🎮 Try free for 48 hours — no credit card required! Start now or use code LAUNCH50 for 50% off.
kranky.iokranky.io

kranky.ai

One API. Every model.
Pay-as-you-go.

OpenAI-compatible LLM gateway. Call Anthropic, OpenAI, and open-source models through one endpoint, one key, one bill. Prepaid credits, no monthly minimums, BYOK supported.

Get an API keySee it in code

2

Providers wired

Anthropic + OpenAI (more coming)

10

Models live

5%

Markup over provider rates

flat, no tiering

<10ms

Latency overhead

per request, p50

Drop-in replacement for the OpenAI SDK

Already using OpenAI? Change the base URL and key. Everything else stays the same.

curl
curl https://kranky.ai/api/llm/v1/chat/completions \
  -H "Authorization: Bearer sk-kranky-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-5",
    "messages": [{"role": "user", "content": "hi"}],
    "stream": true
  }'
Python (openai-sdk)
from openai import OpenAI

client = OpenAI(
  base_url="https://kranky.ai/api/llm/v1",
  api_key="sk-kranky-...",
)

resp = client.chat.completions.create(
  model="claude-sonnet-4-5",
  messages=[{"role": "user", "content": "hi"}],
)
print(resp.choices[0].message.content)

How it works

01

Get an API key

Sign up, top up $5+ of credits, get a key. OpenAI SDK works out of the box — just swap the base URL.

02

Call any model

Use the same /v1/chat/completions endpoint for every provider. Pick the model by id (gpt-4o, claude-sonnet-4-5, …).

03

Pay only for tokens

Provider pricing + 5% routed transparently. We bill credits per request — no monthly minimums, cancel any time.

Available models

More coming weekly. Ping us if there's one you need.

Model idProviderContext window
gpt-4oopenai128K tokens
gpt-4o-miniopenai128K tokens
claude-sonnet-4-6anthropic1000K tokens
claude-sonnet-4-5anthropic200K tokens
claude-opus-4-8anthropic1000K tokens
claude-opus-4-7anthropic1000K tokens
claude-haiku-4-5anthropic200K tokens
nova-microbedrock128K tokens
nova-litebedrock300K tokens
nova-probedrock300K tokens

Pricing

Pay-as-you-go

Provider rate + 5%

No monthly minimum. Top up credits when you want.

  • All models, all providers
  • Streaming + non-streaming
  • Per-request usage tracking + audit log
Bring your own keysAvailable now

Flat infrastructure fee

Your provider keys, our routing + analytics + auth.

  • Zero LLM markup — you pay the provider directly
  • Unified billing across providers
  • Per-team usage dashboards (coming soon)

Stop juggling provider keys.

One key. One bill. Every model that matters.

Get an API key