diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 85b0a7677..d501d8572 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -1392,36 +1392,6 @@ "mode": "chat", "supports_function_calling": true }, - "sambanova/Meta-Llama-3.1-8B-Instruct": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 0.0000001, - "output_cost_per_token": 0.0000001, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true - }, - "sambanova/Meta-Llama-3.1-70B-Instruct": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 0.0000003, - "output_cost_per_token": 0.0000003, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true - }, - "sambanova/Meta-Llama-3.1-405B-Instruct": { - "max_tokens": 256000, - "max_input_tokens": 256000, - "max_output_tokens": 256000, - "input_cost_per_token": 0.0000006, - "output_cost_per_token": 0.0000006, - "litellm_provider": "sambanova", - "mode": "chat", - "supports_function_calling": true - }, "friendliai/mixtral-8x7b-instruct-v0-1": { "max_tokens": 32768, "max_input_tokens": 32768, diff --git a/tests/load_tests/test_otel_load_test.py b/tests/load_tests/test_otel_load_test.py index f0f4d959a..c6a160276 100644 --- a/tests/load_tests/test_otel_load_test.py +++ b/tests/load_tests/test_otel_load_test.py @@ -42,8 +42,8 @@ def test_otel_logging_async(): print(f"Average performance difference: {avg_percent_diff:.2f}%") assert ( - avg_percent_diff < 10 - ), f"Average performance difference of {avg_percent_diff:.2f}% exceeds 10% threshold" + avg_percent_diff < 15 + ), f"Average performance difference of {avg_percent_diff:.2f}% exceeds 15% threshold" except litellm.Timeout as e: pass