c2e.e2e.one Gateway

Cursor Subscription → API Gateway

Configured via wrangler secret put AUTH_KEY
Optional. If not set in worker env, stored locally in browser session.
Cursor Subscription Active
Loading...
Checking upstream usage...
Included Cap: $70.00
Cursor Models Pool 98% left
2% used
Includes Cursor Grok & Composer (200k)
Other Models Pool 63% left
37% used
Includes Gemini 3.8 Flash (1M), etc.
Included Spend Balance 36% left
$24.99 / $70.00
$45.01 spend used of $70.00
Total Gateway Calls
0
0 errors (100% success)
Prompt Cache Rate
0% Cached
0 cached tokens
Tokens Processed
0
0 prompt · 0 completion
Upstream Concurrency
0 / 8 Active
0Slot rate limiter
Configured Gateway Models All Active
gemini-3-8-flash 1M Tokens
Google Gemini 3.8 Flash (High, Medium, Low Effort)
0 calls
grok4-6 200k
xAI Grok 4.6 (standard non-fast mode · credit-saver)
0 calls
composer & composer-fast 200k
Cursor Composer 2.5 / Fast
0 calls
glm5-2 200k
Zhipu GLM 5.2 High
0 calls
Cursor Upstream Account & Limits
Fetching live usage from api2.cursor.sh...
Plan / Membership: —
Cursor Models Pool: —
Other Models Pool: —
Included Plan Balance: —
Overall Plan Usage: —
Spend Limit Policy: —
Billing Period Start: —
Fingerprint Tenant: —
Recent API Calls 0 requests
Time Method & Path Model Status Duration Tokens (In / Out / Cache)
No requests recorded yet. Send requests to the API to see live logs!
Request Options
Quick Hello Python Script
Model Response Output
Ready
// Output will stream here in real time...
Configuring opencode & API Clients

This gateway implements the complete OpenAI Responses API and Chat Completions API atop your private Cursor subscription credits.

opencode Configuration (~/.config/opencode/config.json)
{
  "api_base": "https://c2e.e2e.one/v1",
  "api_key": "YOUR_AUTH_KEY",
  "model": "gemini-3-8-flash"
}
URL-Path Model Endpoints (Direct Model Routing)

You can target models directly via URL paths without altering request bodies:

Model Responses API URL Chat Completions URL Context Limit
gemini-3-8-flash https://c2e.e2e.one/api/gemini-3-8-flash/responses https://c2e.e2e.one/api/gemini-3-8-flash/chat/completions 1,000,000 tokens
gemini-3-8-flash-low https://c2e.e2e.one/api/gemini-3-8-flash-low/responses https://c2e.e2e.one/api/gemini-3-8-flash-low/chat/completions 1,000,000 tokens
grok4-6 https://c2e.e2e.one/api/grok4-6/responses https://c2e.e2e.one/api/grok4-6/chat/completions 200,000 tokens
composer https://c2e.e2e.one/api/composer/responses https://c2e.e2e.one/api/composer/chat/completions 200,000 tokens
glm5-2 https://c2e.e2e.one/api/glm5-2/responses https://c2e.e2e.one/api/glm5-2/chat/completions 200,000 tokens
Curl Test Example
curl -X POST https://c2e.e2e.one/api/gemini-3-8-flash/responses \
  -H "Authorization: Bearer YOUR_AUTH_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Explain token-level prompt caching in 2 sentences.",
    "stream": true
  }'