Guide

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...

Nemotron multimodal model for visual reasoning and agentic AI workflows

Nemotron multimodal model for visual reasoning and agentic AI workflows

MiniMax-M2 from Fireworks AI - text input, 192,000 token context

MiniMax-M2 from Synthetic - text input, 196,608 token context

Efficient open MiniMax model built for coding agents and tool-heavy workflows

Efficient open MiniMax model built for coding agents and tool-heavy workflows

Efficient open MiniMax model built for coding agents and tool-heavy workflows

Efficient open MiniMax model built for coding agents and tool-heavy workflows

MiniMax model for chat, coding, office work, and agentic tasks

Video model for prompt-guided generation, editing, and motion workflows

OCR model for extracting structured text from documents and screenshots

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning,...

Qwen3-VL-32B-Instruct is a large-scale multimodal vision-language model designed for high-precision understanding and reasoning across text, images, and video. With 32 billion parameters, it combines deep visual perception with advanced text...

Multimodal model for analyzing text, images, documents, and rich media

LFM2-8B-A1B is an efficient on-device Mixture-of-Experts (MoE) model from Liquid AI’s LFM2 family, built for fast, high-quality inference on edge hardware. It uses 8.3B total parameters with only ~1.5B active per token, delivering strong performance while keeping compute and memory usage low—making it ideal for phones, tablets, and laptops.

LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.

Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...

Speech generation model for controllable voice, narration, and audio delivery

Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4...

Cogito v2 405B is a dense hybrid reasoning model that combines direct answering capabilities with advanced self-reflection. It represents a significant step toward frontier intelligence with dense architecture delivering performance competitive with leading closed models. This advanced reasoning system combines policy improvement with massive scale for exceptional capabilities.

Qwen vision-language model for visual reasoning, documents, and agent tasks

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image generation. This natively multimodal model features superior instruction following, text...

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

Video model for prompt-guided generation, editing, and motion workflows

Video model for prompt-guided generation, editing, and motion workflows

Fast Claude lane for lightweight agents, office tasks, and responsive chat

Fast Claude model for responsive assistance, classification, and lightweight agents

Fast Claude model for responsive assistance, classification, and lightweight agents

Fast Claude model for responsive assistance, classification, and lightweight agents

Fast Claude model for responsive assistance, classification, and lightweight agents

Fast Claude model for responsive assistance, classification, and lightweight agents

Fast Claude model for responsive assistance, classification, and lightweight agents

Fast Claude model for responsive assistance, classification, and lightweight agents

Fast Claude lane for lightweight agents, office tasks, and responsive chat

Video model for prompt-guided generation, editing, and motion workflows

Video model for prompt-guided generation, editing, and motion workflows

Fast Claude lane for lightweight agents, office tasks, and responsive chat

Qwen3-VL-8B-Thinking is the reasoning-optimized variant of the Qwen3-VL-8B multimodal model, designed for advanced visual and textual reasoning across complex scenes, documents, and temporal sequences. It integrates enhanced multimodal alignment and...

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...

[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code quality, and user experience while incorporating GPT Image 1's superior instruction following,...

Efficient GLM model for fast reasoning, coding, and agent workflows

Qwen vision-language model for visual reasoning, documents, and agent tasks

Qwen vision-language model for visual reasoning, documents, and agent tasks

o3-deep-research is OpenAI's advanced model for deep research, designed to tackle complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

o4-mini-deep-research is OpenAI's faster, more affordable deep research model—ideal for tackling complex, multi-step research tasks. Note: This model always uses the 'web_search' tool which adds additional cost.

Llama-3.3-Nemotron-Super-49B-v1.5 is a 49B-parameter, English-centric reasoning/chat model derived from Meta’s Llama-3.3-70B-Instruct with a 128K context. It’s post-trained for agentic workflows (RAG, tool calling) via SFT across math, code, science, and...

Speech generation model for controllable voice, narration, and audio delivery

ERNIE-4.5-21B-A3B-Thinking is Baidu's upgraded lightweight MoE model, refined to boost reasoning depth and quality for top-tier performance in logical puzzles, math, science, coding, text generation, and expert-level academic benchmarks.

Qwen coding model for software agents, repository edits, and code reasoning