import litellm
 from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
 from litellm.llms.openai_like.json_loader import JSONProviderRegistry
+from litellm.proxy.auth.model_checks import get_known_models_from_wildcard
 from litellm.utils import ProviderConfigManager
 
 AIAND_API_BASE = "https://api.aiand.com/v1"
@@ -80,3 +82,27 @@ def test_aiand_responses_provider():
     assert config is not None
     assert config.custom_llm_provider == "aiand"
     assert config.get_complete_url(api_base=None, litellm_params={}) == f"{AIAND_API_BASE}/responses"
+
+
+def _aiand_catalog() -> frozenset[str]:
+    return frozenset(name for name, info in litellm.model_cost.items() if info.get("litellm_provider") == "aiand")
+
+
+def test_aiand_wildcard_lists_its_priced_models():
+    catalog: Final = _aiand_catalog()
+
+    assert catalog
+    assert frozenset(get_known_models_from_wildcard("aiand/*")) == catalog
+
+
+def test_aiand_calls_are_billed_from_their_cost_rows():
+    catalog: Final = _aiand_catalog()
+    assert catalog
+
+    for model in sorted(catalog):
+        row: Final = litellm.model_cost[model]
+        prompt_cost, completion_cost = litellm.cost_per_token(model=model, prompt_tokens=1000, completion_tokens=500)
+
+        assert prompt_cost == pytest.approx(1000 * row["input_cost_per_token"])
+        assert completion_cost == pytest.approx(500 * row["output_cost_per_token"])
+        assert prompt_cost > 0 and completion_cost > 0