OpenAI: GPT-5 Mini

Not enough data yet to set these providers' speed against their price.

llm.buzz and OpenAI tie for the cheapest OpenAI: GPT-5 Mini, at $0.6875 per million tokens blended.
OpenAI serves OpenAI: GPT-5 Mini fastest, at 93 tok/s (median over 24 hours).
OpenAI starts answering OpenAI: GPT-5 Mini quickest, first token in 2.48 s (median over 24 hours).
OpenAI has the best uptime for OpenAI: GPT-5 Mini, 100% over 72 hours.

ModelCompare with

Output speedtok/s, median over 24 h, higher is better

OpenAI93 tok/s

llm.buzzNot measured

First tokenseconds, median over 24 h, lower is better

OpenAI2.48 s

llm.buzzNot measured

Blended price$ per 1M tokens, lower is better

llm.buzz$0.6875

OpenAI$0.6875

2 providers

Providers with their prices and measured figures. Select a column header to sort by it.

llm.buzz	$0.6875	$0.25	$2.00	Not measured	Not measured	97.2%test
OpenAI	$0.6875	$0.25	$2.00	93 tok/stest	2.48 stest	100%test

Customer traffic on this model is still below the publishing floor, so its figures are from llm.buzz's test requests, tagged "test".

The last 24 hours, by hour

Last 24 hours, from llm.buzz's test requests

Output speed, tok/s

Data table

Provider	From (UTC)	p50	p90	p99
OpenAI	Oct 26, 13:00	93 tok/s	93 tok/s	93 tok/s
OpenAI	Oct 26, 21:00	93 tok/s	93 tok/s	93 tok/s
OpenAI	Oct 27, 02:00	93 tok/s	93 tok/s	93 tok/s
OpenAI	Last 24 hours	93 tok/s	93 tok/s	93 tok/s

Time to first token

Data table

Provider	From (UTC)	p50	p90	p99
OpenAI	Oct 26, 13:00	3.57 s	3.57 s	3.57 s
OpenAI	Oct 26, 21:00	2.48 s	2.48 s	2.48 s
OpenAI	Oct 27, 02:00	2.07 s	2.07 s	2.07 s
OpenAI	Last 24 hours	2.48 s	3.57 s	3.57 s

Last 72 hours, by hour

Best provider 100%

This model

llm.buzz

OpenAI

Speed and first tokenOutput speed and time to first token are medians over the last 24 hours, per provider, from text requests.
UptimeThe share of attempts the provider served over the 72 hours before the figures' end, provider failures counted against it.
Two sourcesCustomer traffic once enough organizations count toward a figure; below that, llm.buzz's test requests, short streamed requests sent to every live provider. The tables tag those "test".
PriceEach provider's price per million tokens, with a running discount applied. The blended price weighs input and output 3 to 1, a chat request's usual mix.

Let the router pickName the model; llm.buzz sends each request to a provider and moves to the next when one fails.