// PRODUCTION ENDPOINT

One key. Every frontier coding API.

Pay-as-you-go gateway. No SMS verification. Instant API key. Drop-in compatible with Claude Code, Codex CLI, Cursor, Cline, and major SDKs.

No SMS or ID check Key issued instantly Pay per token
ENDPOINT STATUS:ONLINE
HOST:r-8g8.qcode.cc
PROTO:https / 1.1 + 2
SSE:supported
// WHY THIS GATEWAY

Everything you need, nothing you don't

One key routes Claude, GPT / Codex, and leading coding models through native protocols — with usage you can watch and billing you can predict.

⚡

Pay-as-you-go

No subscription, no minimums. Top up any amount, use what you need.

🔑

Instant key

Get your API key right after payment. No KYC, no waiting, no SMS.

🛰

Dual native protocols

Anthropic Messages + OpenAI Responses & Chat Completions — single key, smart routing.

📊

Live usage stats

Check spend and quota any time on the stats page with your own key.

⌨

Drop-in compatible

Works with Claude Code, Codex CLI, Cursor, Cline, Continue, LangChain, and OpenAI/Anthropic SDKs.

↯

Streaming + tools

Full SSE streaming and tool-use support — same wire format as official APIs.

// GET STARTED

Live in three steps

From zero to your first request in a couple of minutes.

Get your key

Top up and receive an API key instantly — no identity check, no waiting.

Point your tool at the gateway

Change the base URL and paste your key. Your existing SDK or CLI keeps working.

Ship

Call Claude, GPT-6.2, GLM, Kimi, DeepSeek, and Qwen through one key. Watch spend live on the stats page.

// PRICING

Pay for what you use

No subscription and no minimum — each request is metered by actual token usage against your prepaid balance.

0

Subscription

No monthly fee and no minimum spend. Top up any amount and draw it down as you go.

Token

Per-token billing

Each request is metered by the tokens it actually uses; unit prices vary by model.

6+

Model families, one key

Claude, GPT / Codex, GLM, Kimi, DeepSeek, and Qwen billed together against a single balance.

24/7

Live balance

Every request is metered in real time. Check remaining quota any moment on the stats page.

Need volume rates or a custom plan? Talk to us.

// ENDPOINTS

Production endpoints

Compatible with the official wire formats — point your existing SDK at the URL below and use your key.

Claude · Anthropic Messages API
POSThttps://r-8g8.qcode.cc/api/v1/messages
Header: x-api-key: cr_...
Codex · OpenAI Responses API (GPT-6.2 / GPT-6)
POSThttps://r-8g8.qcode.cc/openai/v1/responses
Header: Authorization: Bearer cr_...
OpenAI-Compatible · Chat Completions API (GLM / Kimi / DeepSeek / Qwen)
POSThttps://r-8g8.qcode.cc/openai/v1/chat/completions
Header: Authorization: Bearer cr_...
// QUICKSTART

60-second integration

Set two environment variables, run your existing tool. That's it.

Claude Code
# ~/.bashrc
export ANTHROPIC_BASE_URL="https://r-8g8.qcode.cc/api"
export ANTHROPIC_AUTH_TOKEN="cr_..."
claude
Codex CLI
# ~/.codex/config.toml
[model_providers.provider]
name="provider"
base_url="https://r-8g8.qcode.cc/openai"
env_key="OPENAI_API_KEY"
Cursor / OpenAI SDK
# .env
OPENAI_BASE_URL="https://r-8g8.qcode.cc/openai/v1"
OPENAI_API_KEY="cr_..."

Already using another client? Point its base URL at the gateway and paste your key.

Cursor
Override Base URL → /openai/v1
Cline / Roo Code
Anthropic-compatible → /api
Continue.dev
apiBase → /openai/v1
Chatbox
Custom endpoint → /openai/v1
LangChain
base_url → /openai/v1
OpenAI SDK
baseURL → /openai/v1
Anthropic SDK
base_url → /api
Claude Agent SDK
ANTHROPIC_BASE_URL → /api
// MODEL LINEUP

Models routed through this gateway

Latest production models across vendors — keep your client up to date and new models become available automatically.

Model Context Best for
claude-fable-5-2 anthropic1Mflagship · agent
claude-opus-5-5 anthropic1Mflagship · agent
claude-sonnet-5-5 anthropic1Mcoding · long context
claude-haiku-5-5 anthropic1Mfast · high throughput
claude-fable-5 anthropic1Mflagship · agent
claude-opus-5 anthropic1Mflagship · agent
claude-sonnet-5 anthropic1Mcoding · long context
gpt-6.2-astra openai1.05Mflagship · reasoning
gpt-6.2-sol openai1.05Mflagship · reasoning
gpt-6.1-sol openai1.05Mflagship · reasoning
gpt-6-sol openai1.05Mflagship · reasoning
glm-5.3 zhipu200Kcoding · multi-agent
kimi-k3.1-pro moonshot256Kcoding · multi-agent
deepseek-v4.1-flash deepseek128Kfast · high throughput
qwen3.8-max qwen256Kcoding · multi-agent

Track every request

Enter your key on the stats page to see today's spend, remaining quota, and rate limits — updated live.

Open stats →
// FAQ

Questions, answered

Do I need to verify my identity?
No. There's no SMS code and no ID check. Top up and your key is issued immediately.
Which tools and SDKs work?
Anything that speaks the Anthropic Messages or OpenAI Responses / Chat Completions protocol — Claude Code, Codex CLI, Cursor, Cline, Continue, LangChain, and the official SDKs. Change the base URL and go.
How am I billed?
By actual token usage, deducted from your prepaid balance in real time; unit prices vary by model. No subscription and no minimum spend.
Is my data stored?
The gateway is stateless. Request logs are purged after 30 days and no personal data is retained.
How do I check my usage?
Open the stats page and enter your key to see live spend, remaining quota, and limits.
// CONTACT

Get in touch

Contact details are coming soon. Check back shortly, or open the stats page to manage an existing key.

Ready to build?

One key for Claude, GPT-6.2, and frontier coding models — with usage you can watch in real time.