200 models · 1,226 open weights · 200 API-only · refreshed nightly

API-only models

Closed models whose weights are not published: you can only call them through a hosted API. Prices are USD per million tokens from OpenRouter, refreshed daily; intelligence and coding scores come from Artificial Analysis.

All 1,426 Open weights (self-host) 1,226 API-only 200

All text-generation 186 text-to-image 10 text-to-speech 4

Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB

4 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
01	GPT Audio openai · text-to-speech API-only	—	128 K	proprietary · API terms	—	API $4.38/M
02	GPT Audio Mini openai · text-to-speech API-only	—	128 K	proprietary · API terms	—	API $1.05/M
03	Lyria 3 Pro Preview google · text-to-speech API-only	—	1.0 M	proprietary · API terms	—	API Free/M
04	Lyria 3 Clip Preview google · text-to-speech API-only	—	1.0 M	proprietary · API terms	—	API Free/M

VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.