All vikis
007 First Light
AI
Aion 2
Ananta
ARC Raiders
ArcheAge Chronicles
Call of Duty: Modern Warfare 4
ChatGPT
Chrono Odyssey
Civilization 3
Civilization 4
Crimson Desert
Deadlock
Diablo 4
Diablo 5
Enshrouded
Fable
Final Fantasy Resonance
Football Manager 27
Forza Horizon 6
God of War
Grand Theft Auto 6
Heroes of Might and Magic 3Claude Console
The Claude Console at platform.claude.com is Anthropic's web dashboard for the Claude API, where developers create API keys, test prompts in the playground, organize workspaces, watch usage and rate limits, and buy credits. It was called the Anthropic Console until Sep 2025, and its Workbench became the playground in Aug 2026.
The Claude Console, at platform.claude.com, is where developers sign up for the Claude API, create API keys, try prompts in the playground, manage workspaces and team members, see usage, cost and rate limits, and pay for credits. It is separate from the claude.ai chat app: a Claude Pro or Max subscription does not include API usage through the Console (What is the Pro plan?), and the two bill separately. The Console used to be the Anthropic Console at console.anthropic.com; Anthropic moved its developer products under the Claude name on Sep 16, 2025, and console.anthropic.com has redirected to platform.claude.com since Jan 12, 2026.
Quick facts
| Address | platform.claude.com (sign-in required) |
| API keys | The API keys page; a key starts with sk-ant- and is shown only once |
| Try prompts | Playground, which replaced the Workbench in Aug 2026 |
| Billing | The Billing page: prepaid credits by card, invoices for enterprise (Pricing) |
| Usage and limits | Usage and Rate limits pages |
| Workspaces | Up to 100 per organization by default, plus the Default Workspace |
| Zero data retention | The Console and playground are not covered |
How do you get a Claude API key?
- Sign up or sign in at platform.claude.com.
- Open the API keys page and click to create a key.
- Name it, choose an expiration, pick the linked account (yourself or a service account) and, optionally, a workspace.
- Copy the key at once: it starts with
sk-ant-and the Console shows it only once (Get your Claude API key). - Store it as an environment variable rather than in code:
export ANTHROPIC_API_KEY="your-api-key-here"
Since Aug 27, 2026 there are three kinds of key: a personal key acts as you and stops working if you leave the organization; a service account key belongs to a service account for CI, production or agents; and the old workspace key, a key with no owner, is now legacy. A key not tied to one workspace must send an anthropic-workspace-id header. Lost keys cannot be recovered, only replaced (Get your Claude API key).
For local development, Anthropic now recommends signing in with the ant command-line tool (ant auth login), which opens a browser sign-in to the Console so no key needs to be pasted anywhere (Get started); see Claude API SDKs.
Playground (formerly Workbench)
The playground at platform.claude.com/playground is the Console's prompt tester. Since it replaced the Workbench on Aug 18, 2026, it accepts every Messages API parameter, offers templates (for example with code execution or web search), and shows the full SDK request and raw API response for each run, so a working prompt can be copied straight into code.
Anthropic's notes on the change disagree slightly on dates: a Jul 17, 2026 entry said the experimental prompt generate, improve and templatize APIs would retire "along with the Workbench on August 17, 2026", while the Aug 18 entry announced the playground (Release notes). Older guides that mention the Workbench's prompt generator and prompt improver describe tools that have since been retired with it. For writing good prompts, see Prompting Claude.
Anthropic's Jul 9, 2024 demo shows what those Workbench tools did: the prompt generator turned a one-line task (triaging customer support requests) into a detailed prompt template, Claude wrote realistic test inputs for it, and an Evaluate page ran the prompt over a whole set of test cases, added by hand, generated or uploaded from a CSV, so the results could be graded.
Workspaces, members and roles
Workspaces separate projects, environments or teams inside one organization, each with its own members, keys and limits (Workspaces). Only organization admins can create them, on the Workspaces page. Files and prompt caches are isolated per workspace.
- The Default Workspace cannot be renamed, archived or deleted, and cannot have a spend limit.
- The Claude Code workspace appears automatically when a member first signs in to Claude Code with a Console account; it holds per-user keys, has separate rate limits and is the only workspace with per-user monthly spend limits. Archiving it turns off Claude Code sign-in through Console billing for everyone.
- Workspace roles are Workspace User (playground only), Workspace Limited Developer, Workspace Developer (keys and API) and Workspace Admin; organization admins are admins of every workspace.
Archiving a workspace archives all of its keys within seconds and cannot be undone.
Usage, billing and limits
The Usage page charts tokens, requests and cost, with two rate limit charts showing your peak input and output tokens per minute against your limit and your cache hit rate (Rate limits). The Rate limits page shows your tier and has the Request tier increase button. On Billing you buy credits and can set your own monthly spend limit below your tier's cap. New users get a small amount of free credit to test with (Pricing). See Claude API Rate Limits and Claude API Pricing.
Max, Ultra and Team subscribers can link one Console organization to receive monthly API credits ($100 for Max, $200 for Ultra, pooled seat amounts for Team, as of Nov 6, 2026), which expire at the end of each billing cycle.
Other Console tools
- Capabilities: admins turn the web search and web fetch tools on or off and set domain lists (Web fetch tool); see Web Search and Web Fetch Tools.
- Agent builder and session viewer for Managed Agents: configure an agent's model, prompt, tools, MCP servers and skills visually, test it in an inline session, and inspect past sessions with cost per run (Build in Console).
- Files: the Files API uploads for the workspace.
- Security: IP allowlists (beta since Nov 5, 2026, up to 1,000 entries per organization) limit where a leaked key works.
The status of the Console itself is listed separately on status.claude.com; see Claude Status and Outages.
Frequently asked questions
Is the Claude Console free? Signing up for the Claude Console is free and new accounts get a small amount of test credit; after that, Claude API usage is paid per token with prepaid credits, separately from any claude.ai subscription.
Is the Claude Console the same as claude.ai? No. claude.ai is the Claude chat app sold by subscription, while the Claude Console at platform.claude.com is the developer dashboard for API keys, billing and testing.
Where did the Claude Workbench go? The Claude Workbench became the playground in the Claude Console on Aug 18, 2026, at platform.claude.com/playground; its experimental prompt generator and improver APIs were retired.
I lost my Claude API key. Can I see it again? No. The Claude Console shows a key only once, at creation, and even the Admin API returns only a partial hint, so create a new key and delete the old one.
What was the Anthropic Console? The Anthropic Console at console.anthropic.com is the old name and address of the Claude Console; it now redirects to platform.claude.com.
Sources
- Evaluate prompts in the Anthropic Console, Anthropic, Jul 9, 2024 (video)
- Get your Claude API key, Anthropic docs, read Nov 6, 2026
- Get started, Anthropic docs, read Nov 6, 2026
- Workspaces, Anthropic docs, read Nov 6, 2026
- Rate limits, Anthropic docs, read Nov 6, 2026
- Pricing, Anthropic docs, read Nov 6, 2026
- API credits for Max, Ultra, and Team plans, Anthropic docs, read Nov 6, 2026
- API and data retention, Anthropic docs, read Nov 6, 2026
- Build in Console, Anthropic docs, read Nov 6, 2026
- Web fetch tool, Anthropic docs, read Nov 6, 2026
- Release notes, Anthropic docs, read Nov 6, 2026
- What is the Pro plan?, Claude Help Center, read Nov 6, 2026
- Claude Status, read Nov 6, 2026
Moments
Evaluate prompts in the Anthropic Console
Anthropic
Related
- Claude API PricingClaude API prices are per million tokens, from $0.10 input and $0.50 output on Claude Haiku 5.5 to $10 and $50 on Claude Fable 5.1, with Opus 5.5 at $4 and $20 and Sonnet 5.5 at $2 and $10, as of Nov 6, 2026. Prompt caching and the 50% Batch discount lower that.
- Claude on Cloud PlatformsBesides Anthropic's own Claude API, Claude models are sold through Amazon Bedrock, Claude Platform on AWS, Google Cloud (Google managed or Anthropic managed) and Microsoft Foundry. The Anthropic-operated options get new API features the same day, while Bedrock and Google managed run Claude on the cloud provider's own infrastructure with fewer features.
-
Code Execution ToolThe Claude API's code execution tool runs Bash commands and Python in a sandboxed Linux container at Anthropic, with 5 GiB of memory and no internet access. Each organization gets 1,550 free container hours a month, then $0.05 per hour, and it is free when used with the newer web search or web fetch tools.
-
Computer UseComputer use is a Claude API tool that lets Claude operate a desktop through screenshots, mouse clicks and keystrokes, which your own application carries out. It launched in public beta on Oct 22, 2024 and has been generally available as the computer_toolset_20260801 toolset since Aug 19, 2026.
- Files APIThe Claude Files API stores a PDF, text file, image or dataset once with POST /v1/files and returns a file_id that later Claude API requests reference instead of re-uploading. Files up to 500 MB, 1 TB per organization, free to store; out of beta since Aug 19, 2026.
-
- Message Batches APIThe Message Batches API runs up to 100,000 Claude API requests asynchronously at 50% off the normal price; most batches finish within an hour, every batch within 24 hours, and results stay downloadable for 29 days.
-
Model Context ProtocolThe Model Context Protocol (MCP) is an open standard, introduced by Anthropic on Nov 25, 2024, for connecting AI applications such as Claude to outside tools and data through MCP servers. OpenAI, Google and Microsoft support it, and Anthropic donated it to the Linux Foundation's Agentic AI Foundation on Dec 9, 2025.
See also
-
Claude APIThe Claude API is Anthropic's REST API at api.anthropic.com for building with Claude models: create an API key in the Claude Console at platform.claude.com, then send requests to the Messages API, paying per token.
- Claude API SDKsAnthropic publishes official Claude API SDKs in seven languages (Python, TypeScript, Java, Go, Ruby, C# and PHP) plus the ant command-line tool; the Python SDK installs with pip install anthropic and the TypeScript SDK with npm install @anthropic-ai/sdk. Since Oct 21, 2026 the new major versions are Apache 2.0 licensed.
-
Messages APIThe Messages API is the Claude API's main endpoint, POST /v1/messages: you send a model, max_tokens and a list of user and assistant messages, and Claude returns a message with content blocks, a stop_reason and token usage, whole or streamed.
-
Prompting ClaudeAnthropic's advice for prompting Claude is to be clear and direct, explain why, give three to five examples, separate parts of a prompt with XML tags, set a role, and put long documents before the question.
-
- Claude API Rate LimitsClaude API rate limits are set per organization by usage tier (Start, Build, Scale, Custom) as requests, input tokens and output tokens per minute; on the Start tier Claude Opus 5.5 allows 4,000 requests, 2,000,000 input tokens and 400,000 output tokens a minute. Going over returns a 429 error, while a 529 error means the API itself is overloaded.