Search the full model catalog.

Chat model based on Qwen 3.8 27B with refusal behavior reduced through direction removal. On Wiro a request takes about 25K input tokens and returns up to 16K.

Seed v2.1 Turbo by ByteDance is a 256K-context reasoning model for coding and agent workflows. It can use images for understanding and returns text or JSON.

Seed V2 Pro is ByteDance’s Seed2.0 Pro-class model for long-horizon reasoning, agent-style task planning, and image-grounded Q&A in chat workflows. ([seed.bytedance.com](https://seed.bytedance.com/en/seed2?utm_source=openai))

Gemini 3.5 Flash-Lite is Google’s fast multimodal model for high-volume extraction, classification, and sub-agent tasks, with up to 1,048,576 input tokens.

Gemini 3.6 Flash by Google is a fast, natively multimodal reasoning model for agentic coding and long-context analysis. It takes text plus media and returns text.

OpenAI’s GPT 5.6 Luna is a fast GPT‑5.6 tier for vision Q&A and chat. Add one or more images plus a prompt to get grounded text answers.

OpenAI GPT 5.6 Terra is a balanced multimodal model for everyday work. Add images and a prompt to get clear, grounded text analysis and writing.

OpenAI’s GPT 5.6 Sol is a flagship reasoning model that can analyze images and produce detailed text answers for coding, research, and visual Q&A.

Grok 4.5 is xAI’s flagship reasoning model for coding and long-context work. It supports tool calling and image understanding, returning detailed text answers.

GPT-5.4 Nano is OpenAI’s smallest GPT-5.4 tier for fast classification, extraction, and image understanding. Built for high-volume workflows.

OpenAI GPT‑5.4 mini is a text model with image understanding and tool support. It’s built for high-volume coding assistants, subagents, and UI screenshot analysis.

OpenAI GPT-5.4 takes text plus optional images and returns detailed answers, code, and extracted facts. It supports a 1,050,000-token context window.

OpenAI GPT‑5.5 is a long-context reasoning model that accepts text and images, then generates reliable writing, code, and structured text outputs for professional work.

Google’s Gemini 3.5 Flash is a fast multimodal reasoning model built for agents, coding, and long-context analysis. It takes text plus media and returns text.

Qwen3.6-27B is a 27B dense vision-language model from Qwen for agentic coding and reasoning, with optional thinking traces in outputs. On Wiro a request takes about 25K input tokens and returns up to 16K.

Grok 4.1 Fast by xAI is a long-context chat model built for tool calling and agent workflows. It can analyze images and return grounded text answers with sources.

Grok 4.20 is xAI’s flagship text model with a 2M-token context window, tool calling, and structured JSON outputs. Attach images for vision Q&A and OCR.

Decensored Qwen3.5-4B checkpoint for chat, coding, and analysis. Supports optional thinking traces and sampling controls for output style. On Wiro a request takes about 72K input tokens and returns up to 16K.

A large language model optimized for chat interactions and logical reasoning tasks. Designed for developers and researchers.

Qwen3.5-4B is the 4B model of Qwen's Qwen3.5 line. A Thinking field turns its reasoning pass on or off, and Wiro gives it room for 72,704 input tokens per request.