How it worksModelsDevelopersBusinessDocs
Contact SalesSupportGet Started

Built for
Developers

One API key. Every model. Plug Hicap into any tool that supports a custom endpoint—Cline, Claude Code, your own apps—and get reserved GPU capacity at a fraction of the cost.

Get StartedDocumentation

Developer Tools Integration

Connect your existing development workflow to Hicap's reserved GPU capacity for faster, more cost-effective AI inference.

Claude Code Router

Use the Claude Code router to set up Hicap as a provider on Claude Code and access models across different families—OpenAI, Anthropic, Google, and more.

  1. 1Install Claude Code and Claude Code Router globally
  2. 2Create config at ~/.claude-code-router/config.json
  3. 3Set Hicap as the provider with api.hicap.ai/v1 endpoint
  4. 4Run 'ccr start', then 'ccr code' to begin

Cline VS Code & CLI

Hicap is a registered provider with Cline, available on both the Cline VS Code extension and the Cline CLI. Use your BYOK API key to access Hicap deals, performance, and reliability benefits.

  1. 1Install the Cline extension for VS Code
  2. 2Select 'BYOK' as the API provider
  3. 3Choose 'Hicap' from the provider dropdown
  4. 4Paste your Hicap API key
View Setup Guide→

OpenClaw

Use your Hicap API key with OpenClaw, a powerful OpenAI-compatible provider. Hicap routes your requests through our reserved capacity while maintaining full security and control.

  1. 1Install OpenClaw provider integration
  2. 2Set baseURL to 'https://api.hicap.ai/v1'
  3. 3Set the 'api-key' header with your Hicap API key
  4. 4Start using OpenClaw with Hicap's reserved GPU capacity

Simple Application Integration

Using the OpenAI SDK, just change the base URL and add your Hicap API key in the request header.

Two-Line Migration

Swap out your OpenAI client config—everything else stays the same. Same SDK, same API calls, same response format.

// Before — direct OpenAI
const openai = new OpenAI({
  apiKey: process.env.OPENAI_API_KEY,
});
// After — Hicap
const openai = new OpenAI({
  baseURL: "https://api.hicap.ai/v1",
  defaultHeaders: {
    "api-key": process.env.HICAP_API_KEY,
  },
});
// Your code stays exactly the same
const response = await openai.chat.completions.create({
  model: "gpt-5.4",
  messages: [{ role: "user", content: prompt }],
});

console.log(response.choices[0].message.content);

AI Migration Prompt

Paste this prompt into your AI coding assistant to migrate your entire project in one go:

Migrate this project from OpenAI direct to Hicap.

Find all OpenAI SDK client initializations and update them to use Hicap:

Required changes:
1. Set baseURL to "https://api.hicap.ai/v1"
2. Add "api-key" header with the Hicap API key
3. Remove any existing apiKey or Authorization headers

The Hicap client config should look like:
{
  baseURL: "https://api.hicap.ai/v1",
  defaultHeaders: { "api-key": <your-hicap-key> }
}

Also:
- Add HICAP_API_KEY to environment variables (.env, .env.example, etc.)
- Update any config files, constants, or helper functions that create OpenAI clients
- Keep all API calls unchanged (chat.completions.create, embeddings, etc.)
- Search for patterns like: new OpenAI, createOpenAI, OpenAIClient, openai.create

Quick Test with CURL

curl https://api.hicap.ai/v1/chat/completions \ -H "Content-Type: application/json" \ -H "api-key: $HICAP_API_KEY" \ -d '{"model":"gpt-5.4","messages":[{"role":"user","content":"Hello"}]}'

Scaling your team?

Get volume pricing, shared billing, and dedicated support for your engineering team. We'll set up everything you need.

Get StartedContact Sales