You set the pace.And the price.

Choose an open model, then set the latency your workload actually needs. We handle the infrastructure behind one API, so you get serious savings without giving up reliability, technical depth, or a provider you can trust.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.gradiated.com",
    api_key="YOUR_GRADIATED_API_KEY",
)

response = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[{
        "role": "user",
        "content": "Explain inference in one sentence.",
    }],
    extra_body={"service_tier": "fast"},
)

Lower cost when your request can wait.

Select mode

2.3xfaster inference than other providers

Best suited for

Interactive workloads where response time matters most.

Pick the model.

Run leading open models through one API. No provider hunt, new account, or integration for every model.

Set the pace.

Choose the latency your workload needs. Pay for that requirement instead of somebody else's idea of fast.

Trust the endpoint.

Get material savings from a reliable, SOC 2 provider with the technical depth to run production workloads.

Read docs

Available models

Move your application over to open-source models and spend ~10x less on tokens for the equivalent quality.

More models coming soon. Request a model