Use this API gateway for my agent setup:
API key: XPT_KEY
Base URL: https://api.xphantomtroupe.com/v1
Default model: gpt-5.4
Coding model: gpt-5.3-codex
Fast model: gpt-5.4-mini
Please detect my tool config
(OpenClaw, Hermes Agent, Codex, Continue.dev, or any OpenAI-compatible client),
update the environment variables/config files,
run a small test request,
and tell me exactly what changed.GPT API gateway
One API. GPT 5.5 Model. No VPN. Fuel your OpenClaw agents at a fraction.
Access supported OpenAI GPT models and agent workflows through one OpenAI-compatible gateway with quota control, sticky sessions, billing, and observability.
GPT model routes4
Supported agentsOpenClaw+
Sticky sessionsEnabled
BillingRealtime
AccessNo VPN needed
Mission Briefing
Mission Deployment: 30-Second Agent Setup.
For people who hate manually editing .env files. Copy this mission brief into OpenClaw, Hermes, Codex, Continue.dev, or any agent that can edit config. Replace the placeholder key, then let the agent set the OpenAI-compatible base URL for you.
Get key
Create your key from the xPHANTOM dashboard.
Paste prompt
Replace XPT_KEY, then send the prompt to your agent.
Let it patch
Your agent updates config, tests the route, and reports back.
Model discovery
Supported OpenAI GPT models
The catalog is intentionally tight: GPT and Codex routes only, with latency and capability tags exposed before you send traffic.
OAIfast
gpt-5.5
OpenAI
ReasoningTool callingFlagship
OAIfast
gpt-5.4
OpenAI
GeneralFastTools
CDXagent-grade
gpt-5.3-codex
Codex
CodingAgentsLong tasks
OAIinstant
gpt-5.4-mini
OpenAI
FastCheapUtility
Supported agent
Use xPHANTOM where your agents already run
OpenClaw, Hermes Agent, Codex, local runners, and custom OpenAI-compatible agents can all point at the same API key and base URL.
Coding agent
Use with APIOpenClaw
Use xPHANTOM as the OpenAI-compatible backend for planning, code edits, and repo automation.
OpenAI-compatible base URL
Autonomous agent
Use with APIHermes Agent
Run Hermes sessions through GPT routes with sticky sessions, quota, and balance controls.
GPT · sticky session
Code generation
Use with APICodex
Point Codex-style coding flows at GPT and Codex routes without changing your agent surface.
GPT · Codex
Local runner
Use with APIOpenCode
Use the same API key for local agent runs, reviews, refactors, and terminal workflows.
Local · OpenAI-compatible
IDE assistant
Use with APIContinue.dev
Configure xPHANTOM as the OpenAI-compatible backend for IDE chat and inline code work.
IDE · GPT
Custom tools
Use with APIOther agents
Any runner that accepts an OpenAI base URL can join the same quota, billing, and routing layer.
Bring your own agentDeveloper controls
Controls for running GPT routes in production
A gateway is useful when you can see what happened, what it cost, and which limits were applied.
Unified API
OpenAI-compatible `/v1/chat/completions` endpoint for GPT models and agent clients.
Sticky sessions
Keep a conversation on the same account, key, or route lane when continuity matters.
Real-time billing
Track spend, token usage, and remaining balance as requests move.
Quota controls
Set account, project, model, and agent limits before usage runs away.
GPT account routing
Balance multiple OpenAI account pools behind one stable gateway.
Channel health
See route status, latency, failover state, and account availability.
Pricing
Start small, scale into reserved GPT routing
Plans are powered by pricing.json, so quota and prices can be adjusted without touching layout code.
Recruit
HK$50/mo
- 500K token
- Concurrency 1
- gpt-5.4
Spider
HK$200/mo
- 3M token
- Concurrency 3
- gpt-5.4 · gpt-5.5
Magician
HK$500/mo
- 10M token
- Concurrency 10
- gpt-5.5 · gpt-5.3-codex
Boss
Contact us
- Unlimited
- Concurrency ∞
- custom GPT pool · priority failover · reserved quota
The Spider never sleeps. Connect your agent and let the network handle the rest.
