NewCLI Code API

code.newcli.com

LMSpeed tracks NewCLI Code API API pricing, model coverage, speed tests, and uptime signals for code.newcli.com.

An OpenAI-compatible API service for code generation models.

NewCLI Code API offers 17 LLM API models.

Speed benchmark average: 44 tok/s.

Avg Speed43.54 tok/s

Latency3.79 s

Updated6/8/2026

Created At12/20/2025

Website

API Endpoints

code.newcli.com

Supported Models

Model	Speed	Latency	Tests
gpt-5.5	43.54 tok/s	3.79s	10

Available Models

16 models available (last updated: 6/3/2026)

claude-3-5-haiku-20241022claude-haiku-4-5-20251001claude-opus-4-5-20251101claude-opus-4-6claude-opus-4-7claude-sonnet-4-5-20250929claude-sonnet-4-6gpt-5.2gpt-5.3gpt-5.3-codexgpt-5.4gpt-5.4-fastgpt-5.5gpt-5.5-fastgpt-image-1gpt-image-2

NewCLI Code API

API Endpoints

Supported Models

Available Models

NewCLI Code API

API Endpoints

Leaderboard Rankings

Supported Models

Available Models

Leaderboard Rankings