Developer console and API keys for the Claude model family
The Anthropic Console is the developer home for Claude models: you create an API key, pick a model, and send prompts from your own code. It includes a workbench for drafting and comparing prompts, token counting and prompt caching controls that change what a request costs, a batch API for large asynchronous jobs, and dashboards for usage, rate limits and spend. There is no ongoing free API tier, so every experiment bills by token, and the console is tooling rather than a chat product for end users. Teams come here to put Claude inside an application instead of a browser tab.
Last updated: 2026-09-20. This site only provides an index; for exact features, pricing, and licensing, see the official website.
llm app development, prompt engineering, api integration and cost monitoring
If you're comparing similar products, check the alternatives below, or browse all tools in the AI Models & Platforms category.
API keys, a prompt workbench for testing requests, usage and spend dashboards, and documentation of model capabilities, limits and pricing. You still write the application yourself; the console is where you obtain access and check how prompts behave.
Access is pay-per-token, with only limited trial credit rather than an ongoing free tier. Budget a small amount for evaluation, set spend limits early, and watch caching and batch options because both change the effective cost per request.
The console is for developers building on the API: keys, billing, prompt testing and logs. The chat app is a finished product for end users. If you only want to talk to Claude, you do not need the console at all.
Node-based local interface for running image and video diffusion models
Browser playground for prompting and prototyping with Gemini models
Hosted Jupyter notebooks with optional free GPU and TPU runtimes
Where most of the open machine learning world lives