MiniMax M2.5

MiniMaxtext → textHugging Face OpenRouter

The cheapest provider for MiniMax M2.5 is Venice at $0.44 per 1M tokens (blended), charging $0.27 per 1M input and $0.95 per 1M output tokens. 7 providers serve it; the most expensive charges 2.4× as much. Context window: 200K tokens. Prices tracked since Oct 3, 2026.

Best price

$0.44

at Venice

Input / output

$0.27 / $0.95

per 1M tokens

Providers

2.4× spread

7 days

—

best price

30 days

—

best price

Context

200K

tokens

Providers

Active offers ranked by blended price. Bars are relative to the most expensive.

Provider prices for MiniMax: MiniMax M2.5, USD per 1M tokens
Provider	Input	Output	Blended	vs cheapest	Context	Uptime 1d	Price since
VeniceCheapest	$0.27	$0.95	$0.44	best	198K	93.0%	Oct 3
StreamLake −10% discount	$0.27	$1.08	$0.473	+7%	200K	99.5%	Oct 3
AtlasCloud fp8	$0.295	$1.20	$0.521	+18%	192K	99.7%	Oct 3
DigitalOcean	$0.30	$1.20	$0.525	+19%	64K	100%	Oct 3
Friendli	$0.30	$1.20	$0.525	+19%	192K	100%	Oct 3
Minimax fp8	$0.30	$1.20	$0.525	+19%	200K	100%	Oct 3
Novita fp8	$0.30	$1.20	$0.525	+19%	200K	99.5%	Oct 3
Minimaxhighspeed fp8	$0.60	$2.40	$1.05	+139%	200K	99.0%	Oct 3

VeniceCheapest
$0.44
$0.27 in · $0.95 out
best
198K ctx93.0% uptime
StreamLake
$0.473
$0.27 in · $1.08 out
+7%
200K ctx99.5% uptime−10% discount
AtlasCloud
$0.521
$0.295 in · $1.20 out
+18%
192K ctx99.7% uptimefp8
DigitalOcean
$0.525
$0.30 in · $1.20 out
+19%
64K ctx100% uptime
Friendli
$0.525
$0.30 in · $1.20 out
+19%
192K ctx100% uptime
Minimax
$0.525
$0.30 in · $1.20 out
+19%
200K ctx100% uptimefp8
Novita
$0.525
$0.30 in · $1.20 out
+19%
200K ctx99.5% uptimefp8
Minimax
highspeed
$1.05
$0.60 in · $2.40 out
+139%
200K ctx99.0% uptimefp8

Blended = (3 × input + output) / 4.

Price history

Hover to compare providers at any point in time. Click a legend item to hide it.

USD per 1M tokens · each step is a price change

Not enough history yet

Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.

Other pricing

Cache, reasoning and per-call fees. Token rates per 1M; others per unit.

Offered by	Cache read
Venice, Minimax +1	$0.03
StreamLake	$0.027
AtlasCloud, DigitalOcean +2	$0.06

Change log

Every recorded change for this model since Oct 3, 2026.

No changes yet

Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.

About this model

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1...

Released: Feb 12, 2026
First tracked: Oct 3, 2026
Canonical slug: minimax/minimax-m2.5-20260211
Weights: MiniMaxAI/MiniMax-M2.5