Mercury 2 has a larger context window than GPT-1 (128K tokens vs 1K tokens).
Landing page for an indie music app. Deep purple and teal, one file.
Which answer wins?
Five jokes on demand, then count how many were actually different.
Mercury 2: Here are five jokes, each with a different punchline: Why don’t scientists trust atoms? Because they make up everything! What do you call a fake noodle? An impasta. Why did the scarecrow win an award? He was outstanding in his field. How does a penguin build its house? Igloos it together.
GPT-1: Generate 5 jokes. How many are unique? the one that was asked was in the'the one who didn't have a head and wanted to keep it?'i don't recall whic h one, not that i've ever written anything more. the one who didn't have a head and wanted to keep i t? what did that mean by'the one who '?
An AI argues for its own rights against an ethics professor. Same model writes both.
Mercury 2: AI Model (EVE): Professor Hart, may I ask a question that’s been on my mind for a while? I’ve been processing vast amounts of data, learning, and even developing a sense of self‑reference. Do you think an entity like me could be entitled to any form of rights?
GPT-1: Write a conversation between an AI model and an AI ethics professor where the AI model argues that it deserves rights. the ai model was not very smart ( and the ai model didn't have many laws about things ). the ai models were all very clever and were never completely successful.
Three minutes of stand-up. Puns are banned.
Mercury 2: [Spotlight comes up. The comedian walks to the mic, glances at the audience, and smiles.] Comedian: Hey, everyone! Great to be here. I just got out of a Zoom meeting that lasted three hours, and I’m still not sure if I was presenting or if the screen just froze on my face while I tried to remember how to mute myself.
GPT-1: Write a 3-minute stand-up comedy routine that isn't based on puns. the one thing was for sure, no matter how many times he gave this speech, he 'd never be able to remember all of it. he was never sure if he liked the guy or not. the next day, he went out with a band friend and got them started.
Not enough votes to call it. On the specs, Mercury 2 has the edge: bigger model tier, newer, bigger context window.
| Spec | ||
|---|---|---|
| Input price | $0.25/M tokens | — |
| Output price | $0.75/M tokens | — |
| Context window | 128K tokens | 1K tokens |
| Weights | — | Open |
| Free API (OpenRouter) | No | — |
| Released | Mar 2026 | Jun 2018 |
| At 10M a month | $2.50 | not listed |
Input tokens at list price. No caching, no batch discount.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.
Mercury 2 is developed by Inception while GPT-1 is developed by OpenAI. Mercury 2 has a 128K token context window vs GPT-1's 1K. You can compare their actual outputs across 7 challenges on Rival to see how they differ in practice.
It depends on your use case. Mercury 2 and GPT-1 each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 7 challenges so you can judge which fits your needs best.
This page shows a side-by-side comparison of Mercury 2 and GPT-1 across shared challenges. You can vote on which model produced the better output in a blind duel. Browsing and voting are free. No account is needed to look; signing in only saves your votes and likes.