← Back to context Comment by bossyTeacher 16 hours ago Anyone who has used gpt-x via openai vs microsoft has experienced this very clearly. 3 comments bossyTeacher Reply energy123 7 hours ago Which one is better? dannyw 5 hours ago For OpenAI, OpenAI direct has always been better; except maybe early 2023-era when OpenAI Platform was not that stable or reliable yet.For Anthropic, it can vary based on model and time. For Opus 4.7, Bedrock is the clear winner in TPS by leaps: https://artificialanalysis.ai/models/claude-opus-4-7/provide... weli 6 hours ago As a rule of thumb inference offered by the model labs are closer to the "true implementation" compared to third parties. They have other problems though.
energy123 7 hours ago Which one is better? dannyw 5 hours ago For OpenAI, OpenAI direct has always been better; except maybe early 2023-era when OpenAI Platform was not that stable or reliable yet.For Anthropic, it can vary based on model and time. For Opus 4.7, Bedrock is the clear winner in TPS by leaps: https://artificialanalysis.ai/models/claude-opus-4-7/provide... weli 6 hours ago As a rule of thumb inference offered by the model labs are closer to the "true implementation" compared to third parties. They have other problems though.
dannyw 5 hours ago For OpenAI, OpenAI direct has always been better; except maybe early 2023-era when OpenAI Platform was not that stable or reliable yet.For Anthropic, it can vary based on model and time. For Opus 4.7, Bedrock is the clear winner in TPS by leaps: https://artificialanalysis.ai/models/claude-opus-4-7/provide...
weli 6 hours ago As a rule of thumb inference offered by the model labs are closer to the "true implementation" compared to third parties. They have other problems though.
Which one is better?
For OpenAI, OpenAI direct has always been better; except maybe early 2023-era when OpenAI Platform was not that stable or reliable yet.
For Anthropic, it can vary based on model and time. For Opus 4.7, Bedrock is the clear winner in TPS by leaps: https://artificialanalysis.ai/models/claude-opus-4-7/provide...
As a rule of thumb inference offered by the model labs are closer to the "true implementation" compared to third parties. They have other problems though.