# ClaudeAPIKey.dev Documentation > Anthropic-compatible API gateway. Base URL: https://aiprimetech.io ## Getting started - [Introduction](https://aiprimetech.io/docs/getting-started/introduction/) — What ClaudeAPIKey.dev is, which endpoints it speaks, and how it differs from calling Anthropic directly. - [Quickstart](https://aiprimetech.io/docs/getting-started/quickstart/) — Get a key, set two environment variables, and make your first request in about a minute. - [Authentication](https://aiprimetech.io/docs/getting-started/authentication/) — How to send your key, which header each format expects, and how to keep keys safe. - [Models](https://aiprimetech.io/docs/getting-started/models/) — Every model id you can call, its context window, and what it costs per million tokens. - [Base URLs](https://aiprimetech.io/docs/getting-started/base-urls/) — The one setting that trips everyone up: which URL each client expects, with and without the /v1 suffix. - [Your first request explained](https://aiprimetech.io/docs/getting-started/first-request/) — A line-by-line walkthrough of one Messages call — what every field does and what comes back. ## API reference - [API overview](https://aiprimetech.io/docs/api-reference/overview/) — Every endpoint the gateway exposes, which format it speaks, and what it returns. - [Messages API](https://aiprimetech.io/docs/api-reference/messages/) — POST /v1/messages — the Anthropic-format endpoint: parameters, response shape and examples. - [Chat Completions API](https://aiprimetech.io/docs/api-reference/chat-completions/) — POST /v1/chat/completions — the OpenAI-format endpoint, for Cursor, LangChain, LiteLLM and the OpenAI SDKs. - [Models endpoint](https://aiprimetech.io/docs/api-reference/models-endpoint/) — GET /v1/models — discover exactly which model ids your key can call. - [Streaming](https://aiprimetech.io/docs/api-reference/streaming/) — Server-sent events in both formats — the event shapes differ, and mixing them up reads as silence. - [Errors](https://aiprimetech.io/docs/api-reference/errors/) — Every status code the gateway returns, what actually causes it, and the fix. - [Rate limits](https://aiprimetech.io/docs/api-reference/rate-limits/) — How throttling works, what a 429 means here, and how to build a client that does not trigger one. - [Tool use and function calling](https://aiprimetech.io/docs/api-reference/tool-use/) — Let a model call your functions — the request loop, both formats, and the mistakes that cost tokens. - [Vision and image input](https://aiprimetech.io/docs/api-reference/vision/) — Send images to multimodal models — encoding, size limits, and what it costs. ## Integration guides - [Claude Code](https://aiprimetech.io/docs/guides/claude-code/) — Point Anthropic's CLI agent at the gateway with two environment variables — and avoid the one trap that silently bills the wrong key. - [Cursor](https://aiprimetech.io/docs/guides/cursor/) — Use Claude models inside Cursor through the OpenAI-compatible endpoint, without an Anthropic account. - [Cline](https://aiprimetech.io/docs/guides/cline/) — Configure the Cline VS Code extension against the Anthropic-format endpoint. - [Aider](https://aiprimetech.io/docs/guides/aider/) — Run the terminal pair-programmer against the gateway in either wire format. - [Zed](https://aiprimetech.io/docs/guides/zed/) — Add the gateway as a custom assistant provider in the Zed editor. - [Continue](https://aiprimetech.io/docs/guides/continue/) — Configure the Continue extension for VS Code and JetBrains. - [VS Code extensions](https://aiprimetech.io/docs/guides/vscode-extensions/) — Which VS Code AI extensions accept a custom base URL, and how to point each at the gateway. - [JetBrains IDEs](https://aiprimetech.io/docs/guides/jetbrains/) — IntelliJ IDEA, PyCharm, WebStorm, GoLand and the rest — via Continue or an OpenAI-compatible plugin. - [OpenCode](https://aiprimetech.io/docs/guides/opencode/) — Point the open-source terminal coding agent at the gateway. - [Codex CLI](https://aiprimetech.io/docs/guides/codex-cli/) — Run OpenAI's Codex CLI and the Codex extension against the gateway. - [OpenClaw](https://aiprimetech.io/docs/guides/openclaw/) — Configure the OpenClaw agent framework to use gateway models. - [MCP servers for Claude Code](https://aiprimetech.io/docs/guides/mcp-servers/) — A Model Context Protocol config that earns its place, plus the traps that cost real time. - [API key configuration by tool](https://aiprimetech.io/docs/guides/api-key-configuration/) — One table: where each client expects the key and the base URL, with the /v1 suffix spelled out. ## Working with the API - [Cost control](https://aiprimetech.io/docs/guides/cost-control/) — Where the tokens actually go in an agentic workload, and the four levers that move the bill. - [Prompt caching](https://aiprimetech.io/docs/guides/prompt-caching/) — Re-read a stable prefix at a fraction of the input price — what to cache, what not to, and how to verify it worked. - [Context management](https://aiprimetech.io/docs/guides/context-management/) — Why long sessions get expensive non-linearly, and the patterns that keep history bounded. - [Migrating from the Anthropic API](https://aiprimetech.io/docs/guides/migration-from-anthropic/) — Move an existing Anthropic-SDK codebase over by changing two values. - [Migrating from the OpenAI API](https://aiprimetech.io/docs/guides/migration-from-openai/) — Keep the OpenAI SDK and reach Claude models by changing the base URL. - [Production best practices](https://aiprimetech.io/docs/guides/best-practices/) — What to get right before an integration carries real traffic. - [Troubleshooting](https://aiprimetech.io/docs/guides/troubleshooting/) — Symptom-first index — find what you are seeing and jump to the cause. ## SDKs - [SDKs overview](https://aiprimetech.io/docs/sdks/) — Official Anthropic and OpenAI SDKs both work unmodified — pick by which format you prefer. - [Python](https://aiprimetech.io/docs/sdks/python/) — Working examples with the anthropic and openai packages, including streaming and async. - [TypeScript](https://aiprimetech.io/docs/sdks/typescript/) — Node examples with @anthropic-ai/sdk and openai, including streaming. - [cURL](https://aiprimetech.io/docs/sdks/curl/) — Dependency-free examples for every endpoint — useful for debugging and CI checks. - [Go](https://aiprimetech.io/docs/sdks/go/) — Call the gateway from Go with the standard library — no third-party client needed. ## Billing - [Pricing](https://aiprimetech.io/docs/billing/pricing/) — How credits convert to tokens, what the bonuses are, and how to work out the cost of a task. - [Credits](https://aiprimetech.io/docs/billing/credits/) — How the prepaid balance works, what draws it down, and how to avoid running dry mid-run. - [Unlimited plans](https://aiprimetech.io/docs/billing/plans/) — Flat-rate access for a fixed window — what they include and when they beat credits. - [Payment methods](https://aiprimetech.io/docs/billing/payment-methods/) — Card and crypto — which to use, and why the bonus differs. - [Refunds and support](https://aiprimetech.io/docs/billing/refunds/) — What can be refunded, what cannot, and how to raise a billing issue. ## Resources - [FAQ](https://aiprimetech.io/docs/resources/faq/) — Direct answers to the questions we are actually asked. - [Glossary](https://aiprimetech.io/docs/resources/glossary/) — The terms used throughout these docs, defined precisely. - [Security and privacy](https://aiprimetech.io/docs/resources/security/) — How to handle keys, what to avoid sending, and the boundaries of this service. - [Changelog](https://aiprimetech.io/docs/resources/changelog/) — Notable changes to the API surface, models and documentation. - [Status and reliability](https://aiprimetech.io/docs/resources/status/) — How the gateway handles upstream failures, and what to do when something is degraded. - [Availability and payment methods](https://aiprimetech.io/docs/resources/supported-countries/) — Where the service can be used, and how to pay when card networks are unavailable.