MiniMax - Closed weights

MiniMax-M2.7-highspeed pricing and specs

Name: MiniMax-M2.7-highspeed
Author: MiniMax

MiniMax-M2.7-highspeed is a closed-weights model from MiniMax that costs $0.60 per 1M input tokens and $2.40 per 1M output tokens on the first-party API, with a 205K-token context window.

Last verified October 17, 2026 from platform.minimax.io. All sources

Input / 1M: $0.60
Output / 1M: $2.40
Context: 205K tokens
Weights: Closed

Pricing per 1M tokens

Item	Price / 1M tokens	Applies to
Input	$0.60	Standard requests
Output	$2.40	Standard requests
Cache read	$0.06	Standard requests
Cache write (5 minutes)	$0.375	Standard requests

Note: A faster serving variant of M2.7 (MiniMax says same performance, about 100 tps vs about 60 tps). Marked closed because MiniMax publishes no separate weights repo for the highspeed id; the base M2.7 weights are at huggingface.co/MiniMaxAI/MiniMax-M2.7. Being retired: unavailable to new users from 2026-10-19 and retired on 2026-11-18 per MiniMax's models page; re-check or remove after 2026-11-18. Text and tool-call input only. max output is the documented max_tokens ceiling for non-M3 models and includes thinking tokens. release date is the M2.7 series release (release notes list both MiniMax-M2.7 and M2.7-highspeed on 2026-03-18).

Specs

Context window: 204,800 tokens
Max output: 204,800 tokens
Release date: March 18, 2026
Provider: MiniMax
API model id: MiniMax-M2.7-highspeed
Vercel AI Gateway id: minimax/minimax-m2.7-highspeed
Weights: Closed weights

What MiniMax-M2.7-highspeed costs in practice

Worked from the standard list rates above, with the math shown so you can swap in your own token counts.

One agent session

1M input tokens and 100K output tokens, no caching.

Input1M x $0.60 = $0.60
Output0.1M x $2.40 = $0.24

$0.84per session

A chat app

10,000 requests a day at 2K input and 500 output tokens each.

Input20M x $0.60 = $12.00
Output5M x $2.40 = $12.00

$24.00per day

$720.00 per 30-day month

The same session at a 90% cache hit

90% of the input is read from the prompt cache. The one-time cache write premium is not included.

Cached input0.9M x $0.06 = $0.054
Uncached input0.1M x $0.60 = $0.06
Output0.1M x $2.40 = $0.24

$0.354per session

Compare with

Model	Input / 1M	Output / 1M	Context	Why listed
MiniMax-M2.7-highspeed (this page)	$0.60	$2.40	205K	-
MiniMax-M2.5-highspeedMiniMax	$0.60	$2.40	205K	Similar output price, same provider
Qwen3.5-27BAlibaba Cloud (Qwen)	$0.30	$2.40	262K	Similar output price
Qwen3.5-PlusAlibaba Cloud (Qwen)	$0.40	$2.40	1M	Similar output price
Amazon Nova 2 LiteAmazon	$0.30	$2.50	1M	Similar output price
MiniMax-M2.5MiniMax	$0.30	$1.20	205K	Same provider
MiniMax-M2.7MiniMax	$0.30	$1.20	205K	Same provider
MiniMax-M3MiniMax	$0.30	$1.20	1M	Same provider

FAQ

How much does MiniMax-M2.7-highspeed cost per million tokens?

MiniMax-M2.7-highspeed costs $0.60 per 1M input tokens and $2.40 per 1M output tokens on MiniMax's first-party API, per platform.minimax.io on October 17, 2026. Per 1M tokens, cache reads cost $0.06.

What is MiniMax-M2.7-highspeed's context window?

MiniMax-M2.7-highspeed has a 204,800-token context window and returns up to 204,800 output tokens per response.

Are MiniMax-M2.7-highspeed's weights open?

No. MiniMax-M2.7-highspeed is a closed-weights model. You call it through MiniMax's API as MiniMax-M2.7-highspeed or through Vercel AI Gateway as minimax/minimax-m2.7-highspeed.

When was MiniMax-M2.7-highspeed released?

MiniMax released MiniMax-M2.7-highspeed on March 18, 2026.

Sources

Last verified October 17, 2026 from platform.minimax.io.

Newsletter

One email per week. New model releases, price cuts and what they mean for your bill.