From bcead282e224952792e40b3a36f3e8a8fde94094 Mon Sep 17 00:00:00 2001
From: yuneng-jiang <yuneng@berri.ai>
Date: Tue, 18 Aug 2026 20:26:17 -0700
Subject: [PATCH] test: move the remaining live groq call sites off the retired
 llama models (#37426)

The earlier sweep only caught the conformance suite in tests/llm_translation.
Groq retired llama-3.1-8b-instant alongside llama-3.3-70b-versatile, and four
tests under tests/local_testing still call them for real, so litellm_router_testing
and both local_testing shards 404 with model_not_found.

Only the sites that leave the process move. The chunk fixtures in
test_stream_chunk_builder, and the cost and routing tests that never open a
socket, keep the old ids because the string is data there, not a request.
---
 tests/local_testing/test_model_alias_map.py         | 4 ++--
 tests/local_testing/test_router.py                  | 2 +-
 tests/local_testing/test_router_batch_completion.py | 6 +++---
 tests/local_testing/test_stream_chunk_builder.py    | 2 +-
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/tests/local_testing/test_model_alias_map.py b/tests/local_testing/test_model_alias_map.py
index 14c1de2f6a7..9ef0448e7c6 100644
--- a/tests/local_testing/test_model_alias_map.py
+++ b/tests/local_testing/test_model_alias_map.py
@@ -15,7 +15,7 @@ from litellm import completion, embedding
 
 litellm.set_verbose = True
 
-model_alias_map = {"good-model": "groq/llama-3.1-8b-instant"}
+model_alias_map = {"good-model": "groq/openai/gpt-oss-120b"}
 
 
 def test_model_alias_map(caplog):
@@ -34,7 +34,7 @@ def test_model_alias_map(caplog):
             if rec.levelname == "ERROR" and rec.name.startswith("LiteLLM"):
                 pytest.fail(f"Unexpected litellm ERROR log: {rec.getMessage()}")
 
-        assert "llama-3.1-8b-instant" in response.model
+        assert "gpt-oss-120b" in response.model
     except litellm.ServiceUnavailableError:
         pass
     except Exception as e:
diff --git a/tests/local_testing/test_router.py b/tests/local_testing/test_router.py
index af1a052e86d..7bc29517f8c 100644
--- a/tests/local_testing/test_router.py
+++ b/tests/local_testing/test_router.py
@@ -120,7 +120,7 @@ async def test_router_provider_wildcard_routing():
     print("response 2 = ", response2)
 
     response3 = await router.acompletion(
-        model="groq/llama-3.1-8b-instant",
+        model="groq/openai/gpt-oss-120b",
         messages=[{"role": "user", "content": "hello"}],
     )
 
diff --git a/tests/local_testing/test_router_batch_completion.py b/tests/local_testing/test_router_batch_completion.py
index f7a1b41ca29..bb9e1851c61 100644
--- a/tests/local_testing/test_router_batch_completion.py
+++ b/tests/local_testing/test_router_batch_completion.py
@@ -44,7 +44,7 @@ async def test_batch_completion_multiple_models(mode):
             {
                 "model_name": "groq-llama",
                 "litellm_params": {
-                    "model": "groq/llama-3.1-8b-instant",
+                    "model": "groq/openai/gpt-oss-120b",
                 },
             },
         ]
@@ -143,7 +143,7 @@ async def test_batch_completion_fastest_response_streaming():
             {
                 "model_name": "groq-llama",
                 "litellm_params": {
-                    "model": "groq/llama-3.1-8b-instant",
+                    "model": "groq/openai/gpt-oss-120b",
                 },
             },
         ]
@@ -179,7 +179,7 @@ async def test_batch_completion_multiple_models_multiple_messages():
             {
                 "model_name": "groq-llama",
                 "litellm_params": {
-                    "model": "groq/llama-3.1-8b-instant",
+                    "model": "groq/openai/gpt-oss-120b",
                 },
             },
         ]
diff --git a/tests/local_testing/test_stream_chunk_builder.py b/tests/local_testing/test_stream_chunk_builder.py
index 38e04b93f18..664fd936205 100644
--- a/tests/local_testing/test_stream_chunk_builder.py
+++ b/tests/local_testing/test_stream_chunk_builder.py
@@ -871,7 +871,7 @@ def load_env():
     }
     LLAMA3_3 = {
         "messages": messages,
-        "model": "groq/llama-3.3-70b-versatile",
+        "model": "groq/openai/gpt-oss-120b",
         "api_base": "https://api.groq.com/openai/v1",
         "temperature": 0.0,
         "tools": tools,