1984

1984 provides an OpenAI-compatible chat API service hosted in Japan for accessing AI language models.

1984 offers 1 LLM API models.

Speed benchmark average: 145 tok/s.

Avg Speed145.28 tok/s

Latency1.06 s

Updated4/16/2026

Created At8/13/2025

Supported Models

Model	Speed	Latency	Tests
vllm.Qwen/Qwen3-Coder-30B-A3B-Instruct	145.28 tok/s	1.06s	5

1984 provides an OpenAI-compatible chat API service hosted in Japan for accessing AI language models.

1984 offers 1 LLM API models.

Speed benchmark average: 145 tok/s.

Avg Speed145.28 tok/s

Latency1.06 s

Updated4/16/2026

Created At8/13/2025

Model	Speed	Latency	Tests
vllm.Qwen/Qwen3-Coder-30B-A3B-Instruct	145.28 tok/s	1.06s	5

Data as of Apr 16, 2026, 02:27 PMRankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.