MiniMax-M2.7 pricing & specs

MiniMax · released 2026-03-18 · ● verified 2026-11-17 · deprecated

This model is deprecated. Cheapest compatible replacement: Gemma 4 E2B IT.

input / 1M$0.30
output / 1M$1.20
context204.8K
max output131.1K

MiniMax-M2.7 is a MiniMax model released on 2026-03-18. At $0.30 per million input tokens and $1.20 per million output tokens, its blended price of $0.525 per 1M tokens is lower than 65% of the 185 models we track. It offers text input, a 204.8K-token context window, built-in reasoning and tool calling. Its weights are open, and it is available from 3 tracked hosting providers.

// price history ($/1M tokens)

$1.38
input $/1Moutput $/1M2026-03-18 → 2026-11-17

// cheaper or similar alternatives

modelinoutctxvs MiniMax-M2.7
Gemma 4 E2B IT$0.04$0.08131.1K−90.5%
Qwen3.7 Flash$0.03$0.131M−89.5%
GPT OSS 20B$0.03$0.14131.1K−89%
GPT OSS 120B$0.037$0.17131.1K−86.6%
DeepSeek V4 Flash 0731$0.06$0.181.05M−82.9%

// price by host

hostin $/1Mout $/1M
DeepInfra$0.25$1.00
Novita AI$0.30$1.20
Together AI$0.30$1.20

// embed this price badge

Show the live price of MiniMax-M2.7 in your README or docs (updated daily):

MiniMax-M2.7 API price badge
[![MiniMax-M2.7 price](https://aisignals.dev/badge/minimax/minimax-m2.7.svg)](https://aisignals.dev/models/minimax/minimax-m2.7)

// faq

How much does MiniMax-M2.7 cost?

MiniMax-M2.7 costs $0.30 per million input tokens and $1.20 per million output tokens. At 50M input and 10M output tokens per month that is about $27.00.

What is the context window of MiniMax-M2.7?

204.8K tokens, with up to 131.1K output tokens per request.

Does MiniMax-M2.7 support prompt caching?

Yes. Cached input tokens cost $0.06 per million and cache writes cost $0.375 per million.

What are cheaper alternatives to MiniMax-M2.7?

Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out), GPT OSS 20B ($0.03 in / $0.14 out) offer the same input types and capabilities for less.

Is MiniMax-M2.7 open weights?

Yes. It is available from 3 tracked hosts; the cheapest is DeepInfra at $0.25 input and $1.00 output per million tokens.

// spec sheet

input / 1M
$0.30
output / 1M
$1.20
cache read / 1M
$0.06
cache write / 1M
$0.375
blended (3:1)
$0.525
context
204.8K
max output
131.1K
input types
text
reasoning
yes
tool calling
yes
structured output
no
open weights
yes
knowledge cutoff
n/a
price source
MiniMax

report a data error

// cost calculator

modelin $/1Mout $/1M= monthly
Gemma 4 E2B IT$0.04$0.08$2.80
Qwen3.7 Flash$0.03$0.13$2.80
GPT OSS 20B$0.03$0.14$2.90
MiniMax-M2.7$0.30$1.20$27.00

Base-tier list prices. Long-context tiers, caching and batch discounts are not included.