GPT-4o by OpenAI — current API prices and limits, plus how to call it with one withConflux key, one bill across every model.
withConflux is OpenAI-compatible — change only the base URL and key, then pass gpt-4o.
// Node — official OpenAI SDK, OpenAI-compatible
import OpenAI from "openai";
const ai = new OpenAI({ baseURL: "https://withconflux.com/v1", apiKey: process.env.CONFLUX_KEY });
const res = await ai.chat.completions.create({
model: "gpt-4o",
messages: [{ role: "user", content: "Hello" }],
});A request with a 10,000-token prompt and a 2,000-token response on GPT-4o costs about $0.04 ($2.50/1M in × 10k + $10.00/1M out × 2k). At 100,000 such calls/month that's roughly $4,500 — the same whether you call OpenAI directly or through withConflux, just on one bill.
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| GPT-4o | $2.50 | $10.00 | 128K |
| GPT-6 Astra | $20.00 | $75.00 | 1.05M |
| GPT-5.6 Sol | $8.00 | $30.00 | 1.05M |
| GPT-5.6 Terra | $4.00 | $18.00 | 1.05M |
$2.50 per 1M input tokens and $10.00 per 1M output tokens (provider list price), as of 1 Oct 2026. withConflux passes provider pricing through on one bill.
128K tokens.
Yes — withConflux is OpenAI-compatible. Change only the base URL and your API key, then pass "gpt-4o" as the model.
Send a chat completion to https://withconflux.com/v1 with model "gpt-4o" and your withConflux key. See the code example on this page.
Prices shown as of 1 Oct 2026, sourced from the providers' public pricing — check the provider for the latest. Product and model names are trademarks of their respective owners; withConflux is not affiliated with or endorsed by them.