Campeões de Velocidade Ranking

Top 20 modelos ranqueados por velocidade de saída (tok/s)

Posição	Modelo	Criador	Velocidade de Saída (tok/s)	Preço/1M	Velocidade
🥇	Mercury 2 Inception	Inception	771 tok/s	$0.38	771 tok/s
🥈	Granite 4.0 H Small IBM	IBM	496 tok/s	$0.11	496 tok/s
🥉	Granite 3.3 8B (Non-reasoning) IBM	IBM	443 tok/s	$0.09	443 tok/s
4	NVIDIA Nemotron 3 Super 120B A12B (Reasoning) NVIDIA	NVIDIA	408 tok/s	$0.41	408 tok/s
5	Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) Google	Google	356 tok/s	$0.17	356 tok/s
6	Nova Micro Amazon	Amazon	344 tok/s	$0.06	344 tok/s
7	Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) Google	Google	330 tok/s	$0.17	330 tok/s
8	gpt-oss-20B (low) OpenAI	OpenAI	321 tok/s	$0.09	321 tok/s
9	Gemini 2.5 Flash-Lite (Reasoning) Google	Google	317 tok/s	$0.17	317 tok/s
10	Sarvam 30B (Reasoning) Sarvam	Sarvam	305 tok/s	$0.00	305 tok/s
11	gpt-oss-20B (high) OpenAI	OpenAI	304 tok/s	$0.09	304 tok/s
12	gpt-oss-120B (low) OpenAI	OpenAI	299 tok/s	$0.26	299 tok/s
13	gpt-oss-120B (high) OpenAI	OpenAI	291 tok/s	$0.26	291 tok/s
14	Ministral 3 3B Mistral	Mistral	289 tok/s	$0.10	289 tok/s
15	Gemini 2.5 Flash-Lite (Non-reasoning) Google	Google	244 tok/s	$0.17	244 tok/s
16	GPT-5.4 mini (xhigh) OpenAI	OpenAI	230 tok/s	$1.69	230 tok/s
17	Gemini 3.1 Flash-Lite Preview Google	Google	230 tok/s	$0.56	230 tok/s
18	GPT-5.4 mini (medium) OpenAI	OpenAI	229 tok/s	$1.69	229 tok/s
19	Gemini 2.5 Flash (Reasoning) Google	Google	229 tok/s	$0.85	229 tok/s
20	Qwen3 0.6B (Reasoning) Alibaba	Alibaba	224 tok/s	$0.40	224 tok/s