01Build on
Models
New models worth building on, in every modality.
Drama 3
A text-to-speech model for builders who need expressive long-form voice synthesis inside their own pipelines.
Ling 3.1 Flash
A permissively d open-weight text model gives builders a self-hostable option without legal review before serving.
MiniCPM-V 4.7 35B A3B
Extending the MiniCPM-V line upward gives builders a heavier vision-language option for image and document understanding inside their own stack.
Gemini 4 Argon
The newest flagship reasoning tier, aimed at the hardest multi-step problems and long-horizon agentic tasks.
LFM2.5 24B A2B
A small-footprint text model sized for single-GPU and local serving where a hosted API is not an option.
Olmo 3.1 32B Think
A reasoning model from a lab that publishes its training data and recipes, so the whole stack can be inspected and adapted.
MiniCPM-V 4.7 1B
The small end of the same release targets on-device and edge vision work where a hosted call is not an option.
ScaleDown Extract
Description-driven entity extraction that lets you define output fields in plain English instead of maintaining a fixed schema.
ScaleDown Summarize
Abstractive summarization as an endpoint, for when you need a faithful rewrite of long documents rather than lifted sentences.
Multics
Multics generates video from a still image, giving builders a self-hostable path to animating product shots, storyboards, or ad creative.
Muse Wonder
A frontier reasoning model built for agentic personal and professional work, taking text, images, video, audio, and PDFs through one endpoint.
H2O Lightning 4B
H2O Lightning 4B takes image-text input in a footprint small enough to co-locate with other services on one machine.
JEV 35B
JEV 35B targets classification and decision tasks, so it can gate or route traffic without paying for a full chat model.
LightOnOCR 3 0.8B
An image-to-text OCR model you can host yourself, so document extraction pipelines stop round-tripping every page through a hosted vision API.
Youtu-Parsing-Omni
Converts document images straight into structured text, so parsing can live inside a multimodal pipeline instead of a separate OCR stack.
Qwen-Image 2.1 Turbo
A faster cut of the Qwen image line for builders who want generation latency down without leaving the Qwen ecosystem.
Voxtral Mini 4B Realtime Arabic
Gives Arabic voice agents a streaming transcription path instead of forcing batch audio uploads through a hosted API.
Strands Decider 26B A4B
A heavier decider for agent stacks whose routing calls have outgrown what the small variant can resolve.
GPT-6.1 Sol
Sol is the model Asana's browser agent runs on, making it the current reference point for teams wiring web-automation agents into OpenAI's stack.
LIDstral Arabic
A small classifier for tagging Arabic text before it reaches a larger model, useful for routing and filtering pipelines.
Iris 3B
Small enough to run on your own hardware for asset generation when you would rather not call a hosted image API.
Step 5 Preview
A flagship agentic model aimed at long-horizon tool use and multi-step workflows.
NVIDIA CorrDiff Cosmo ERA5
NVIDIA's CorrDiff line lands on Hugging Face for teams doing atmospheric downscaling work who want the model weights in their own pipeline.
d1-omni 600M
A compact image-text model for local multimodal understanding on constrained hardware.
Interfaze 1 Lite
An image-to-image model for lightweight visual editing and generation pipelines.
d1-3B
A small multimodal model for local deployment and quick experimentation.
Claude Haiku 5.5
Built for high-volume summarization, subagents, and browser automation where throughput matters more than peak reasoning.
Cohere Transcribe 03-2026
Cohere's speech recognition entry gives builders a self-hostable transcription model to drop into their own audio pipeline instead of renting one per minute.
Cosmos-H Surgical Simulator
NVIDIA's image-to-video model built specifically for surgical simulation footage.
Mistral Large 4
Frontier-class reasoning, coding, and agentic work at $0.68/$2.09 per 1M tokens, with a 512K window that swallows whole repos.
Gemini Nano Banana 2.1
Google's image tier now handles product recontextualization better, which matters if you generate catalog or ad imagery where the object has to sit convincingly in a new scene.
PPLX Decider v1.1 27B
Perplexity's decider is built for routing and classification calls, so it can sit in front of a larger model as a gate that decides what actually gets sent downstream.
DiarizationLM Gemma 4 E4B
Speaker diarization model on Gemma 4 E4B, Apache-2.0, 8B total params.
VisionHOPE
MIT-licensed image classification model, no parameter count published.
Clef Flash
9.4B open image-text-to-text model under Apache 2.0, small enough to run locally while handling multimodal input.
GEV 26B Decide
A decision specialist that classifies instead of generating — judgment calls without a full LLM pass.
Kolibri 1
Open-weight German-English MoE built for sovereign, regulated EU deployments rather than raw scale.
JEV 27B VL
A mid-size vision-language model for builders who need image understanding inside an open stack, with no API dependency.
Clef
Apache-licensed 27.4B image-text-to-text model, useful for builders needing a self-hostable multimodal base.
ALoDLM 8B
Amazon's text generator, but cc-by-nc-4.0 keeps it out of commercial pipelines.