Skip to main content
Watch: I Built an AI App Without Leaving Databricks

MiniMax - Open weights

MiniMax-M2.7 pricing and specs

MiniMax-M2.7 is an open-weights model from MiniMax that costs $0.30 per 1M input tokens and $1.20 per 1M output tokens on the first-party API, with a 205K-token context window.

Last verified from platform.minimax.io. All sources

Input / 1M
$0.30
Output / 1M
$1.20
Context
205K tokens
Weights
Open

Pricing per 1M tokens

ItemPrice / 1M tokens
Input$0.30
Output$1.20
Cache read$0.06
Cache write (5 minutes)$0.375

Note: Being retired: MiniMax's models page says the M2.5 and M2.7 families stop being available to new users on 2026-10-19 and are retired on 2026-11-18 (M Plan and Token Plan requests get routed to M3.1 Flash Preview from 2026-10-19). Re-check or remove this entry after 2026-11-18. Text and tool-call input only (no image or video). Thinking cannot be turned off. max output is the documented max_tokens ceiling for non-M3 models (204800, recommended 65536) and thinking tokens count toward it. The weights license is non-commercial: commercial use needs prior written authorization from MiniMax. Pricing page shows a single Standard tier for this model.

Specs

Context window
204,800 tokens
Max output
204,800 tokens
Release date
Provider
MiniMax
API model id
MiniMax-M2.7
Vercel AI Gateway id
minimax/minimax-m2.7
Weights
Open weights
License
MiniMax M2.7 Non-Commercial License (Hugging Face license tag: other)
Weights download
huggingface.co

What MiniMax-M2.7 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 $0.30 = $0.30
  • Output0.1M x $1.20 = $0.12

$0.42per session

A chat app

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

  • Input20M x $0.30 = $6.00
  • Output5M x $1.20 = $6.00

$12.00per day

$360.00 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 $0.30 = $0.03
  • Output0.1M x $1.20 = $0.12

$0.204per session

Compare with

ModelInput / 1MOutput / 1M
MiniMax-M2.7 (this page)$0.30$1.20
DeepSeek V4.1 FlashDeepSeek$0.30$1.20
GPT-5.6 LunaOpenAI$0.20$1.20
MiniMax-M2.5MiniMax$0.30$1.20
MiniMax-M3MiniMax$0.30$1.20
MiniMax-M2.5-highspeedMiniMax$0.60$2.40
MiniMax-M2.7-highspeedMiniMax$0.60$2.40

Compare

Side-by-side pages with both models' prices, specs, cost examples and like-for-like benchmark rows.

FAQ

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

MiniMax-M2.7 costs $0.30 per 1M input tokens and $1.20 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's context window?

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

Are MiniMax-M2.7's weights open?

Yes. MiniMax-M2.7's weights are published at https://huggingface.co/MiniMaxAI/MiniMax-M2.7 under the MiniMax M2.7 Non-Commercial License (Hugging Face license tag: other).

When was MiniMax-M2.7 released?

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

Sources

Last verified from platform.minimax.io.

Newsletter

Get model price changes as they ship

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