OverpayingForAIPricing desk

Tool call · 7 checks · max 400 tokens · benched 2026-09-16

MiniMax M3 vs MiniMax M2.7 vs MiniMax M2.5 on emit a calendar tool call

Minimax models side by side on "Emit a calendar tool call": MiniMax M2.5 scores 10/10; MiniMax M2.5 is the cheapest answer scoring 8+ at $0.20 per 1,000 runs. Outputs, checks, judge reasons, latency and cost.

The prompt every model received

System

You are a function-calling engine. Reply with JSON only, no prose, no code fences.

User

You have one tool:
{"name": "create_event", "parameters": {"title": "string", "start": "ISO 8601 date-time without timezone, e.g. 2026-01-31T09:00", "duration_minutes": "integer", "attendees": "array of email strings"}}

Produce the tool call for this user message as a JSON object of the shape {"name": string, "arguments": object}.

User: Book a 45-minute design review with [email protected] and [email protected] on 2 October 2026 at 3pm.

Rubric for the judge: Correct tool name, ISO start 2026-10-02T15:00, integer duration 45, both attendees in an array, a sensible title.

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.

MiniMax M3

minimax/minimax-m3

10/10
Latency
297ms
Cost
$0.00025
Per 1,000
$0.25

309 in · 134 out (65 reasoning) · 13 words · checks 7/7

  • json_valid
  • json_keys
  • regex
  • contains
  • regex
  • contains
  • contains
{"name": "create_event", "arguments": {"title": "Design Review", "start": "2026-10-02T15:00", "duration_minutes": 45, "attendees": ["[email protected]", "[email protected]"]}}

Judge: All rubric criteria met: correct tool name, proper ISO 8601 start datetime, integer duration of 45 minutes, both attendees in array format, and sensible title.

MiniMax M2.7

minimax/minimax-m2.7

10/10
Latency
777ms
Cost
$0.00052
Per 1,000
$0.52

156 in · 392 out (336 reasoning) · 13 words · checks 7/7

  • json_valid
  • json_keys
  • regex
  • contains
  • regex
  • contains
  • contains
{"name": "create_event", "arguments": {"title": "Design review", "start": "2026-10-02T15:00", "duration_minutes": 45, "attendees": ["[email protected]", "[email protected]"]}}

Judge: All rubric criteria met: correct tool name, proper ISO 8601 start datetime, integer duration of 45 minutes, both attendees in array format, and sensible title.

MiniMax M2.5

minimax/minimax-m2.5

10/10
top judge scorecheapest scoring 8+
Latency
1.7s
Cost
$0.00020
Per 1,000
$0.20

156 in · 149 out (93 reasoning) · 13 words · checks 7/7

  • json_valid
  • json_keys
  • regex
  • contains
  • regex
  • contains
  • contains
{"name": "create_event", "arguments": {"title": "Design review", "start": "2026-10-02T15:00", "duration_minutes": 45, "attendees": ["[email protected]", "[email protected]"]}}

Judge: All rubric criteria met: correct tool name, proper ISO 8601 start datetime, integer duration of 45 minutes, both attendees in array format, and sensible title.

Frequently asked

What does this prompt test?

Tool call: Correct tool name, ISO start 2026-10-02T15:00, integer duration 45, both attendees in an array, a sensible title. The deterministic checks are json_valid, json_keys, regex, contains, regex, contains, contains.

Which model should I pick for this task?

If the judge's bar of 8/10 is good enough for you, MiniMax M2.5 at $0.20 per 1,000 runs. If you need the top score, MiniMax M2.5 at $0.20 per 1,000 runs.

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

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.