Quickstart
From zero to a frontier model call in 60 seconds.
One OpenAI-compatible endpoint:https://nimbusapi.net/api/v1. Any model from the catalog. Real-time credit accounting. No retry markup, no quota juggling.
Sign in to render snippets with your actual key inline.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_KEY",
base_url="https://nimbusapi.net/api/v1",
)
response = client.chat.completions.create(
model="claude-opus-4-8",
messages=[{"role": "user", "content": "ship it"}],
)
print(response.choices[0].message.content)Catalog
Browse every routed model with live pricing and context window.
Open catalog →Pricing
Pay-as-you-go credit. $5 minimum. No subscription, no expiry.
See pricing →Top up
Add credit via NOWPayments (BTC/LTC/USDC) or Coinbase Commerce.
Add credit →OpenCode
Agent CLI. Drop-in OpenAI-compatible provider.
Open guide →Cursor
Cursor IDE model config.
Open guide →Cline
VSCode autonomous agent.
Open guide →Roo Code
VSCode pair programmer.
Open guide →Python SDK
OpenAI-compatible client against Meridian.
Open guide →TypeScript SDK
OpenAI-compatible client against Meridian.
Open guide →OpenAI & Anthropic SDKs
Drop-in compatibility for existing SDK code.
Open guide →cURL
Raw HTTP examples (chat, SSE, embeddings).
Open guide →Images
Text-to-image generation.
Open guide →Docs Pricing
User_tokens and multipliers.
Open guide →