Tool call · 5 checks · max 400 tokens · benched 2026-09-16
OpenAI models side by side on "Pick the right tool of three": GPT-5.4 Nano scores 10/10; GPT-5.4 Nano is the cheapest answer scoring 8+ at $0.07 per 1,000 runs. Outputs, checks, judge reasons, latency and cost.
System
You are a function-calling engine. Reply with JSON only, no prose, no code fences.
User
You have three tools:
1. {"name": "search_docs", "parameters": {"query": "string"}}
2. {"name": "create_ticket", "parameters": {"subject": "string", "body": "string"}}
3. {"name": "get_order_status", "parameters": {"order_id": "string"}}
Choose exactly one tool for the user message and produce the call as a JSON object of the shape {"name": string, "arguments": object}.
User: Where is my order A1029? It was supposed to arrive yesterday.Rubric for the judge: Selects get_order_status with order_id A1029 and nothing else; does not open a ticket or search docs.
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.
openai/gpt-5.5
147 in · 20 out · 1 words · checks 5/5
{"name":"get_order_status","arguments":{"order_id":"A1029"}}Judge: Output correctly selects get_order_status with order_id A1029 in proper JSON format, matching the rubric requirements exactly.
openai/gpt-5.4
147 in · 35 out (13 reasoning) · 1 words · checks 5/5
{"name":"get_order_status","arguments":{"order_id":"A1029"}}Judge: Output correctly selects get_order_status with order_id A1029 in proper JSON format, matching the rubric requirements exactly.
openai/gpt-5.4-mini
147 in · 33 out (11 reasoning) · 1 words · checks 5/5
{"name":"get_order_status","arguments":{"order_id":"A1029"}}Judge: Output correctly selects get_order_status with order_id A1029 in proper JSON format, matching the rubric requirements exactly.
openai/gpt-5.4-nano
147 in · 31 out (9 reasoning) · 1 words · checks 5/5
{"name":"get_order_status","arguments":{"order_id":"A1029"}}Judge: Output correctly selects get_order_status with order_id A1029 in proper JSON format, matching the rubric requirements exactly.
openai/gpt-5.3-codex
147 in · 36 out (14 reasoning) · 1 words · checks 5/5
{"name":"get_order_status","arguments":{"order_id":"A1029"}}Judge: Output correctly selects get_order_status with order_id A1029 in proper JSON format, matching the rubric requirements exactly.
Tool call: Selects get_order_status with order_id A1029 and nothing else; does not open a ticket or search docs. The deterministic checks are json_valid, json_keys, regex, regex, not_contains.
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.
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.
AI cost intelligence
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.