MiniMax

MiniMax M2.5

The prior-generation MiniMax M2.5 agent model, available via OpenRouter and inference gateways at the standard M-series rate card.

ActiveAvailable from 20 providers
Tool callingCan invoke external tools and APIs (function calling) mid-response.Structured outputCan return JSON or schema-constrained responses instead of free text.ReasoningUses extended thinking / chain-of-thought for harder multi-step problems.Effort controlLets you dial thinking depth (low / medium / high) to trade cost for quality.Fine-tuningSupports training a custom variant on your own data (vendor fine-tune API or self-hosted open weights).

Source: MiniMax pay-as-you-go pricing, MiniMax models

Price per 1M tokens via Inceptron (OpenRouter)
$0.15 in / $0.9 out
Context window204,800
Max output204,800
Cache read$0.05 / M
ModalitiesText → Text
Priced across20 providers

Pricing

Every billing leg from the live catalog, in USD per 1M tokens.

Billing legRate
Input$0.15 / M
Output$0.9 / M
Cache read$0.05 / M

Cost calculator

Billing-grade math over the rate card above, including the thinking tokens most estimates miss.

Hidden reasoning tokens bill as output. 1.0x = thinking off. Medium-effort reasoning typically lands near 3x; heavy reasoning runs 6x to 8x. Set it to match your workload.

Estimated monthly cost
$84.00
at current list prices
Fresh input$30.00
Cached input$0.00
Output incl. thinking$54.00
Track this automatically →

Compare providers

The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.

PlatformInput / MOutput / MCache read / MBatchAccess
InceptronLowest
$0.15$0.9$0.05—via OpenRouter
DigitalOcean
$0.225$0.9$0.06—via OpenRouter
Mara
$0.24$0.96——via OpenRouter
Venice
$0.27$0.95$0.03—via OpenRouter
DeepInfra
$0.15$1.15$0.03—via OpenRouter
Chutes
$0.15$1.2$0.075—via OpenRouter
StreamLake
$0.27$1.08$0.027—via OpenRouter
AtlasCloud
$0.295$1.2$0.06—via OpenRouter
Fireworks AI
$0.3$1.2$0.03—Direct
AWS Bedrock
$0.3$1.2—✓Direct
Friendli
$0.3$1.2$0.06—via OpenRouter
MiniMax
$0.3$1.2$0.03—via OpenRouter
Nebius
$0.3$1.2——via OpenRouter
Novita
$0.3$1.2$0.03—via OpenRouter
Parasail
$0.3$1.2$0.03—via OpenRouter
SiliconFlow
$0.3$1.2$0.03—via OpenRouter
Wandb
$0.3$1.2$0.3—via OpenRouter
AWS Bedrock · Regional
from$0.3$1.2—✓Direct
Phala
$0.2$1.38$0.075—via OpenRouter
Azure AI Foundry (Fireworks)
$0.33$1.32$0.033—Direct

Regional deployments are priced per region; the lowest available region rate is shown.

Price history

Has this model gotten cheaper or more expensive?

No changePriced at $0.15 / $0.9 per 1M since July 10, 2026.

More from MiniMax

Other models from the same provider.

MiniMax M3
minimax/minimax-m3
$0.3 / $1.2 in / out per 1M
MiniMax M2.7
minimax/minimax-m2.7
$0.25 / $1 in / out per 1M

Stop estimating. Track it.

SuperPenguin meters every MiniMax M2.5 call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.

Get started free

Rates are generated from SuperPenguin's live pricing catalog.