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

10 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
01	GPT-5 Image Mini openai · text-to-image API-only	—	400 K	proprietary · API terms	—	API $2.38/M
02	GPT-5 Image openai · text-to-image API-only	—	400 K	proprietary · API terms	—	API $10.00/M
03	Nano Banana (Gemini 2.5 Flash Image) google · text-to-image API-only	—	33 K	proprietary · API terms	—	API $0.85/M
04	Nano Banana 2.1 google · text-to-image API-only	—	66 K	proprietary · API terms	—	API $3.00/M
05	Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) google · text-to-image API-only	—	66 K	proprietary · API terms	—	API $0.56/M
06	Nano Banana 2 (Gemini 3.1 Flash Image) google · text-to-image API-only	—	131 K	proprietary · API terms	—	API $1.13/M
07	Nano Banana Pro (Gemini 3 Pro Image) google · text-to-image API-only	—	66 K	proprietary · API terms	—	API $4.50/M
08	GPT-5.4 Image 2 openai · text-to-image API-only	—	272 K	proprietary · API terms	—	API $9.75/M
09	Nano Banana 2 (Gemini 3.1 Flash Image Preview) google · text-to-image API-only	—	66 K	proprietary · API terms	—	API $1.13/M
10	Nano Banana Pro (Gemini 3 Pro Image Preview) google · text-to-image API-only	—	66 K	proprietary · API terms	—	API $4.50/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.