v1 gateway is live · 99.99% uptime

The Ultimate AI API Gateway for Developers.

One API Key. All major models (GPT-4o, Claude 3.5, Gemini). Zero 429 errors. Drop-in replacement for OpenAI.

curl -H "Authorization: Bearer 0xinf_***" api.0xinf.com/v1/chat

~/projects/app — curl api.0xinf.com
zsh
Request
$ curl https://api.0xinf.com/v1/chat/completions
  -H "Authorization: Bearer 0xinf_sk_***"
  -H "Content-Type: application/json"
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "ping"}
    ]
  }'
200 OK · 142ms
{
  "id": "cmpl_0xinf_8fJk2",
  "model": "gpt-4o",
  "provider": "openai",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "pong → you're live."
      }
    }
  ],
  "usage": { "total_tokens": 17 }
}
region: iad1route: gateway → openai● healthy
// why 0xinf

Built for the next generation of AI apps.

A single, resilient gateway that abstracts away the chaos of multi-provider AI infrastructure.

Drop-in Replacement

Fully OpenAI compatible. Just change the BaseURL and API Key.

Ultimate Reliability

Enterprise-grade connection pooling. Say goodbye to rate limits and 429s.

All-in-One Routing

Access OpenAI, Anthropic, Google, and Meta through a single unified endpoint.

Transparent Pay-as-you-go

Millisecond-level latency logs and exact token usage billing. No hidden fees.

// developer experience

Integrated in 60 seconds.

Keep your existing SDK. Swap one line. Get every model, with built-in failover.

# pip install openai
from openai import OpenAI

client = OpenAI(
    api_key="0xinf_sk_live_***",
    base_url="https://api.0xinf.com/v1",
)

resp = client.chat.completions.create(
    model="claude-3-5-sonnet",
    messages=[{"role": "user", "content": "ship it"}],
)

print(resp.choices[0].message.content)
endpoint: api.0xinf.com/v1=> OpenAI compatible
// supported models

One Key, Infinite Intelligence.

Route across every major frontier and open-source model with automatic failover and streaming.

OP
GPT-4oOpenAI · flagship
AN
Claude 3.5 SonnetAnthropic · reasoning
GO
Gemini 1.5 ProGoogle · 1M ctx
ME
Llama 3 70BMeta · open
MI
Mistral LargeMistral · fast
OP
GPT-4o miniOpenAI · cheap
AN
Claude 3 HaikuAnthropic · low-latency
GO
Gemini 1.5 FlashGoogle · stream
OP
GPT-4oOpenAI · flagship
AN
Claude 3.5 SonnetAnthropic · reasoning
GO
Gemini 1.5 ProGoogle · 1M ctx
ME
Llama 3 70BMeta · open
MI
Mistral LargeMistral · fast
OP
GPT-4o miniOpenAI · cheap
AN
Claude 3 HaikuAnthropic · low-latency
GO
Gemini 1.5 FlashGoogle · stream
+ 80 more models · new providers added weekly
// pricing

Pay for what you use. Nothing more.

Deposit credits, ship features, and only spend what you actually consume.

Pay-as-you-go

Developer

most popular
$0to start · $5 minimum top-up

Provider passthrough pricing + 0% gateway fee on the first $50.

  • No monthly commitment
  • No rate limits
  • Real-time dashboard
  • Top-up never expires
  • Per-token transparent billing
  • All providers, one invoice