MiniMax M2 pricing for chatbot

Quick start

Call MiniMax M2 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-m2",
    max_tokens=1000,
    messages=[{"role": "user", "content": "Your prompt here"}]
)
# Cost: ~$0.001520 per call at standard rates
# Input:  $0.26/MTok
# Output: $1.00/MTok

How MiniMax M2 compares on cost

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

Highest-quality affordable option: GPT 5.6 Luna at $0.001600/call (1.1x the cost, 85/100 quality). MiniMax M2 is already the cheapest choice for chatbot.

What drives chatbot cost

Conversational cost compounds: every turn resends the history, so the tenth message in a thread costs several times the first. Cost grows with the square of conversation length unless you cache the prefix or truncate history. Prompt caching is not an optimization here, it is the difference between a viable and an unviable unit economic.

For MiniMax M2 specifically, that means output tokens cost 3.8x more than input, at $1.00 vs $0.26 per MTok. At this use case’s 2,000/1,000 token split, output accounts for 66% of the $0.001520 per-call cost.

MiniMax M2 quality benchmarks for chatbot

Benchmark data for chatbot is pending for MiniMax M2. Test against your own evaluation suite before moving to production.

Benchmark data is not yet available for MiniMax M2. We recommend testing against your own evaluation criteria.

About MiniMax M2

Prices from platform.minimax.io/docs/pricing/overview (read 2026-10-11). No cache discount published (set 1.0 — no discount). No batch discount published. Not yet benchmarked, so never recommended.

Other models from MiniMax

You can compare MiniMax M2 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