Search the full model catalog.

A dense 9-billion parameter language model optimized for chat and reasoning tasks. Designed for efficient deployment and high-quality responses.

A decensored build of Qwen3.5-27B, made with Heretic, a tool that edits the model's weights to cut refusals. Text chat with an optional thinking mode and function calling.

The smallest model in ByteDance's Seed 2.0 series, a reasoning LLM that reads images and calls functions. Reasoning is on by default and can be switched off for simple jobs.

A lightweight ByteDance language model for chat and tool calling, with image understanding and a 256K-token context window.

Qwen3.5-27B is a 27B model from Qwen's Qwen3.5 line that always reasons before it replies and can call your functions. Qwen reports 72.4 on SWE-bench Verified for it.

Requests here run Gemini 3.1 Pro Preview, which Google built on Gemini 3 Pro's sparse mixture-of-experts design. One request can hold up to 1M tokens of mixed text, audio, video, images and documents.

GPT-5 Nano is a GPT-5 model that OpenAI describes as a good fit for summarization and classification. It reads text and up to 10 images and supports function calling, web search and structured output.

AI model for processing text prompts and image inputs with advanced reasoning capabilities. Supports multi-modal inputs and customizable responses.

A compact AI model optimized for text generation tasks, designed for efficient processing and accurate responses.

Google's Gemini 3 Flash reads text, images, video, audio and documents and answers in text. It is built on Gemini 3 Pro, with a thinking level you can set from minimal to high.

Google's Gemini 2.5 Flash reads text, images, video and audio and answers in text, with adjustable thinking, function calling and JSON schema output over a context of about one million tokens.

A Qwen3 mixture-of-experts model (30.5B total, 3.3B active) that reasons in a think block or answers directly, chosen turn by turn. On Wiro it accepts function definitions and can return JSON.

Qwen3-30B-A3B-Thinking-2507 reasons before every answer, and its thinking runs longer than in the original Qwen3-30B-A3B. Qwen recommends it for highly complex reasoning tasks.

Qwen3-32B is Qwen's 32.8B dense model. It reasons step by step by default and answers directly on request, and on Wiro it can call your functions or return a JSON object.

Qwen2.5-14B-Instruct is the 14.7B instruction-tuned model from Alibaba's Qwen2.5 series, built for chat, multilingual writing, coding help and JSON output.

Qwen reports 83.1 on MATH and 74.5 on Arena-Hard for this 32.5B-parameter Qwen2.5 chat model. On Wiro a request holds about 17,000 input tokens, with JSON mode and function calling.

A 3.21B-parameter Llama 3.2 model that Meta distilled from Llama 3.1 8B and 70B, for multilingual chat and summarization. On Wiro it takes up to 128 function tools and can reply with a JSON object.

A 12B model that Mistral AI trained jointly with NVIDIA, instruction-tuned for chat in many languages and for function calling. The card calls it a drop-in replacement for Mistral 7B.

The 3.09B-parameter Qwen2.5 chat model that Qwen added for mobile applications. Its license, the Qwen Research License, allows non-commercial research and evaluation only.

The smallest instruction-tuned Qwen2.5 model, with 0.49B parameters and about 32,768 input tokens on Wiro. It suits routing and tagging jobs where the reply is short and the format is fixed.