LLM Cost
MinimaxTool use

MiniMax M2.5 pricing

If you are budgeting for MiniMax M2.5, start with the numbers below. We index 8 provider prices. Cheapest input is $0.270 per million tokens. Cheapest output is $1.08 per million tokens. The model lists a 1.0M context window in our data.

1.0M context·8 providers·save up to 10% vs native via Openrouter·verified Oct 6, 2026
Estimate costCompare with GPT-4oPick any other model
Best input$0.270per 1M tokens · Openrouter
Best output$1.08per 1M tokens · Openrouter

Pricing across providers

Use this table to read MiniMax M2.5 list prices. We show 8 sources right now. Lowest input in the grid: Openrouter. The chart below the table helps when output prices are much higher than input prices.

B
Baseten
Input / 1M
$0.300
Output / 1M
$1.20
F
Friendliai
Input / 1M
$0.300
Output / 1M
$1.20
Cached in: $0.060
N
Nebius
Input / 1M
$0.300
Output / 1M
$1.20
N
Novita
Input / 1M
$0.300
Output / 1M
$1.20
Cached in: $0.030
O
Openrouter
Input / 1M
$0.270
Output / 1M
$1.08
Cached in: $0.027
T
Tensormesh
Input / 1M
$0.300
Output / 1M
$1.20
Cached in: $0.0000
W
Wandb
Input / 1M
$0.300
Output / 1M
$1.20
M
Minimaxnative
Input / 1M
$0.300
Output / 1M
$1.20
Cached in: $0.030

Input vs output · per provider

Cost calculator

Use this block to stress test MiniMax M2.5 cost without a spreadsheet. All estimates come from public list rates in this page.

Provider

In: $0.300/M·Out: $1.20/M

0.030000¢ / req

0.060000¢ / req

Daily
$9.00
Monthly
$270
Annual
$3.3K

Model specifications

Context length, caps, and capability flags for MiniMax M2.5. Values follow the main provider (Minimax) record in our index.

Context window
1,000,000 tokens
Max output
8,192 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
N/A
Primary provider
Minimax
Model family
N/A

Compare MiniMax M2.5

Jump into a comparison when you want one table for two models instead of two tabs. 6 curated matches for MiniMax M2.5.

Locked

Compare with

Pick a model on both sides.

Popular MiniMax M2.5 comparisons

Frequently asked questions

Read these after the table if you want plain language around MiniMax M2.5 rates.

MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens via the native API. Prompt caching reduces input costs to $0.03/M tokens.

Related models

Models close to MiniMax M2.5 by family, provider, and context window — each with live pricing in our catalog.

Fw Minimax M2 5
Minimax
$1.32/M out1000K ctx
Fw Minimax M3
Minimax
$1.32/M out512K ctx
MiniMax M1
Minimax
$2.20/M out1000K ctx
Minimax M2 1 Lightning
Minimax
$2.40/M out1000K ctx
Minimax M2 5 Highspeed
Minimax
$2.40/M out205K ctx
Minimax M2 5 Lightning
Minimax
$2.40/M out1000K ctx
MiniMax M2.7
Minimax
$0.55/M out205K ctx
Minimax M2 7 Highspeed
Minimax
$2.40/M out205K ctx
Minimax M2p1
Minimax
$1.20/M out205K ctx
Minimax Minimax M2 5
Minimax
$1.44/M out1000K ctx
MiniMax-01
Minimax
$1.10/M out1000K ctx
Minimax M1 80k
Minimax
$0.10/M out4K ctx
MiniMax M2
Minimax
$1.20/M out200K ctx
MiniMax M2.1
Minimax
$1.20/M out197K ctx
MiniMax M2-her
Minimax
$1.20/M out66K ctx
Minimax M2 Maas
Minimax
$1.20/M out197K ctx
Minimax M2p7
Minimax
197K ctx
MiniMax M3
Minimax
$1.20/M out1049K ctx
Minimax Minimax M2
Minimax
$1.20/M out128K ctx
Minimax Minimax M2 1
Minimax
$1.44/M out196K ctx
GPT-4o
OpenAI · GPT-4
$10.00/M out128K ctx
GPT-4o mini
OpenAI · GPT-4
$0.60/M out128K ctx
Claude Sonnet 4.6
Anthropic · Claude Sonnet
$15.00/M out200K ctx
Gemini 2.0 Flash
Google · Gemini 2.0
$0.40/M out1049K ctx