Claude Opus is 10x faster than OpenAI GPT 5 at non-streaming completions - Peterbe.comSkip to main navigation<br>Skip to main content<br>Skip to search<br>Claude Opus is 10x faster than OpenAI GPT 5 at non-streaming completions<br>Friday, Jul 24, 2026<br>0 comments Python, AI
This picture summarizes it well:
Here on my blog, for this popular blog post I get a lot of comments. 28k blog comments over the years. Some of them are terribly written and hard to understand, so I let AI suggest a rewrite. That code that sends the blog post comment to AI, I actually fire off three times: once with OpenAI gpt-5, once with OpenAI gpt-5-mini, and once with Claude claude-opus-4.8. I use my human eyes and judgement to evaluate the results, and I can tell you they do equally well. Only the slightest differences.
The surprising thing is how amazingly slow OpenAI's gpt-5 is! It's nearly 10x slower than claude-opus-4.8. What's up with that!?
It's also clear that the latency difference between gpt-5-mini and gpt-5 is significant. At the time of writing, the input token price difference between gpt-5.4 and gpt-5.4-mini is $2.50 compared to $0.75! That's a 3x difference.
Conclusion
If you're constructing a prompt the API, use Claude.
If you have to use OpenAI, consider the mini model because it's both cheaper and faster.
Bonus
Before I added Claude, I used to use litellm to wrap OpenAI's models. The code looks like this:
response = litellm.completion(<br>model="openai-gpt-5",<br>api_key=settings.OPENAI_API_KEY,<br>messages=my_prompt_messages,
Unlike, if you use the native OpenAI Python SDK the invocation looks like this:
client = openai.OpenAI(api_key=settings.OPENAI_API_KEY)<br>response = client.responses.create(<br>model="gpt-5,<br>input=my_prompt_messages,
I measured the difference, in speed, where I compare using the OpenAI SDK versus the litellm wrapper and the difference looks like this:
Granted, in June I "only" did a bit over 30 of these calls, but strangely there's a difference!
I don't have the intricate knowledge to understand why the litellm makes the total time different from using the SDK. (not sure I care either!)
Either way, I'm moving away from litellm and only use the SDKs provided by Claude and OpenAI. Feels safer given the CVEs we've seen this year on litellm.
Type your comment here<br>Post commentYour email will never ever be published.
Related posts<br>Previous:Best Django Redis configuration for speed and size July 19, 2026 Python, DjangoRelated by category:How to use a list/tuple/array in Django with a raw SQL cursor July 14, 2026 PythonUsing AI to rewrite blog post comments November 12, 2025 PythonComparison of speed between gpt-5, gpt-5-mini, and gpt-5-nano December 15, 2025 PythonAutocomplete using PostgreSQL instead of Elasticsearch December 18, 2025 PythonRelated by keyword:Using AI to rewrite blog post comments November 12, 2025 This site, PythonComparison of speed between gpt-5, gpt-5-mini, and gpt-5-nano December 15, 2025 PythonBot traffic hitting my blog July 9, 2025 This site, Web development<br>© peterbe.com 2003 - 2026<br>Check out my side project: That's Groce!