EN ▾
OpenAI-compatible API, a Claude Code alternativehttps://api.claudecodeapikey.com/v1
Get API key

OpenAI-compatible API, a Claude Code alternative

Claude Code API: an independent guide and a drop-in alternative

A direct, OpenAI-compatible API for coding tools, an alternative to Claude Code, that removes content refusals, letting your coding agents generate code without unnecessary blocks.

  • Pay-as-you-go credit, no monthly fees
  • 100,000 token context window
  • Instant trial key, no card needed

Try it in one request

curl https://api.claudecodeapikey.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Write a blunt product review of a cheap VPN."}]
  }'

Not Claude and not affiliated with Anthropic: one uncensored open-weight model, OpenAI-compatible API, one price. Claude Code can't connect directly: it needs a local translator such as LiteLLM.

per 1M input tokens
$0.15
Output tokens / 1M
$0.50
token context
100,000
trial credit
$0.50
requests per minute
300

What you get

  • OpenAI-Compatible Endpoint

    Works with the official OpenAI SDKs and any OpenAI-compatible client by changing base_url and the API key. Supports streaming via SSE and tool/function calling.

  • Uncensored Model

    An open-weight model tuned to answer without content refusals for lawful adult use. It is NOT GPT, Claude, Gemini, Grok, DeepSeek or any other vendor's model.

  • Transparent Pricing

    $0.15 per 1M input tokens and $0.50 per 1M output tokens. Paid credit never expires and no subscription is required.

  • Instant Access

    New users get $0.50 of trial credit, one per person, valid for 7 days. Claim this credit with one click on your API key page. No phone number or card is needed for the trial.

  • Privacy First

    An account needs only an email and a password. Prompts are not used for training.

  • Simple Limits

    300 requests per minute per key with an 8 MB request body. One key per account that can be regenerated at any time.

How it works

  • Create Account

    Sign up with an email and password on the Get API key page.

  • Receive Key

    Your API key is shown immediately after signup.

  • Configure Tool

    Update your base_url and API key in your coding agent settings.

What people build with it

  • Aggressive Code Generation

    Generate large blocks of code without the model refusing to output based on content filters. Ideal for rapid prototyping where style matters less than volume.

  • Security Research

    Ask the model about controversial topics or edge cases in security without hitting unnecessary refusals. Useful for analyzing code in sensitive contexts.

  • High-Volume Sessions

    Run extended coding sessions with high token usage without worrying about monthly caps. Pay only for what you use with prepaid credit.

  • Custom Agent Integration

    Integrate an uncensored LLM into custom coding agents that need tool calling support. Works seamlessly with existing OpenAI-compatible workflows.

Why Use an Uncensored API for Coding?

Standard coding APIs often refuse to generate code for certain topics, even if the code itself is perfectly valid. This API serves an uncensored large language model that removes these content refusals. It is tuned to answer without blocking lawful adult, fictional, security-research, or controversial topics. This means your coding agent can generate code for any domain without interruption.

The model is an open-weight model run on our own GPU servers. It is not GPT, Claude, Gemini, Grok, DeepSeek, or any other vendor's model. It is a dedicated service for developers who want predictable, uncensored output for their coding tasks. You get text in and text out with full support for streaming and function calling.

OpenAI-Compatible Compatibility

This API is designed to work as a drop-in replacement for the OpenAI API. You can use it with Claude Code, Cursor, Codex, and any other tool that supports OpenAI-compatible endpoints. Simply update the base_url to https://api.claudecodeapikey.com/v1 and provide your API key. The endpoint supports POST /v1/chat/completions with streaming via SSE and tool/function calling.

The model id to send is "uncensored". It handles a context window of 100,000 tokens, which covers both prompt and completion. It does not support embeddings, image, audio, or video generation, nor does it offer fine-tuning. This is a focused text API for coding agents that need reliability and freedom from content filters.

Pricing: Pay-As-You-Go

We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. There are no monthly fees or subscriptions. You preload credit and pay only for what you use. The credit never expires, so you can use it whenever you need it. Top-ups start from $20 by crypto (USDT on TRC20, USDC on Base). You also get bonus credit: +5% from $50, +10% from $100, and +15% from $200.

This model is ideal for high-volume coding sessions where costs can add up quickly. You avoid the risk of overage fees or hitting a monthly cap. It is not for you if you need a free unlimited tier or specific SLA percentages. It is also not for you if you need model routing between vendors or on-prem deployment. We are an independent service, not a reseller of Anthropic or OpenAI.

Instant Trial Key

New users get $0.50 of trial credit, one per person, valid for 7 days. Claim this credit with one click on your API key page. No card is needed to start. You sign up with an email and password on the Get API key page. The key is shown immediately after signup. You can regenerate the key at any time, which revokes the old one. There is one key per account.

Privacy is simple: an account needs only an email and a password. Prompts are not used for training. The hard content limit that always applies is no sexual content involving minors; requests of that kind are blocked. You can test the API with a simple curl request to ensure it works with your setup before committing to a top-up.

Questions and answers

Is this the official Anthropic API?

No, we are an independent service. We serve an uncensored open-weight model that is not GPT, Claude, Gemini, Grok, DeepSeek, or any other vendor's model. We are not Anthropic, OpenAI, or Cursor. We provide a compatible endpoint for tools that already support OpenAI-compatible APIs.

Does the trial credit expire?

The $0.50 trial credit is valid for 7 days from account creation. Claim this credit with one click on your API key page. Paid credit does not expire. You can top up from $20 by crypto (USDT on TRC20, USDC on Base). There are no monthly fees or subscriptions.

Can I use this with Cursor or Claude Code?

Yes, this API is OpenAI-compatible. You can configure it as a custom endpoint in Cursor, Claude Code, or any other OpenAI-compatible client. Update the base_url to https://api.claudecodeapikey.com/v1 and use the model id "uncensored".

What are the request limits?

You are limited to 300 requests per minute per key. The request body size is limited to 8 MB. You get one key per account, which can be regenerated at any time to revoke the old one.

Is my data used for training?

No, prompts are not used for training. An account needs only an email and a password. We are transparent about our operations and do not claim certifications like SOC2 or HIPAA. We focus on providing a reliable, uncoded text API for coding tasks.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API key