MiniMax M3 pricing for bug detection

Quick start

Call MiniMax M3 with the OpenAI Python SDK pointed at api.minimax.chat:

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.minimax.chat/v1",
    api_key=os.environ["MINIMAX_API_KEY"],
)
response = client.chat.completions.create(
    model="minimax-m3",
    max_tokens=2000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.003900 per call at standard rates
# Input:  $0.30/MTok
# Output: $1.20/MTok

How MiniMax M3 compares on cost

Per-call cost for all models scoring 50+ on bug detection benchmarks. Hover for details.

Highest-quality affordable option: Claude Sonnet 5 at $0.0300/call (7.7x the cost, 96/100 quality). MiniMax M3 is already the cheapest choice for bug detection.

What drives bug detection cost

Bug detection sends a file and gets back a short list of suspected defects, so input dominates and output stays small. That makes it cheap per call and tempting to run continuously, which is the real cost driver: frequency, not per-call price. Caching the unchanged parts of the codebase and running only on changed files is worth more than switching models.

For MiniMax M3 specifically, that means output tokens cost 4.0x more than input, at $1.20 vs $0.30 per MTok. At this use case’s 5,000/2,000 token split, output accounts for 62% of the $0.003900 per-call cost.

MiniMax M3 quality benchmarks for bug detection

Benchmark data for bug detection is pending for MiniMax M3. Test against your own evaluation suite before moving to production.

Benchmark data is not yet available for MiniMax M3. We recommend testing against your own evaluation criteria.

About MiniMax M3

Prices from platform.minimax.io/docs/pricing/overview (read 2026-10-11). Long context (>512K tokens) is billed above the listed input and output rates. Cache hit: $0.06/MTok input. No batch discount published. Not yet benchmarked, so never recommended.

Other models from MiniMax

You can compare MiniMax M3 head-to-head against any other model on our model comparison pages, or track how pricing has changed over time on the pricing history tracker.

Frequently asked questions