Developer Features
One key. Every model.
Point any OpenAI-compatible tool — Cline, Claude Code, or your own apps — at Hicap and reach every major model through one key. No rewrites; reserved capacity at a fraction of the cost when you need it.
Change the base URL. Keep your code.
Using the OpenAI SDK, point the client at api.hicap.ai and add your Hicap API key in the request header. Everything else stays exactly as it is.
Two lines of config.
Same SDK
Keep the OpenAI client you already ship.
Same API calls
chat.completions, embeddings, streaming: unchanged.
Same response format
Nothing downstream needs to know.
const openai = new OpenAI({
apiKey: process.env.OPENAI_API_KEY,
});const openai = new OpenAI({
baseURL: "https://api.hicap.ai/v1",
defaultHeaders: {
"api-key": process.env.HICAP_API_KEY,
},
});const response = await openai.chat.completions.create({
model: "gpt-5.4",
messages: [{ role: "user", content: prompt }],
});
console.log(response.choices[0].message.content);The 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.createQuick test
Verify it in one call.
Drop in your key and confirm the endpoint is live before you wire up your tools.
1curl https://api.hicap.ai/v1/chat/completions \2 -H "api-key: $HICAP_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "gpt-5.4",6 "messages": [7 { "role": "user", "content": "Hello" }8 ]9 }'
Exact steps for your stack.
Focused guides for tools like Claude Code Router, LiteLLM, OpenClaw, and Cline: config examples and the fastest path from API key to working integration.
Go straight to the implementation details.
Every tool-specific setup guide, config example, and reference link lives in the integrations library.
Teams
Bring the whole team.
Volume pricing, shared billing, and dedicated support for your whole engineering team.
