Quickstart

This guide assumes you already have:

A virtual key with the sk-corvex- prefix. If you don’t, ask your team admin or see Authentication.
The Corvex API base URL — the examples below use https://api.tokenfactory.corvex.cloud.

Never paste a key into a public Gist, a screenshot, or a client-side bundle. Treat it like a password — it carries spend and rate-limit authority for the whole workspace.

Send a chat completion

Already on the OpenAI SDK? Swap 2 lines.

The base-URL/API-key swap shown on the drop-in page is copy-paste runnable against the Corvex public endpoint.

curl https://api.tokenfactory.corvex.cloud/v1/chat/completions \
  -H "Authorization: Bearer sk-corvex-YOUR_VIRTUAL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-5.2-FP8",
    "messages": [
      {"role": "user", "content": "Hello, world."}
    ]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="sk-corvex-YOUR_VIRTUAL_KEY",
    base_url="https://api.tokenfactory.corvex.cloud/v1",
)

resp = client.chat.completions.create(
    model="zai-org/GLM-5.2-FP8",
    messages=[{"role": "user", "content": "Hello, world."}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-corvex-YOUR_VIRTUAL_KEY",
  baseURL: "https://api.tokenfactory.corvex.cloud/v1",
});

const resp = await client.chat.completions.create({
  model: "zai-org/GLM-5.2-FP8",
  messages: [{ role: "user", content: "Hello, world." }],
});
console.log(resp.choices[0].message.content);

If your client library defaults to OpenAI’s hosted endpoint, set base_url (Python) / baseURL (TypeScript) — pointing it at your Corvex gateway is the only change needed.

What you’ll get back

A successful call returns HTTP 200 and a JSON body shaped like this:

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "created": 1763472000,
  "model": "zai-org/GLM-5.2-FP8",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 9,
    "total_tokens": 17
  }
}

Model naming

Corvex models use bare lab-canonical Hugging Face repo ids — <hf-namespace>/<model-name> (e.g. zai-org/GLM-5.2-FP8, moonshotai/Kimi-K2.7-Code). There is no corvex/ prefix; legacy corvex/<…> ids return HTTP 404. Serving is handled server-side — you only send the model id, and the platform routes it for you. Get the current list of available models for your virtual key:

curl https://api.tokenfactory.corvex.cloud/v1/models \
  -H "Authorization: Bearer sk-corvex-YOUR_VIRTUAL_KEY"

When something goes wrong

If the Authorization header is missing, malformed, or the key is unknown to the workspace, the gateway returns HTTP 401:

{
  "error": {
    "code": "invalid_api_key",
    "message": "Invalid API key"
  }
}

Most often this is one of:

The key is unset in the shell that ran curl.
The key was copied with whitespace or a trailing newline.
The key belongs to a different workspace than the model you’re calling.

For the full error taxonomy (429 rate-limit, 403 model-blocked, etc.) see the Errors reference.

What’s next

Authentication → — how your virtual key works and where to create one.
API Reference → — every endpoint, request/response schemas, and error codes.

The OpenAI SDK drop-in examples on the drop-in page are copy-paste runnable. The broader samples on this page are illustrative.

Get Started

Guides

Models

Pricing

Integrations & Harness

API Reference

Reference

Send a chat completion

Already on the OpenAI SDK? Swap 2 lines.

What you’ll get back

Model naming

When something goes wrong

What’s next

​Send a chat completion

Already on the OpenAI SDK? Swap 2 lines.

​What you’ll get back

​Model naming

​When something goes wrong

​What’s next

Send a chat completion

What you’ll get back

Model naming

When something goes wrong

What’s next