Models

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...

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

[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows, allowing users to seamlessly move between reasoning, coding, and...

Agentic model for autonomous multi-step research, synthesis, and cited reports

Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

Flagship Qwen model for complex reasoning, coding, and agentic workflows

xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk

Open multimodal Qwen MoE for local agents that need vision, audio, and code

Fast Grok coding model tuned for agentic engineering and iterative edits

Stronger Opus tier for advanced software work and high-stakes reasoning

Low-latency speech generation with steerable prompts and expressive audio tags

Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....

Strong GLM coding model for agentic engineering, terminals, and repository generation

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...

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...

Open Gemma instruction model for efficient chat and self-hosted deployments

Open Gemma instruction model for efficient chat and self-hosted deployments

StepFun flash model for efficient multimodal reasoning, coding, and tool use

Earlier Qwen multimodal workhorse for million-token agent and document tasks

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7...

Fast GLM vision model for screenshots, documents, and multimodal agent tasks

High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications

Nemotron model for efficient reasoning, coding, and specialized AI agents

MiMo omni model for text, image, video, audio, and agents

Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks

Low-latency M2.7 variant for interactive coding plans and agent loops

Open MiniMax flagship for coding agents, office automation, and complex environments

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding,...

Faster GLM-5 lane for coding agents that need lower latency

Efficient Mistral model for fast chat, extraction, and production assistants

Fast Mistral production model for chat, extraction, and cost-sensitive agents

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...

Reasoning Grok for document-heavy analysis and long-horizon tool use

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token context window (922K input, 128K...

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for...

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2.5 Flash performance across...

Compact Qwen3.5 multimodal model for fast chat, reasoning, and tool use

Small Qwen3.5 multimodal model for low-cost chat, reasoning, and tool use

Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combines...

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...

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

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

Qwen instruction model for multilingual chat, reasoning, and tool use

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

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

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...