Tool Use
32 items tagged with "tool-use"
Best Practices2
Model Context Protocol (MCP)
The Model Context Protocol is an open standard that lets AI applications connect to external tools and data sources through a uniform client-server interface.
AI Agent Design Patterns
AI agent design patterns are reusable structures for LLM systems that plan, use tools, and act over multiple steps, covering reflection, tool use, planning, and multi-agent collaboration.
Models22
GPT-6.1 Terra
OpenAI model introduced for fast and capable computer use, with a very large context window available through OpenRouter.
GPT-6.1 Terra Pro
Higher-tier GPT-6.1 Terra variant listed on OpenRouter, intended for capable computer-use and long-context agentic workflows.
Beam 1.0 501B-A23B
Beam is a 501B-parameter open-weight model for agentic coding and long-horizon tasks. It is available through OpenRouter and is also referenced by Hugging Face and AWS as an open model that can be owned, customized, and deployed.
GPT-6
OpenAI's GPT-6 model is rolling out globally in ChatGPT with Intelligent UI, enabling faster responses with visuals and interactive experiences. OpenAI also published a model guide for the GPT-6 family during the tracked date range.
GPT-5.6
OpenAI frontier general-purpose model announced as delivering more intelligence per token, stronger performance per dollar, and scalable capability for demanding work.
Gemini 3.5
Google’s Gemini 3.5 is a new frontier model series focused on combining strong general intelligence with agentic action/tool use, announced at Google I/O 2026.
Gemini 3.5 Flash
A fast, efficient Gemini 3.5-series model variant listed on OpenRouter, intended for low-latency agentic and general assistant workloads with a very large context window.
Claude Opus 4.7 Fast
A latency-optimised variant of Claude Opus 4.7 with a one-million-token context window, designed for real-time agentic workflows, dependency auditing, and large codebase analysis where Opus-class reasoning is required at lower response times.
Grok 4.3
A new Grok-series flagship model variant listed on OpenRouter with a 1M-token context window, aimed at high-context general reasoning and assistant use.
Qwen3.6 Max (Preview)
A preview flagship Qwen3.6 foundation model variant aimed at strong general-purpose reasoning and instruction following with a large context window.
Qwen3.6 Flash
A speed-optimized Qwen3.6 foundation model for low-latency chat and agent workloads while retaining a very large context window.
DeepSeek V4 Pro
DeepSeek’s V4 Pro foundation model listing with a 1M-token context window, intended for long-context reasoning and agentic workloads.
DeepSeek V4 Flash
DeepSeek’s V4 Flash foundation model listing with a 1M-token context window, optimized for lower-latency long-context tasks.
GPT-5.5
OpenAI’s flagship GPT-5.5 model, positioned as faster and more capable for complex tasks like coding, research, and data analysis across tools.
Claude Opus 4.7
A new Claude Opus-series frontier model version listed on OpenRouter with a 1M-token context window, intended for high-end reasoning and long-context workloads.
Claude Opus 4.6 Fast
A faster variant of Claude Opus 4.6 exposed via OpenRouter, aimed at high-throughput production workloads while retaining the Opus-class capability profile.
Gemma 4 31B IT
An instruction-tuned Gemma 4 family model offered via OpenRouter with a very large context window, aimed at general-purpose assistant and agentic workflows.
GPT-5.4
OpenAI frontier foundation model positioned as more capable and efficient for professional work, with state-of-the-art coding, computer use, and tool search, plus a 1M-token context window.
GPT-5.4 Pro
Higher-tier GPT-5.4 offering listed by OpenRouter, providing a 1M-token context window for advanced professional and agentic workloads.
Gemini 3.1 Flash-Lite
Google’s fastest and most cost-efficient Gemini 3 series model, built for intelligence at scale.
Gemini 3.1 Pro Preview (Custom Tools)
A Gemini 3.1 Pro preview variant listed on OpenRouter that is explicitly labeled for custom tools, suggesting enhanced tool-use integration with a very large context window.
Gemini 3.1 Pro Preview
Preview release of Google's Gemini 3.1 Pro model with a very large context window, aimed at advanced general-purpose reasoning and long-context workloads.
Tutorials3
How to build an LLM app with function calling (tools)
Give an LLM the ability to call your functions, so it can fetch data and take actions instead of only producing text.
How to build an AI agent that plans and acts
Build an autonomous LLM agent that uses tools in a perceive-plan-act loop to accomplish multi-step tasks.
How to build a Model Context Protocol (MCP) server
Build an MCP server that exposes tools and resources to AI assistants over a standard protocol.
Benchmarks2
tau-bench (Tool-Agent-User Benchmark)
An agentic benchmark testing tool-using models in simulated customer-service dialogues that require following domain policies and calling APIs correctly.
BFCL (Berkeley Function-Calling Leaderboard)
A benchmark for evaluating how accurately LLMs select, call, and parameterize functions and tools, including parallel, multiple, and multi-turn calling scenarios.
FAQs2
What is an AI agent?
An AI agent is a system that uses a language model to decide and take actions toward a goal, rather than producing a single response. It typically ope...
What is the Model Context Protocol (MCP)?
The Model Context Protocol is an open standard that defines how AI applications connect to external tools, data sources, and services in a consistent ...