# AI Prime Tech — Multi-Model AI API Gateway (Claude, GPT, Gemini) > aiprimetech.io is an independent AI API gateway providing instant access to Anthropic Claude (Opus, Sonnet, Haiku, Fable), OpenAI GPT/Codex, Google Gemini, and open models (MiniMax, DeepSeek, Qwen) through a single API key. Anthropic-compatible (`/v1/messages`) and OpenAI-compatible (`/v1/chat/completions`) endpoints. Pay-as-you-go at competitive token rates, no Anthropic account required. Works with Claude Code, Cursor, Cline, Codex CLI, and any standard SDK. ## What it is A unified, multi-provider AI gateway for developers and ML engineers. One key, one balance, every major model. Built for production: failover across upstream channels, prompt caching, and a clean OpenAI/Anthropic-compatible surface so you can switch models without rewriting code. ## For LLM agents Every blog post and model page is also available as clean Markdown — append `.md` to the URL. Examples: - https://aiprimetech.io/blog/claude-api-pricing-guide-2026.md - https://aiprimetech.io/models/claude-fable-5.md - https://aiprimetech.io/models.md (model catalog) ## Key Facts - **Website**: https://aiprimetech.io - **API Base URL**: https://aiprimetech.io - **API Formats**: Anthropic Messages API (`/v1/messages`), OpenAI Chat Completions (`/v1/chat/completions`), OpenAI Responses API (`/v1/responses`) for Codex - **Claude models**: Opus 4.8, Sonnet 4.6, Haiku 4.5, Fable 5 (1M context) - **Other models**: OpenAI GPT-5.x / Codex, Google Gemini, MiniMax-M3, DeepSeek, Qwen - **Billing**: prepaid pay-as-you-go at competitive per-token rates - **Payment**: card and cryptocurrency (BTC, ETH, USDT) - **Signup**: instant, no Anthropic/OpenAI account required - **Regional access**: worldwide, no geographic restrictions - **Setup**: point your Claude Code / Cursor / Codex / SDK at the base URL with your API key ## Pages - [Home](https://aiprimetech.io/) — Multi-model AI gateway overview, models, pricing, FAQ - [Models](https://aiprimetech.io/models/) — Model IDs, context sizes, per-model pricing ([.md](https://aiprimetech.io/models.md)) - [Learn](https://aiprimetech.io/learn/) — Buyer guides: get a key, pricing, Cursor/Cline/Claude Code setup, crypto payment - [Blog](https://aiprimetech.io/blog/) — AI engineering, LLM inference, API cost, and model news - [Docs](https://aiprimetech.io/docs/) — API documentation and integration guides - [Login](https://aiprimetech.io/login) — Dashboard sign-in - [Get API Key](https://aiprimetech.io/register) — Create an account and generate a key ## Learn Buyer-focused guides on getting and using a Claude API key — setup, pricing, tools, and integrations. - [How to Get a Claude API Key](https://aiprimetech.io/learn/how-to-get-a-claude-api-key/) - [Claude API Pricing Explained](https://aiprimetech.io/learn/claude-api-pricing-explained/) - [The Cheapest Way to Use the Claude API](https://aiprimetech.io/learn/cheapest-way-to-use-claude-api/) - [Claude API Gateway vs. Anthropic Direct](https://aiprimetech.io/learn/claude-api-vs-anthropic-direct/) - [Claude API Access Without a Waitlist](https://aiprimetech.io/learn/claude-api-without-waitlist/) - [What 'Unlimited' Claude API Access Means](https://aiprimetech.io/learn/unlimited-claude-api-access/) - [Paying for the Claude API with Crypto](https://aiprimetech.io/learn/claude-api-with-crypto-payment/) - [Claude Models Compared: Opus, Sonnet, Haiku, Fable](https://aiprimetech.io/learn/claude-api-models-compared/) - [How to Reduce Claude Token Usage](https://aiprimetech.io/learn/how-to-reduce-claude-token-usage/) - [What an Anthropic-Compatible API Means](https://aiprimetech.io/learn/anthropic-compatible-api/) - [Using Claude Through an OpenAI-Compatible API](https://aiprimetech.io/learn/openai-compatible-claude-api/) - [How to Use the Claude API with Claude Code](https://aiprimetech.io/learn/use-claude-api-with-claude-code/) - [How to Use the Claude API with Cursor](https://aiprimetech.io/learn/use-claude-api-with-cursor/) - [How to Use the Claude API with Cline](https://aiprimetech.io/learn/use-claude-api-with-cline/) - [How to Use the Claude API with Roo Code](https://aiprimetech.io/learn/use-claude-api-with-roo-code/) - [How to Use the Claude API with Aider](https://aiprimetech.io/learn/use-claude-api-with-aider/) - [How to Use the Claude API in VS Code](https://aiprimetech.io/learn/use-claude-api-with-vscode/) - [How to Use the Claude API in JetBrains IDEs](https://aiprimetech.io/learn/use-claude-api-with-jetbrains/) - [How to Use the Claude API with OpenCode](https://aiprimetech.io/learn/use-claude-api-with-opencode/) - [Running the Hermes Agent on the Claude API](https://aiprimetech.io/learn/run-hermes-agent-with-claude-api/) - [Running OpenClaw on the Claude API](https://aiprimetech.io/learn/run-openclaw-with-claude-api/) ## FAQ highlights - **Which models can I use?** Claude (Opus 4.8 / Sonnet 4.6 / Haiku 4.5 / Fable 5), OpenAI GPT-5.x & Codex, Gemini, and open models (MiniMax-M3, DeepSeek, Qwen) — all through one key. - **Does it work with Claude Code and Cursor?** Yes — set the base URL to https://aiprimetech.io and use your API key. - **Do I need an Anthropic or OpenAI account?** No. Sign up, add credit, generate a key. - **How is billing done?** Prepaid credits, charged per token by model. Credits don't expire while your account is active. ## Documentation Full API documentation. Every page below is also available as Markdown at the same path with a `.md` suffix (for example `https://aiprimetech.io/docs/getting-started/quickstart.md`). - [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. - [Errors](https://aiprimetech.io/docs/api-reference/errors/): Every status code the gateway returns, what actually causes it, and the fix. - [Messages API](https://aiprimetech.io/docs/api-reference/messages/): POST /v1/messages — the Anthropic-format endpoint: parameters, response shape and examples. - [Models endpoint](https://aiprimetech.io/docs/api-reference/models-endpoint/): GET /v1/models — discover exactly which model ids your key can call. - [API overview](https://aiprimetech.io/docs/api-reference/overview/): Every endpoint the gateway exposes, which format it speaks, and what it returns. - [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. - [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. - [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. - [Credits](https://aiprimetech.io/docs/billing/credits/): How the prepaid balance works, what draws it down, and how to avoid running dry mid-run. - [Payment methods](https://aiprimetech.io/docs/billing/payment-methods/): Card and crypto — which to use, and why the bonus differs. - [Unlimited plans](https://aiprimetech.io/docs/billing/plans/): Flat-rate access for a fixed window — what they include and when they beat credits. - [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. - [Refunds and support](https://aiprimetech.io/docs/billing/refunds/): What can be refunded, what cannot, and how to raise a billing issue. - [Authentication](https://aiprimetech.io/docs/getting-started/authentication/): How to send your key, which header each format expects, and how to keep keys safe. - [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. - [Introduction](https://aiprimetech.io/docs/getting-started/introduction/): What ClaudeAPIKey.dev is, which endpoints it speaks, and how it differs from calling Anthropic directly. - [Models](https://aiprimetech.io/docs/getting-started/models/): Every model id you can call, its context window, and what it costs per million tokens. - [Quickstart](https://aiprimetech.io/docs/getting-started/quickstart/): Get a key, set two environment variables, and make your first request in about a minute. - [Aider](https://aiprimetech.io/docs/guides/aider/): Run the terminal pair-programmer against the gateway in either wire format. - [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. - [Production best practices](https://aiprimetech.io/docs/guides/best-practices/): What to get right before an integration carries real traffic. - [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. - [Cline](https://aiprimetech.io/docs/guides/cline/): Configure the Cline VS Code extension against the Anthropic-format endpoint. - [Codex CLI](https://aiprimetech.io/docs/guides/codex-cli/): Run OpenAI's Codex CLI and the Codex extension against the gateway. - [Context management](https://aiprimetech.io/docs/guides/context-management/): Why long sessions get expensive non-linearly, and the patterns that keep history bounded. - [Continue](https://aiprimetech.io/docs/guides/continue/): Configure the Continue extension for VS Code and JetBrains. - [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. - [Cursor](https://aiprimetech.io/docs/guides/cursor/): Use Claude models inside Cursor through the OpenAI-compatible endpoint, without an Anthropic account. - [JetBrains IDEs](https://aiprimetech.io/docs/guides/jetbrains/): IntelliJ IDEA, PyCharm, WebStorm, GoLand and the rest — via Continue or an OpenAI-compatible plugin. - [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. - [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. - [OpenClaw](https://aiprimetech.io/docs/guides/openclaw/): Configure the OpenClaw agent framework to use gateway models. - [OpenCode](https://aiprimetech.io/docs/guides/opencode/): Point the open-source terminal coding agent at the gateway. - [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. - [Troubleshooting](https://aiprimetech.io/docs/guides/troubleshooting/): Symptom-first index — find what you are seeing and jump to the cause. - [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. - [Zed](https://aiprimetech.io/docs/guides/zed/): Add the gateway as a custom assistant provider in the Zed editor. - [Changelog](https://aiprimetech.io/docs/resources/changelog/): Notable changes to the API surface, models and documentation. - [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. - [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. - [SDKs overview](https://aiprimetech.io/docs/sdks/): Official Anthropic and OpenAI SDKs both work unmodified — pick by which format you prefer. - [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. - [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.