Identity and capabilities

Status
active
Local execution
Available weights · transformers · other Hardware requirements and licence restrictions apply.
Context window
1,000,000
Maximum output
512,000
Image input
Yes
Reasoning
Yes
Tool calling
Yes
Release date
First seen
2026-08-29 19:40:01Z UTC
Last verified

Current offers - prices in USD · per 1M tokens

Prices by provider, service tier, context and offer route
Fireworks AIHugging Face Inference Providers⊕ 4 routes ▾Novita AIOpenRouterTogether AIMiniMax
Standard · 0 < input tokens ≤ 524,287
Cached input——
$0.06
———
Input——
$0.3
———
Output——
$1.2
———
Standard · Input ≤ 512,000 tokens
Cached input—————
$0.06
Input—————
$0.3
Output—————
$1.2
Standard · Base contextDeepInfra
Cached input
$0.06
——
$0.06
$0.06
—
Input
$0.3
$0.28
—
$0.3
$0.3
—
Output
$1.2
$1.1
—
$1.2
$1.2
—
Standard · Input > 512,000 tokens
Cached input—————
$0.12
Input—————
$0.6
Output—————
$2.4
Standard · 524,287 < input tokens ≤ 999,999
Cached input——
$0.12
———
Input——
$0.6
———
Output——
$2.4
———
Batch
Input
$0.15
—————
Output
$0.6
—————
Priority · Input ≤ 512,000 tokens
Cached input—————
$0.09
Input—————
$0.45
Output—————
$1.8
Priority · Base context
Cached input
$0.09
—————
Input
$0.45
—————
Output
$1.8
—————
Priority · Input > 512,000 tokens
Cached input—————
$0.18
Input—————
$0.9
Output—————
$3.6
Hugging Face Inference Providers · 4 routes — show all prices

The main table shows DeepInfra: the lowest available starting token price for 2 input tokens per output token. Other input lengths, service tiers and usage ratios may favour another route.

Prices by provider, service tier, context and offer route
DeepInfra
Novita
Together AI
Fireworks AI
Input
$0.28
$0.3
$0.3
$0.3
Output
$1.1
$1.2
$1.2
$1.2

Active promotions

  • MiniMax-M3 permanent 50% off

    MiniMax · officially stated 50%

    Official source

Recent price changes

No price changes in the last 7 days.