New Ora Setup Guide
Install your API access in minutes using the setup command from your order delivery message. Works with Claude Code CLI and Codex CLI-compatible tools.
Before you start
- You have an active New Ora order.
- You have the setup command sent after your order is prepared.
- You will run the command in your terminal (PowerShell / Terminal).
- After setup, run Claude Code CLI from your project folder.
Windows PowerShell setup
One-line install using the setup token from your delivery message.
irm "https://newora.space/api/v1/setup?token=YOUR_API_KEY" | iex- Open Windows PowerShell.
- Paste the setup command from your delivery message.
- Press Enter and wait for New Ora Setup to finish.
- Confirm the setup output shows Customer token installed, OPENAI_API_KEY / OPENAI_BASE_URL configured, Package active, Connection test successful, Usage tracking enabled.
- Open your project folder and run
claude.
macOS / Linux setup
Terminal one-liner using the setup token from your delivery message.
curl -fsSL "https://newora.space/api/v1/setup?token=YOUR_API_KEY" | sh- Open Terminal.
- Paste the macOS/Linux setup command from your delivery message.
- Press Enter and wait for setup to finish.
- Restart your terminal if needed.
- Open your project folder and run
claude.
Manual API setup
For tools that need OpenAI-compatible provider configuration.
https://newora.space/ol/v1Claude Code CLI usage
After setup, launch Claude Code from your project folder.
- Go to your project directory.
- Run
claude. - Send a quick test message such as
hello. - If the assistant replies, setup is working correctly.
Codex CLI usage
Codex-compatible tools use standard OpenAI environment variables.
Configure your Codex-compatible tool with:
OPENAI_API_KEY— installed by your setup commandOPENAI_BASE_URL—https://newora.space/ol/v1
Or configure a manual OpenAI-compatible provider using the same Base URL.
How to verify setup
Expected output from a successful setup run.
New Ora Setup
Gateway: https://newora.space/ol/v1
Order: G2G-123456
Package: Your package name
Daily: $250.00 allowance
Status: Active
Expires: 2026-12-01
Token: sk-newora-...A92F
[OK] OPENAI_API_KEY configured
[OK] OPENAI_BASE_URL configured
[OK] ANTHROPIC_BASE_URL configured
[OK] Package active
[OK] Connection test successful
Done! Run 'claude' in any project directory.Common setup problems
Most issues fall into one of these five buckets.
- setup token expired
- order access expired
- copied wrong command
- customer access disabled/suspended
Regenerate setup from support/admin. Contact support with your order number.
- internet issue
- package expired
- temporary provider issue
- wrong terminal command
Retry after a few minutes. Verify the command. Contact support if it persists.
- Claude Code CLI is not installed
Install Claude Code CLI separately. New Ora setup only configures API environment variables.
- terminal not restarted after setup
Restart your terminal. Rerun the setup command. Verify environment variables.
- suspected sharing or abuse
Open a support ticket with your order number. Support remains available for suspended users.
Allowance, models & error codes
How the daily USD allowance is enforced and what to expect when it runs out.
Every package includes all available models (Claude Opus 5 / 5.5, Sonnet, Haiku, GPT-6, Fable 5, GLM, MiniMax, DeepSeek). Unknown model names return 400 unsupported_model.
Your package has one daily USD allowance shared by all models. Each request's cost is calculated from the tokens it used and the model's price. When the allowance is used up, new requests return 429 quota_exceeded until it resets. The allowance resets 24 hours after your first sign-in and every 24 hours after that — you can see the exact time on your Usage page.
401 unauthorized— API key missing or invalid.403 access_expired— package expired.403 access_suspended— key suspended.400 unsupported_model— model name not recognised.429 quota_exceeded— daily USD allowance used up; resets automatically.503 pool_unavailable— service temporarily unavailable — try again shortly.502 provider_error— upstream provider returned an error.
OpenAI-compatible chat/completions endpoints support streaming (stream: true). Both streamed and non-streamed calls are billed the same and count against the same daily USD allowance.
Your API key is treated as a secret — never commit it, share it, or paste it in support chats. Upstream provider keys are managed server-side and never exposed to customers.
Still stuck?
Open a support ticket with your order number and we'll take it from there.
