Model catalog
Open-source and free-tier models across eight modalities — all behind one API.
Text Generation
Chat and completion with open-source LLMs. OpenAI-compatible.
Gemini 2.5 Flash
Google's fast multimodal model with a large context window.
Llama 3.1 8B Instant
Fast, capable general-purpose LLM. Great default for most tasks.
Llama 3.3 70B Versatile
High-quality reasoning and generation for complex tasks.
Meta: Llama 3.3 70B Instruct (free)
The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...
OpenAI: gpt-oss-120b (free)
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
OpenAI: gpt-oss-20b (free)
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
Qwen: Qwen3 Coder 480B A35B (free)
Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, tool use, and long-context reasoning over...
Cohere: North Mini Code (free)
North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...
GPT-OSS 20B
Open-weight model with strong instruction following.
Google: Gemma 4 26B A4B (free)
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...
Google: Gemma 4 31B (free)
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
LiquidAI: LFM2.5-1.2B-Instruct (free)
LFM2.5-1.2B-Instruct is a compact, high-performance instruction-tuned model built for fast on-device AI. It delivers strong chat quality in a 1.2B parameter footprint, with efficient edge inference and broad runtime support.
LiquidAI: LFM2.5-1.2B-Thinking (free)
LFM2.5-1.2B-Thinking is a lightweight reasoning-focused model optimized for agentic tasks, data extraction, and RAG—while still running comfortably on edge devices. It supports long context (up to 32K tokens) and is...
Meta: Llama 3.2 3B Instruct (free)
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...
NVIDIA: Nemotron 3 Nano 30B A3B (free)
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
NVIDIA: Nemotron 3 Nano Omni (free)
NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...
NVIDIA: Nemotron 3 Super (free)
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
NVIDIA: Nemotron 3 Ultra (free)
NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...
NVIDIA: Nemotron 3.5 Content Safety (free)
NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...
NVIDIA: Nemotron Nano 12B 2 VL (free)
NVIDIA Nemotron Nano 2 VL is a 12-billion-parameter open multimodal reasoning model designed for video understanding and document intelligence. It introduces a hybrid Transformer-Mamba architecture, combining transformer-level accuracy with Mamba’s...
NVIDIA: Nemotron Nano 9B V2 (free)
NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and...
Nex AGI: Nex-N2-Pro (free)
Nex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts text and image input and produces...
Nous: Hermes 3 405B Instruct (free)
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
Poolside: Laguna M.1 (free)
Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...
Poolside: Laguna XS.2 (free)
Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai/), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...
Qwen3 32B
Multilingual model with solid coding and math abilities.
Qwen: Qwen3 Next 80B A3B Instruct (free)
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
Venice: Uncensored (free)
Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...
Image to Text
Vision understanding, captioning, and OCR from images.
Gemini 2.5 Flash (Vision)
Image understanding, captioning, and OCR.
Llama 4 Scout (Vision)
Open multimodal model for visual question answering.
Text to Image
Generate images from prompts with FLUX and SDXL.
FLUX.1 [schnell]
Ultra-fast, high-quality text-to-image generation.
FLUX.1 [dev]
Highest-detail FLUX model for photorealistic images.
Stable Diffusion XL
Versatile open image model with broad style support.
Image to Image
Edit and transform images with a guiding prompt.
FLUX.1 Kontext [dev]
Prompt-guided image editing and transformation.
Text to Video
Create short video clips from text prompts.
LTX Video
Generate short video clips from a text prompt.
Text to Speech
Natural-sounding speech synthesis from text.
PlayAI TTS
Natural English speech synthesis.
Kokoro 82M
Lightweight open-source TTS via Hugging Face.
Speech to Text
Fast, multilingual transcription with Whisper.
Whisper Large v3 Turbo
Fast multilingual transcription (216x real-time).
Whisper Large v3
State-of-the-art accuracy for transcription & translation.
Embeddings
Vector embeddings for search and RAG (entity-to-entity).
BGE Base EN v1.5
Compact, high-quality English text embeddings.
Multilingual E5 Large
Multilingual embeddings for cross-language search.