Dream API

Name: Dream API
Rating: 4.6 (92 reviews)

A unified LLM API gateway providing access to multiple AI models with enterprise-grade security, low latency, and high concurrency.

Dream API offers 16 LLM API models.

Speed benchmark average: 97 tok/s.

Avg Speed92.56 tok/s

Latency1.64 s

Total Tests92

Models16

Updated12/7/2025

Created At8/13/2025

Supported Models

Model	Speed	Latency	Tests
gpt-3.5-turbo-1106	156.38 tok/s	0.82s	5
gpt-3.5-turbo-16k	145.74 tok/s	0.64s	5
gpt-3.5-turbo-0613	140.29 tok/s	0.50s	5
gpt-4o-mini-2024-07-18	130.72 tok/s	0.60s	5
gpt-3.5-turbo-0125	123.25 tok/s	0.69s	4
gpt-4o-2024-05-13	122.74 tok/s	1.60s	5
gpt-3.5-turbo	121.66 tok/s	0.79s	5
gpt-3.5-turbo-16k-0613	108.01 tok/s	0.73s	5
gpt-4o-2024-08-06	107.84 tok/s	3.23s	5
gpt-4o	101.73 tok/s	1.24s	10
gpt-4o-mini	101.71 tok/s	0.68s	5
gpt-4o-2024-11-20	76.02 tok/s	0.93s	10
gpt-4-1106-preview	42.07 tok/s	0.82s	5
gpt-4-0125-preview	28.16 tok/s	0.67s	5
gpt-4-turbo	27.93 tok/s	0.73s	5
deepseek-r1	9.84 tok/s	8.43s	8