Build with RunInfra

Call hosted open-weight models through OpenAI-compatible and Anthropic-compatible Model APIs.

RunInfra hosts open-weight models you can call from your apps and coding agents. Chat completions and Responses are OpenAI-compatible. Messages is Anthropic-compatible. Use a workspace API key and pay for usage from your credit balance.

Using a coding agent? Your agent can set up RunInfra’s open models for you. Copy the prompt from Set up with your coding agent.

Call a hosted model

Set the base URL to https://api.runinfra.ai/v1, use a workspace API key, and pass a model id. There is nothing to provision.

Python

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.runinfra.ai/v1",
    api_key=os.environ["RUNINFRA_GATEWAY_KEY"],
)

response = client.chat.completions.create(
    model="nemotron-3-5-lightning-30b",
    messages=[{"role": "user", "content": "Write a TypeScript retry helper."}],
    max_tokens=16384,
)
print(response.choices[0].message.content)

GET /v1/models is the authoritative list of hosted chat models. It also reports when one is temporarily paused.

Model APIs quickstart

Key, base URL, first call.

OpenAI compatibility

LangChain, LiteLLM, LlamaIndex, AI SDK, plain fetch.

Limits

Request, concurrency, and token limits by operation.

Coding agents

Copy one prompt. Your coding agent sets up RunInfra’s open models for you.

Money, keys, and when it breaks

Pricing and credits

Pay as you go, $5 minimum top-up, and monthly coding plans.

Account and access

Sign up, keys, workspaces, deletion.

Troubleshooting

401, 402, 403, 429, 503, and what to do about each.