MiniMax M3

MiniMaxtext + image + video → textHugging Face OpenRouter

The cheapest provider for MiniMax M3 is CoreWeave at $0.413 per 1M tokens (blended), charging $0.23 per 1M input and $0.96 per 1M output tokens. 13 providers serve it; the most expensive charges 3.2× as much. Context window: 1M tokens. Prices tracked since Oct 3, 2026.

Best price

$0.413

at CoreWeave

Input / output

$0.23 / $0.96

per 1M tokens

Providers

3.2× spread

7 days

—

best price

30 days

—

best price

Context

tokens

Providers

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

Provider prices for MiniMax: MiniMax M3, USD per 1M tokens
Provider	Input	Output	Blended	vs cheapest	Context	Uptime 1d	Price since
CoreWeaveCheapest fp4	$0.23	$0.96	$0.413	best	256K	99.6%	Oct 3
GMICloud fp8·−20% discount	$0.24	$0.96	$0.42	+2%	1M	99.6%	Oct 3
DeepInfra fp8	$0.28	$1.10	$0.485	+18%	512K	99.8%	Oct 3
AtlasCloud fp8	$0.30	$1.20	$0.525	+27%	524K	99.7%	Oct 3
Minimax fp8	$0.30	$1.20	$0.525	+27%	512K	99.5%	Oct 3
Novita fp8	$0.30	$1.20	$0.525	+27%	1M	99.6%	Oct 3
Parasail fp8	$0.30	$1.20	$0.525	+27%	1M	99.2%	Oct 3
StreamLake fp8·−50% discount	$0.30	$1.20	$0.525	+27%	1M	98.1%	Oct 3
Together	$0.30	$1.20	$0.525	+27%	512K	99.0%	Oct 3
Venice fp8	$0.30	$1.20	$0.525	+27%	512K	95.8%	Oct 3
Mara	$0.60	$2.40	$1.05	+155%	1M	97.7%	Oct 3
SambaNova	$0.60	$2.40	$1.05	+155%	1M	94.4%	Oct 3
ModelRun fp4	$0.75	$3.00	$1.31	+218%	1M	99.1%	Oct 3

CoreWeaveCheapest
$0.413
$0.23 in · $0.96 out
best
256K ctx99.6% uptimefp4
GMICloud
$0.42
$0.24 in · $0.96 out
+2%
1M ctx99.6% uptimefp8·−20% discount
DeepInfra
$0.485
$0.28 in · $1.10 out
+18%
512K ctx99.8% uptimefp8
AtlasCloud
$0.525
$0.30 in · $1.20 out
+27%
524K ctx99.7% uptimefp8
Minimax
$0.525
$0.30 in · $1.20 out
+27%
512K ctx99.5% uptimefp8
Novita
$0.525
$0.30 in · $1.20 out
+27%
1M ctx99.6% uptimefp8
Parasail
$0.525
$0.30 in · $1.20 out
+27%
1M ctx99.2% uptimefp8
StreamLake
$0.525
$0.30 in · $1.20 out
+27%
1M ctx98.1% uptimefp8·−50% discount
Together
$0.525
$0.30 in · $1.20 out
+27%
512K ctx99.0% uptime
Venice
$0.525
$0.30 in · $1.20 out
+27%
512K ctx95.8% uptimefp8
Mara
$1.05
$0.60 in · $2.40 out
+155%
1M ctx97.7% uptime
SambaNova
$1.05
$0.60 in · $2.40 out
+155%
1M ctx94.4% uptime
ModelRun
$1.31
$0.75 in · $3.00 out
+218%
1M ctx99.1% uptimefp4

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
CoreWeave	$0.05
GMICloud	$0.048
DeepInfra	$0.056
AtlasCloud, Minimax +6	$0.06
ModelRun	$0.15

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-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...

Released: May 31, 2026
First tracked: Oct 3, 2026
Canonical slug: minimax/minimax-m3-20260531
Weights: MiniMaxAI/Minimax-M3