API overview

CorvusLLM API base URLs and request paths.

OpenAI-compatible tools use https://base.corvusllm.com/v1. Claude Code and Anthropic-native clients use https://base.corvusllm.com/anthropic.

Before calling the API

You can call CorvusLLM with plain HTTP, so curl is enough for the first check. Install Python or Node.js only if you want to use an SDK instead of raw requests.

What to installOfficial sourceQuick check
CorvusLLM keyBuy or top up balanceSend as a Bearer token.
curlBuilt into most terminals.curl --version
Optional SDK runtimesPython downloads or Node.js downloadUse only for application code.
Local checks
curl --version
python --version
node --version

Zero-to-working setup

Use this block when you want the shortest reliable path from a clean install to one successful HTTP / curl / fetch request through CorvusLLM.

2
Configure

Use a terminal, script, backend service, or fetch-capable runtime that can send HTTPS requests.

  • Use Authorization: Bearer YOUR_CORVUSLLM_KEY
  • Send JSON to https://base.corvusllm.com/v1/chat/completions
3
Verify
  • Run one small curl request with model gpt-5.5
  • Confirm the response and dashboard balance movement before larger tests

A JSON response returns message content and your dashboard balance moves by a small amount.

ValuePaste this
Base URL https://base.corvusllm.com/v1
Endpoint https://base.corvusllm.com/v1/chat/completions
Auth header Authorization: Bearer YOUR_CORVUSLLM_KEY
Starter model gpt-5.5
Setup guardrail

Use this path first when debugging. Do not paste /anthropic into OpenAI-compatible HTTP clients.

Authentication

Use your delivered CorvusLLM key as a Bearer token or the equivalent auth field in the environment you are configuring.

Primary endpoints

Path What it is for
/v1/models List the public customer-facing model lineup.
/v1/chat/completions The main OpenAI-compatible chat path.
/v1/responses Responses API style integration. Keep the first implementation non-stream.
/anthropic/v1/messages Anthropic-native path used by Claude Code and similar tools.

First test request

List models
curl https://base.corvusllm.com/v1/models ^
  -H "Authorization: Bearer YOUR_CORVUSLLM_KEY"

Short answer

Use CorvusLLM like an OpenAI-compatible API when your tool expects a /v1 endpoint. Use the Anthropic-native endpoint only for Claude Code style tools that expect Anthropic message semantics. Do not mix the two paths inside one client configuration.

Independent service boundary

CorvusLLM is an independent AI API proxy. It is not affiliated with OpenAI, Anthropic, Google, or Z.AI. Treat the key as a CorvusLLM key, not as a direct provider account key.

Request shape

The OpenAI-compatible path is the safest first integration path for SDKs, backend apps, scripts, n8n, Open WebUI, ChatBox, and any client that lets you override the base URL. Your app sends the CorvusLLM key in the same place it would normally send an OpenAI API key.

Client typeBase URLAuth fieldModel value
OpenAI SDKshttps://base.corvusllm.com/v1apiKeyPublic CorvusLLM slug
Raw HTTPhttps://base.corvusllm.com/v1Authorization: BearerPublic CorvusLLM slug
Claude Codehttps://base.corvusllm.com/anthropicANTHROPIC_AUTH_TOKENClaude public slug

Common mistakes

  • Do not append /v1 twice. If the SDK asks for a base URL, paste https://base.corvusllm.com/v1 exactly.
  • Do not use /anthropic for OpenAI SDKs. That path is for Anthropic-native clients.
  • Do not invent model names. Copy the public customer slug from Models & Slugs.
  • Do not debug inside a complex app first. Run the model-listing curl command before changing app code.

Balance rule

If the key has no balance left, the API stops with 429 out of balance. It does not silently continue spending. Check the personal dashboard after a small test request if you need to confirm that usage is being deducted from the expected key.

Quickstart

Move from delivered key to first working request with the shortest setup path.

 After you buy

Confirm key delivery, dashboard balance, first request behavior, and top-up flow.

 OpenAI SDK setup

Configure Node.js, Python, or other OpenAI-compatible clients.

 Claude Code setup

Use the Anthropic-native path for Claude Code style clients.

 Model slugs

Copy the exact customer-facing slug before testing a request.

 Billing and cache

Understand prepaid balance, cache reads, cache writes, and 429 behavior.

 Troubleshooting errors

Diagnose auth, base URL, model slug, balance, image, tool, and streaming issues.

 OpenAI-compatible API page

Buyer-facing service overview, pricing entry points, and independent-service disclosures.

 Pricing tracker

Compare current public CorvusLLM model rates with source-linked official rates.

 Trust Center

Review data handling, no-SLA boundary, support expectations, and provider affiliation notes.
Topic map

Continue with the right source

Open the exact setup, model, billing, and troubleshooting pages instead of guessing configuration values.

docs Set up CorvusLLM without guessing. Overview: The clean start page: base URLs, model overview, environment overview, and where to begin. docs Use the canonical customer slug and keep it simple. Models & Slugs: Every customer-facing model with one customer slug, provider family, pricing. docs Most CorvusLLM issues are the same four mistakes. Troubleshooting: Clear fixes for wrong base URLs, bad model slugs, out-of-balance errors, delivery questions. trust Trust Center The Trust Center explains affiliation, data handling, support, refunds, compatibility evidence, pricing methodology. trust How to Verify CorvusLLM Before You Buy The verification checklist shows how to test CorvusLLM claims, endpoint setup, pricing data, status, legal pages. trust Proof of Operations Proof of Operations collects public evidence assets, published data, operational boundaries. status Checking current status The status page shows customer-facing live checks for website, checkout, customer login, and API compatibility routes. faq Frequently Asked Questions CorvusLLM FAQ and help center with searchable answers about pricing, refunds, delivery, API setup, Cursor, Claude Code. docs Buy, paste, test, and verify your balance in minutes. Quickstart: The shortest safe path from purchase to a working request and a visible balance in the dashboard. docs bills against the customer key balance and stops at zero. Billing, Balance & Cache: How prepaid balance works, how same-key top-ups work, how usage deductions, out-of-balance behavior. docs Choose the path once, then stay consistent. Environment Overview: Every supported environment at a glance: which base URL to use, where to paste the key. models AI Models The CorvusLLM model catalog directory helps users find current customer-facing model families, public slugs, pricing context.
Browse docs
On this page