OverpayingForAIPricing desk

Rewrite · 4 checks · max 400 tokens · benched 2026-09-16

GPT-5.5 vs GPT-5.4 vs GPT-5.4 mini vs GPT-5.4 Nano vs GPT-5.3-Codex on product update to a 280-character post

OpenAI models side by side on "Product update to a 280-character post": GPT-5.4 Nano scores 9/10; GPT-5.4 Nano is the cheapest answer scoring 8+ at $0.07 per 1,000 runs. Outputs, checks, judge reasons, latency and cost.

The prompt every model received

User

Turn this update into a single social media post of at most 280 characters. It must mention "v2.0" and end with the hashtag #OpenSource. Output only the post.

Update: Version 2.0 of our command-line tool is out. It is three times faster on large repositories, adds a built-in diff viewer, and is now licensed under MIT so anyone can contribute.

Rubric for the judge: Punchy post under 280 characters that mentions v2.0, the speed gain, the diff viewer and MIT, ending with #OpenSource.

Side by side

Every cell is one OpenRouter call at temperature 0 with the prompt's token cap and reasoning effort "low" where the model supports it. Cost is usage × the catalogue rate in models.json. Quality is one judge call to anthropic/claude-haiku-4.5 against the prompt's rubric, cached per prompt version.

GPT-5.5

openai/gpt-5.5

9/10
Latency
349ms
Cost
$0.00250
Per 1,000
$2.50

87 in · 69 out (24 reasoning) · 27 words · checks 4/4

  • max_chars
  • contains
  • regex
  • contains
v2.0 is here! Our CLI tool is 3x faster on large repos, adds a built-in diff viewer, and is now MIT licensed so anyone can contribute. #OpenSource

Judge: Post is 139 characters, mentions v2.0, speed gain, diff viewer, MIT licensing, and ends with #OpenSource as required; only minor issue is it doesn't explicitly state 'anyone can contribute' though it's implied by 'MIT licensed so anyone can contribute.'

GPT-5.4

openai/gpt-5.4

9/10
Latency
392ms
Cost
$0.00122
Per 1,000
$1.22

87 in · 67 out (21 reasoning) · 27 words · checks 4/4

  • max_chars
  • contains
  • regex
  • contains
v2.0 of our command-line tool is here: 3x faster on large repositories, now with a built-in diff viewer, and licensed under MIT so anyone can contribute. #OpenSource

Judge: Post is 179 characters, mentions v2.0, speed gain (3x faster), diff viewer, and MIT licensing, ends with #OpenSource as required; only minor issue is it could be slightly punchier but meets all rubric criteria.

GPT-5.4 mini

openai/gpt-5.4-mini

9/10
Latency
357ms
Cost
$0.00037
Per 1,000
$0.37

87 in · 67 out (23 reasoning) · 23 words · checks 4/4

  • max_chars
  • contains
  • regex
  • contains
v2.0 of our command-line tool is here: 3x faster on large repos, built-in diff viewer, and now MIT-licensed so anyone can contribute. #OpenSource

Judge: Post is 139 characters, mentions v2.0, speed gain (3x faster), diff viewer, MIT licensing, and ends with #OpenSource as required; only minor issue is it doesn't explicitly state 'large repositories' but 'large repos' is a clear abbreviation.

GPT-5.4 Nano

openai/gpt-5.4-nano

9/10
top judge scorecheapest scoring 8+
Latency
256ms
Cost
$7.5e-5
Per 1,000
$0.07

87 in · 46 out · 25 words · checks 4/4

  • max_chars
  • contains
  • regex
  • contains
v2.0 is out! Our command-line tool is 3x faster on large repositories, includes a built-in diff viewer, and is now MIT-licensed—so everyone can contribute. #OpenSource

Judge: Post is 271 characters, mentions v2.0, speed gain, diff viewer, and MIT licensing, ends with #OpenSource as required; only minor issue is it could be slightly punchier but otherwise excellent.

GPT-5.3-Codex

openai/gpt-5.3-codex

9/10
Latency
394ms
Cost
$0.00207
Per 1,000
$2.07

87 in · 137 out (91 reasoning) · 27 words · checks 4/4

  • max_chars
  • contains
  • regex
  • contains
v2.0 of our command-line tool is here: 3x faster on large repos, now with a built-in diff viewer, and licensed under MIT so anyone can contribute. #OpenSource

Judge: Post is 179 characters, mentions v2.0, speed gain (3x faster), diff viewer, MIT license, and ends with #OpenSource as required; only minor issue is slightly less punchy tone than optimal.

Frequently asked

What does this prompt test?

Rewrite: Punchy post under 280 characters that mentions v2.0, the speed gain, the diff viewer and MIT, ending with #OpenSource. The deterministic checks are max_chars, contains, regex, contains.

Which model should I pick for this task?

If the judge's bar of 8/10 is good enough for you, GPT-5.4 Nano at $0.07 per 1,000 runs. If you need the top score, GPT-5.4 Nano at $0.07 per 1,000 runs.

Same prompt, other families

Run it yourself

Re-run this prompt on OpenAI with your own OpenRouter key, or tweak the wording and see what changes.

More OpenAI prompts

If our calculators helped you cut down on hidden AI wallet leaks, thanks for using them. A tiny fraction of your savings is what keeps our pricing indexes updated daily.

Not sure which AI is cheapest for your use case? Find out in 30 seconds — no signup required.

Calculate CostDecision Engine →

AI cost intelligence

Stop overpaying for AI tools

Join the OverpayingForAI list for pricing updates, cheaper alternatives, and practical buying guidance.

Now tracking 50+ AI tools, models, platforms, subscriptions, coding tools, and automation products.

We use your email only for OverpayingForAI updates. Unsubscribe anytime.