THE AI MODEL DIRECTORY Start exploring models here

Find your ideal AI model.

From language to images, open weights to APIs. Understand capabilities and compare real costs.
Find the right engine for your next idea.

Explore AI models 6

Provider Input Output License

Discover models worth your attention

GGUFDumps

koboldcpp

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Category pending

Input Not verified→ Output Not verified

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

This repo contains a few simple image generation models. You can also load any Stable Diffusion 1.5, SDXL, SD3 or Flux model into KoboldCpp. For SD1.5 and SDXL, you only need the basic model (and VAE fix if no baked VAE). For SD3 and Flux you will also need a Clip and T5-XXL model (not included here) You can use `--sdmodel` to load the base model, and check `--help` for other SD settings. They are all also available in the image tab in the launcher

Category pending

Input Not verified→ Output Not verified

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

kcppt

koboldcpp

基础档案已收录，详细介绍后续补充。可先查看厂商、分类与来源。

Basic profile indexed · More details to follow

Category pending

Input Not verified→ Output Not verified

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

mmproj

koboldcpp

Please pick the correct projector model to load for your architecture (e.g. all Mistral 7B based models should use the Mistral 7B projector.) When enabled, make sure you refresh KoboldAI Lite, then click Add Img and upload your image. Clicking that image should show Vision is enabled.

Category pending

Input Not verified→ Output Not verified

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

music

koboldcpp

Use the .kcppt files for easy configuration, these will download the right models for you automatically.

Category pending

Input Not verified→ Output Not verified

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

tts

koboldcpp

**For Kokoro, Parler or Dia:** Download the respective model and load it into the TTS model in koboldcpp. You do not need a wavtokenizer. **For Qwen3 TTS (legacy):** You'll need 2 models, one Qwen3TTS model and one Qwen3TTSTokenizer. **For Audio.cpp models:** Download the respective single-file model from this directory and load it into the TTS model in koboldcpp.

Category pending

Input Not verified→ Output Not verified

Price not verifiedCheck multimodal and channel pricing separately

View details ↗

CompareSource / docs ↗

COST EXPLORER

Great models. Clear costs.

Cost analysis

Adjust monthly token usage to compare estimated API costs.

Monthly input tokens 10 MMonthly output tokens 2 M1 M = 1 million tokens · USD
Compares base text-token rates within the same channel

Uses collected, comparable USD-per-million-token rates. Snapshots exclude cache discounts, tiers, extra reasoning output and taxes. Check current source prices.

MODEL HANDBOOK

Understand before you choose

Selection guide & FAQ

How should API prices be compared?+

Separate input, output and cache rates, then estimate the same workload. Image, audio and video rates may use items, duration or resolution rather than tokens.

Do open weights mean free commercial use?+

Not necessarily. Check each version’s license, commercial restrictions and policies. Self-hosting also incurs compute and maintenance costs.

Is the top-ranked model the best for me?+

Rankings depend on tasks, versions and methods. Compare accuracy, latency, reliability and costs on your own workload.

Find your ideal AI model.

Explore AI models 6

GGUFDumps

imgmodel

kcppt

mmproj

music

tts

No matching models

Great models. Clear costs.

Understand before you choose

Follow trends. Find tools. Explore models.