Frontier open models, one API key away

Terminal

What is it?

wally is a command-line tool that connects the coding agent you already use to a model. It runs models on your machine or serves them from Wally Cloud, with the same commands for both.

How does it help you?

You sign in once in your browser with Google or GitHub, and there is no key to copy. Then one command starts OpenCode, Claude Code, Codex or another supported agent on the model you pick.

Where does your data go, and who sees it?

A local model keeps everything on your machine. A hosted model sends your prompts to Wally Cloud, which runs with zero data retention and does not store them, and your credits pay for the run. Wally never moves a request between the two on its own.

API

Keep your OpenAI code. Change the base URL.

What is it?

Wally Cloud serves open models through the OpenAI chat-completions API. You send a request to one URL and read the reply as a stream.

How does it help you?

Your OpenAI client, SDK or curl command works as it is. You change the base URL, the key and the model ID, and nothing else. Switching models later means changing one string.

Where does your data go, and who sees it?

Your app sends the prompt over HTTPS with your API key. Wally Cloud runs the model and streams the reply back. Wally runs with zero data retention by default, so it does not store prompts or replies. We keep usage and billing records, tokens and spend, in a separate place.

curl https://inference.runanywhere.ai/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3-flash",
    "stream": true,
    "messages": [{ "role": "user", "content": "Hello, Wally" }]
  }'

import os
from openai import OpenAI

# A Cloud key from the console
client = OpenAI(
    base_url="https://inference.runanywhere.ai/v1",
    api_key=os.environ["API_KEY"],
)

stream = client.chat.completions.create(
    model="glm-5.3-flash",
    messages=[{"role": "user", "content": "Hello, Wally"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

import OpenAI from "openai";

// A Cloud key from the console
const client = new OpenAI({
  baseURL: "https://inference.runanywhere.ai/v1",
  apiKey: process.env.API_KEY,
});

const stream = await client.chat.completions.create({
  model: "glm-5.3-flash",
  messages: [{ role: "user", content: "Hello, Wally" }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}