Skip to main content
OmniaKey is a coding-first LLM gateway. One API key gives your coding agent — Claude Code, Cursor, Codex, Cline, aider — access to curated Claude, GPT, and Gemini models from Anthropic, OpenAI, and Google. You pay per token against a prepaid balance, with no monthly fee and no plan tiers.

Quick Start

First request in 5 minutes

Coding Agents

Set up Claude Code, Cursor, Cline, aider, Codex

Models

Curated Claude, GPT, and Gemini models

Agent Platforms

OpenClaw, Hermes, and other gateways

​
One key, three native protocols

OmniaKey speaks each vendor’s protocol on a single host — https://api.omniakey.com. Point your tool at the protocol it already uses; no SDK changes required.
ProtocolBase URLUse it with
OpenAI-compatiblehttps://api.omniakey.com/v1Codex, Cursor, Cline, aider, OpenAI SDKs
Anthropic-nativehttps://api.omniakey.comClaude Code, Anthropic SDKs
Gemini-nativehttps://api.omniakey.com/v1betaGoogle Gen AI SDKs
Claude, GPT, and Gemini ids are reachable over the OpenAI-compatible Chat Completions endpoint (/v1/chat/completions), so most tools need only that one base URL. Reach for a vendor’s native protocol when your tool already speaks it (Claude Code → Anthropic, Google Gen AI SDK → Gemini). See the API Reference for per-protocol curl and SDK examples plus the full protocol × vendor matrix.
The Anthropic SDK appends /v1/messages itself, so its base URL is the bare host. The OpenAI and Gemini SDKs use the /v1 and /v1beta suffixes above.

​
Quick example

Point Claude Code at OmniaKey with two environment variables: 
export ANTHROPIC_BASE_URL="https://api.omniakey.com"
export ANTHROPIC_AUTH_TOKEN="your-omniakey-api-key"
claude
Or use any OpenAI-compatible SDK by changing the base URL: 
from openai import OpenAI

client = OpenAI(
    api_key="your-omniakey-api-key",
    base_url="https://api.omniakey.com/v1",
)

response = client.chat.completions.create(
    model="claude-opus-4-8",
    messages=[{"role": "user", "content": "Refactor this function for readability."}],
)

print(response.choices[0].message.content)
VendorModelContext
Anthropicclaude-opus-4-81M
OpenAIgpt-5.51M
Googlegemini-3.1-pro-preview1M
See Models for the current lineup. Launch pricing is shown on the pricing page.