AI model API console
Lower-cost GPT, Claude, and Gemini API
Use one API key with Codex, Claude Code, Gemini CLI, and common developer tools. Set 0-0 as the Base URL to call supported discounted models, with usage, spend, and request history in one console.
API
Low-friction switch
Keep your SDK; change Base URL
Pricing
Discounted model rates
GPT / Claude / Gemini
Usage
Clear spend history
Tokens, cost, and status
Spend-aware console
Model usage, cost, and request status in one view.
Spend (24h)
$0.23
stable
Requests
128
last 24h
Error rate
0%
healthy
Request log
Latency / TPS / Cost
gpt-5.5ttft 312ms · tps 48.2 · $0.0012
claude-opus-4-8ttft 640ms · tps 22.9 · $0.0098
gemini-3.1-prottft 280ms · tps 55.4 · $0.0007
Model names are used to show supported compatibility across GPT, Claude, and Gemini routes.
OpenAI-compatible calls through one endpoint./v1/*
VALUE
Lower costs without losing control
0-0 keeps model access, API keys, usage, and spend together so developers can ship faster and reconcile less.
OpenAI-compatible API
Unified API entrypoint
One key for supported models.
Call supported GPT, Claude, and Gemini models through an OpenAI-compatible endpoint and reduce account switching.
API key management
Create, copy, revoke, and restore keys.
Keep credentials organized for personal projects or small teams without passing upstream keys through the frontend.
Per-request usage records
Every call has context.
Review model, tokens, latency, TTFT, TPS, cost, and request status when you need to debug or reconcile spend.
Access control built in
Account verification, role boundaries, and upstream credentials kept server-side.
Email verification
Verification codes keep account creation clean.
Role protection
Owner safeguards keep admin actions within role boundaries.
Gateway isolation
Upstream API keys stay server-side; calls go through the 0-0 gateway.
Pricing
Current rates for common models, billed in $/M tokens. Input and output are priced separately.
$/M TOKENS
gpt-5.5
97.5% off
Input
$0.125$5
Output
$0.75$30
$/M TOKENS
claude-opus-4-8
75% off
Input
$1.25$5
Output
$6.25$25
$/M TOKENS
gemini-3.1-pro
85% off
Input
$0.3$2
Output
$1.8$12
Clear token billing
Input tokens and output tokens are shown separately, so each call has a readable cost breakdown.
Discounted model pool
The highlighted prices already include the listed discounts for high-frequency GPT, Claude, and Gemini usage.
Change the Base URL, start calling
Register, create an API Key, and update base_url plus api_key in your existing OpenAI SDK setup.
Keep the /v1/chat/completions calling pattern and route supported models through the 0-0 gateway.
Create API Key