One key · every major model

LLM API Gateway

One API key routes to every major model — GPT, Gemini, Claude, DeepSeek, Seedance — with automatic failover, usage analytics, and a single invoice instead of five provider accounts.

Get your gateway key See live pricing

GPT · Gemini · Claude · DeepSeek · Seedance — one key, one invoice · no credit card to start

Sample output pricing

GPT-5 / 1M tokens	$6.67	$10.00
Gemini 2.5 Pro / 1M tokens	$6.67	$10.00
DeepSeek V4 Flash / 1M tokens	$0.07	$0.14

* Illustrative pricing — see the flatkey pricing page for live rates.

Route every model through one endpoint

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://router.flatkey.ai/v1",
    api_key="YOUR_FLATKEY_KEY",
)

response = client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

curl

curl https://router.flatkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $FLATKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

One key, every major model

GPT, Gemini, Claude, DeepSeek, and Seedance behind a single OpenAI-compatible endpoint — swap models by changing one string.

Automatic failover

Health-checked upstream channels with automatic retries and failover, so one provider outage does not take your product down.

Usage analytics

Per-key and per-model usage, live spend tracking, and prepaid limits keep costs visible and bounded.

Single invoice

Consolidate five provider bills into one balance and one invoice — simpler procurement, simpler accounting.

LLM API Gateway

One API key routes to every major model — GPT, Gemini, Claude, DeepSeek, Seedance — with automatic failover, usage analytics, and a single invoice instead of five provider accounts.

Get your gateway key

GPT · Gemini · Claude · DeepSeek · Seedance — one key, one invoice · no credit card to start

How does failover work?

The gateway continuously health-checks upstream channels and retries or reroutes failed requests automatically — no client-side changes required.

Do I have to change my code?

No. flatkey.ai is OpenAI-compatible: keep your existing OpenAI SDK and switch base_url plus api_key. Model ids stay the same.

How is billing handled across models?

One prepaid balance covers every model. Usage analytics and a single invoice keep spend bounded before you scale.