test: point the live together_ai suites at a model together still serves (#37746)

Every live together_ai call in CI has answered 503 Service unavailable since
2026-08-20, across two runs 2.5 hours apart, while Together's status page
reported no incident in either window. These are real calls, not replayed
cassettes: the VCR layer runs filter_non_2xx_response, so a 503 is never
written to a cassette and cannot be replayed back.

Qwen/Qwen2.5-7B-Instruct-Turbo does not appear anywhere on Together's monitored
component list, whose Qwen entries are all Qwen3.x, so a model-level outage
there would never surface as an incident. The same 503 already forced
test_basic_rerank_together_ai to be skipped on a different together_ai model,
so per-model 503s are an established failure mode here rather than a platform
outage.

openai/gpt-oss-20b is the cheapest together_ai entry that carries real pricing
and the capabilities these suites exercise, at $0.05/$0.20 per 1M tokens with
function calling, response schema and tool choice. Together monitors it as a
served component. The retired model also carries null pricing in the cost map,
which is its own liability now that unpriced models are blocked.

test_multiple_deployments.py keeps the old id: it is a router fallback list
that is green today, and busting its cassette to prove a point would trade a
passing test for a live call this change cannot vouch for.

Author: yuneng-berri

tests/llm_translation/test_together_ai.py

@@ -20,7 +20,7 @@
 class TestTogetherAI(BaseLLMChatTest):
     def get_base_completion_call_args(self) -> dict:
         litellm.set_verbose = True
-        return {"model": "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo"}
+        return {"model": "together_ai/openai/gpt-oss-20b"}
 
     def test_tool_call_no_arguments(self, tool_call_no_arguments):
         """Test that tool calls with no arguments is translated correctly. Relevant issue: https://github.com/BerriAI/litellm/issues/6833"""

tests/local_testing/test_completion.py

@@ -67,7 +67,7 @@ def test_completion_custom_provider_model_name():
     try:
         litellm.cache = None
         response = completion(
-            model="together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo",
+            model="together_ai/openai/gpt-oss-20b",
             messages=messages,
             logger_fn=logger_fn,
         )
@@ -2817,7 +2817,7 @@ def test_customprompt_together_ai():
         print(litellm.success_callback)
         print(litellm._async_success_callback)
         response = completion(
-            model="together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo",
+            model="together_ai/openai/gpt-oss-20b",
             messages=messages,
             roles={
                 "system": {
@@ -3657,7 +3657,7 @@ def test_completion_together_ai_stream():
     messages = [{"content": user_message, "role": "user"}]
     try:
         response = completion(
-            model="together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo",
+            model="together_ai/openai/gpt-oss-20b",
             messages=messages,
             stream=True,
             max_tokens=5,

tests/local_testing/test_text_completion.py

@@ -4036,7 +4036,7 @@ def test_async_text_completion_together_ai():
     async def test_get_response():
         try:
             response = await litellm.atext_completion(
-                model="together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo",
+                model="together_ai/openai/gpt-oss-20b",
                 prompt="good morning",
                 max_tokens=10,
             )