How is image generation priced?

Per image, at the model’s default resolution and quality. Higher resolutions or step counts cost more on most APIs. Self-hosted open-source models are essentially free per image once you’ve provisioned the GPU.

What is the “intelligence index”?

A 0–100 composite of public benchmarks (MMLU, MMLU Pro, GPQA, MATH, HumanEval). Higher is better.

How often is this updated?

Monthly. Each model has a lastUpdated stamp. Open an issue if you spot something stale.

AI Models · Text-to-Image

Best Text-to-Image Models Text-to-Image

Generate still images from a text prompt.

Models

Providers

Text-to-Image models

4 models matched. Click any column to sort.

				Notes
Stable Diffusion 3.5 Large	Stability AI	Open	$0.01	Open weights, runs on a single GPU — community’s preferred base model.
FLUX.1 Pro	Black Forest Labs	Proprietary	$0.05	Sharp photorealism + the best text-in-image rendering in the industry.
Midjourney v6.1	Midjourney	Proprietary	$0.02	The artist’s favourite — best aesthetics, most opinionated style.
DALL·E 3	OpenAI	Proprietary	$0.04	Best prompt-adherence in the OpenAI ecosystem — built into ChatGPT.

Showing 4 of 4 models. Click any column header to sort. Prices are USD per 1M tokens unless noted otherwise. Estimates marked with *.

Browse by category

Drill into a slice of the catalog — open-source models, video models, or all models from one provider.

By License

Open Source

Models with publicly-released weights you can self-host or fine-tune.

Proprietary

Closed-weights API-only models from major labs.

By Purpose

Frontier

The most capable models from each major lab.

Reasoning

Long chain-of-thought models built for hard math, code, and planning.

Fast & Cheap

Production-grade workhorses with the best speed and cost.

Code

Models specialised for software engineering tasks.

Multimodal

Models that natively understand text, images, and beyond.

By Modality

Text-to-Video

Generate short video clips from a text prompt.

Text-to-Speech

Generate natural-sounding speech audio from text.

By Provider

OpenAI

All models from OpenAI — GPT, o-series and beyond.

Anthropic

Claude family of models from Anthropic.

Google

Gemini family of models from Google DeepMind.

Mistral

Models from Mistral AI — EU-hosted, multilingual.

DeepSeek

Frontier-class open-weights models from DeepSeek.

xAI

Grok models from xAI.

Frequently asked questions

For aesthetic quality and stylised work, Midjourney v6 is still the favourite. For photorealism and text-in-image, FLUX.1 Pro leads. For self-hosting and fine-tuning, Stable Diffusion 3.5 has the largest ecosystem.

Explore the full catalog

See every AI model in one place — intelligence, speed and price on a single sortable table.

All AI models LLM pricing calculator