Provider directory
Imported model listings
Explore models discovered from provider APIs. Use the source listing to confirm availability, access and terms.
LiquidAI: LFM2.5-24B-A2B
liquid/lfm-2.5-24b-a2b
LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...
- Reported developer
- liquid
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
Pareto 26.9
unbiased/pareto-26.9
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
- Reported developer
- unbiased
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
Pareto 26.10
unbiased/pareto-26.10
Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.
- Reported developer
- unbiased
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
NVIDIA: Nemotron 3.5 Super VL (free)
nvidia/nemotron-3.5-super-vl:free
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
- Reported developer
- nvidia
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
NVIDIA: Nemotron 3.5 Super VL
nvidia/nemotron-3.5-super-vl
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...
- Reported developer
- nvidia
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
Meta: Muse Spark Open
meta/muse-spark-open
Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...
- Reported developer
- meta
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
Moondream: Moondream 3.1
moondream/moondream3.1-9b-a2b
Moondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and...
- Reported developer
- moondream
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
Moondream: Moondream 3 Preview
moondream/moondream3-preview
Moondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering, captioning, OCR, and visual reasoning over images, with...
- Reported developer
- moondream
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
Inception: Mercury 3
inception/mercury-3
Mercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applications where latency compounds, such...
- Reported developer
- inception
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
Reflection: Beam 1.0 501B A23B
reflection/beam-1.0-501b-a23b
Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...
- Reported developer
- reflection
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
XingChen: Xing4.0 29B A4B (free)
xingchen-agi/xing4.0-29b-a4b:free
Xing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B total parameters with 4B active per token...
- Reported developer
- xingchen-agi
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
Elorian: Glimpse
elorian/glimpse
Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...
- Reported developer
- elorian
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
DeepSeek: DeepSeek V4.1 Flash 1017
deepseek/deepseek-v4.1-flash-1017
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...
- Reported developer
- deepseek
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
MiniMax: MiniMax M3.1 Flash (free)
minimax/minimax-m3.1-flash:free
MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity. It is built for complex,...
- Reported developer
- minimax
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
Recursive: Flint (free)
recursive/flint-v1.0:free
Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is suited...
- Reported developer
- recursive
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
intfloat/multilingual-e5-large
intfloat/multilingual-e5-large
Imported provider listing. Add a reviewed English description before publication.
- Reported developer
- intfloat
- Reported license
- mitNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
FacebookAI/roberta-large
FacebookAI/roberta-large
Imported provider listing. Add a reviewed English description before publication.
- Reported developer
- FacebookAI
- Reported license
- mitNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
distilbert/distilbert-base-uncased
distilbert/distilbert-base-uncased
Imported provider listing. Add a reviewed English description before publication.
- Reported developer
- distilbert
- Reported license
- apache-2.0Not independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
Qwen/Qwen2.5-7B-Instruct
Qwen/Qwen2.5-7B-Instruct
Imported provider listing. Add a reviewed English description before publication.
- Reported developer
- Qwen
- Reported license
- apache-2.0Not independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
pyannote/speaker-diarization-3.1
pyannote/speaker-diarization-3.1
Imported provider listing. Add a reviewed English description before publication.
- Reported developer
- pyannote
- Reported license
- mitNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
Qwen/Qwen3.5-9B
Qwen/Qwen3.5-9B
Imported provider listing. Add a reviewed English description before publication.
- Reported developer
- Qwen
- Reported license
- apache-2.0Not independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
openai/clip-vit-large-patch14
openai/clip-vit-large-patch14
Imported provider listing. Add a reviewed English description before publication.
- Reported developer
- openai
- Reported license
- UnknownNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
FacebookAI/roberta-base
FacebookAI/roberta-base
Imported provider listing. Add a reviewed English description before publication.
- Reported developer
- FacebookAI
- Reported license
- mitNot independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed
laion/clap-htsat-fused
laion/clap-htsat-fused
Imported provider listing. Add a reviewed English description before publication.
- Reported developer
- laion
- Reported license
- apache-2.0Not independently verified
- Commercial-use rights
- Unknown
- Pricing
- Check provider
Independent check: not performed