OpenAI compatibility

import os
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="nemotron-3-5-lightning-30b",
    base_url="https://api.runinfra.ai/v1",
    api_key=os.environ["RUNINFRA_GATEWAY_KEY"],
    max_tokens=4096,
)

print(llm.invoke("Write a TypeScript retry helper.").content)

for chunk in llm.stream("Write a TypeScript retry helper."):
    print(chunk.content, end="", flush=True)

import os
import litellm

response = litellm.completion(
    model="openai/deepseek-v4-flash",
    api_base="https://api.runinfra.ai/v1",
    api_key=os.environ["RUNINFRA_GATEWAY_KEY"],
    messages=[{"role": "user", "content": "Write a TypeScript retry helper."}],
    max_tokens=16384,
)
print(response.choices[0].message.content)

import os
from llama_index.llms.openai import OpenAI

llm = OpenAI(
    model="qwen3-8-27b",
    api_base="https://api.runinfra.ai/v1",
    api_key=os.environ["RUNINFRA_GATEWAY_KEY"],
)

print(llm.complete("What is RunInfra?").text)

// Server-side only: never expose RUNINFRA_GATEWAY_KEY in browser code.
import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
import { streamText } from "ai";

const apiKey = process.env.RUNINFRA_GATEWAY_KEY;
if (!apiKey) throw new Error("Set RUNINFRA_GATEWAY_KEY first.");

const runinfra = createOpenAICompatible({
  name: "runinfra",
  baseURL: "https://api.runinfra.ai/v1",
  apiKey,
});

const result = streamText({
  model: runinfra.chatModel("nemotron-3-5-lightning-30b"),
  maxOutputTokens: 4096,
  prompt: "Write a TypeScript retry helper.",
});

for await (const part of result.fullStream) {
  if (part.type === "reasoning-delta") process.stdout.write(part.text);
  if (part.type === "text-delta") process.stdout.write(part.text);
}

const response = await fetch("https://api.runinfra.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.RUNINFRA_GATEWAY_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "nemotron-3-5-lightning-30b",
    messages: [{ role: "user", content: "Write a TypeScript retry helper." }],
    max_tokens: 4096,
    stream: true,
    stream_options: { include_usage: true },
  }),
});

if (!response.ok) {
  const { error } = await response.json();
  throw new Error(`${response.status} ${error.code}: ${error.message}`);
}

const reader = response.body.getReader();
const decoder = new TextDecoder();
let buffer = "";

while (true) {
  const { done, value } = await reader.read();
  if (done) break;

  buffer += decoder.decode(value, { stream: true });
  const lines = buffer.split("\n");
  buffer = lines.pop() ?? "";

  for (const line of lines) {
    if (!line.startsWith("data: ")) continue;
    const payload = line.slice(6).trim();
    if (payload === "[DONE]") continue;

    const chunk = JSON.parse(payload);
    const delta = chunk.choices[0]?.delta;
    // The model's thinking arrives as `reasoning`, the answer as `content`.
    if (delta?.reasoning) process.stdout.write(delta.reasoning);
    if (delta?.content) process.stdout.write(delta.content);
  }
}