Files
litellm/tests/local_testing/test_multiple_deployments.py
T
Yuneng Jiang a9c6156137 [Fix] Test - Together AI: replace deprecated Mixtral with serverless Qwen3.5-9B
Mixtral-8x7B-Instruct-v0.1 is no longer on Together AI's serverless tier
and now requires a dedicated endpoint, causing multiple tests to fail in CI:

  - test_together_ai.py::TestTogetherAI::test_empty_tools
  - test_completion.py::test_completion_together_ai_stream
  - test_completion.py::test_customprompt_together_ai
  - test_completion.py::test_completion_custom_provider_model_name
  - test_text_completion.py::test_async_text_completion_together_ai

Qwen/Qwen3.5-9B is currently serverless on Together AI and supports
function calling, satisfying BaseLLMChatTest capability requirements.
2026-04-14 17:43:35 -07:00

55 lines
1.6 KiB
Python

#### What this tests ####
# This tests error handling + logging (esp. for sentry breadcrumbs)
import sys, os
import traceback
sys.path.insert(
0, os.path.abspath("../..")
) # Adds the parent directory to the system path
import pytest
import litellm
from litellm import completion
messages = [{"role": "user", "content": "Hey, how's it going?"}]
## All your mistral deployments ##
model_list = [
{
"model_name": "mistral-7b-instruct",
"litellm_params": { # params for litellm completion/embedding call
"model": "replicate/mistralai/mistral-7b-instruct-v0.1:83b6a56e7c828e667f21fd596c338fd4f0039b46bcfa18d973e8e70e455fda70",
"api_key": os.getenv("REPLICATE_API_KEY"),
},
},
{
"model_name": "mistral-7b-instruct",
"litellm_params": { # params for litellm completion/embedding call
"model": "together_ai/Qwen/Qwen3.5-9B",
"api_key": os.getenv("TOGETHERAI_API_KEY"),
},
},
{
"model_name": "mistral-7b-instruct",
"litellm_params": {
"model": "deepinfra/mistralai/Mistral-7B-Instruct-v0.1",
"api_key": os.getenv("DEEPINFRA_API_KEY"),
},
},
]
def test_multiple_deployments():
try:
## LiteLLM completion call ## returns first response
response = completion(
model="mistral-7b-instruct", messages=messages, model_list=model_list
)
print(f"response: {response}")
except Exception as e:
traceback.print_exc()
pytest.fail(f"An exception occurred: {e}")
test_multiple_deployments()