Skip to content
Model Pulse

Model

MiniMax-M2.5

Prior MiniMax coding model for agent workflows, office edits, and automation

44 providers · 45 listingsreleased open weights
$0.194
lowest input /M · GreenPT
$0.88
lowest output /M · DInference
229K
context window
204K
max output

Compare providers (sorted by listed input price)

34 of 44 providers publish a price for MiniMax-M2.5. The cheapest full-context option is DevPass (LLM Gateway) at $0.3/$1.2 per M. DInference lists lower but caps context at 200K.

49 listings
Cache read /MCache write /MCapabilitiesStatus
Deep Infra
MiniMaxAI/MiniMax-M2.5
$0.15$1.15$0.03—197Kreasoningtoolsno structuredno visiondeprecatedFeb 12, 2026
GreenPT
minimax-m2.5
$0.194$1.13$0.063—205Kreasoningtoolsno structuredno visionFeb 12, 2026
DInference
minimax-m2.5
$0.22$0.88——200Kreasoningtoolsno structuredno visionFeb 12, 2026
Venice AI
minimax-m25
$0.27$0.95$0.03—198Kreasoningtoolsno structuredno visionJun 11, 2026
OpenRouter
minimax/minimax-m2.5
$0.27$1.08$0.027—205Kreasoningtoolsstructuredno visionFeb 12, 2026
D.Run (China)
public/minimax-m25
$0.29$1.16——205Kreasoningtoolsno structuredno visionMar 1, 2025
Cortecs
minimax-m2.5
$0.296$1.19$0.075—196Kreasoningtoolsstructuredno visionFeb 12, 2026
TokenGo
minimax/minimax-m2.5
$0.3$1.20$0.03—205Kreasoningtoolsno structuredno visionFeb 12, 2026
NanoGPT
minimax/minimax-m2.5
$0.3$1.20$0.15—205Kreasoningtoolsstructuredno visionFeb 12, 2026
DigitalOcean
minimax-m2.5
$0.3$1.20$0.06—66Kreasoningtoolsno structuredvisionApr 16, 2026
SiliconFlow (China)
Pro/MiniMaxAI/MiniMax-M2.5
$0.3$1.22——192Kno reasoningtoolsstructuredno visionFeb 13, 2026
LLM Gatewayvariant
minimax/minimax-m2.5
$0.3$1.20$0.03—205Kreasoningtoolsno structuredno visionFeb 12, 2026
LLM Gatewayvariant
novita/minimax-m2.5
$0.3$1.20$0.03—205Kreasoningtoolsno structuredno visionFeb 12, 2026
OrcaRouter
minimax/minimax-m2.5
$0.3$1.20$0.03$0.375205Kreasoningtoolsno structuredno visionFeb 12, 2026
Alibaba (China)
MiniMax-M2.5
$0.3$1.20——205Kreasoningtoolsno structuredno visionFeb 12, 2026
NovitaAI
minimax/minimax-m2.5
$0.3$1.20$0.03—205Kreasoningtoolsstructuredno visionFeb 12, 2026
CloudFerro Sherlock
MiniMaxAI/MiniMax-M2.5
$0.3$1.20——196Kreasoningtoolsstructuredno visionMar 5, 2026
Hugging Face
MiniMaxAI/MiniMax-M2.5
$0.3$1.20$0.03—205Kreasoningtoolsno structuredno visionFeb 12, 2026
MiniMax (minimax.io)
MiniMax-M2.5
$0.3$1.20$0.03$0.375205Kreasoningtoolsno structuredno visionFeb 12, 2026
FrogBot
minimax-m2-5
$0.3$1.20$0.03—192Kno reasoningtoolsno structuredvisionFeb 22, 2025
1–20 of 49 listings

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M
$0.22▲ 100.0%
Best output /M
$0.88▼ 7.4%
Provider coverage
45
48 at the start · 24 snapshots
Best published input and output price historyDaily lowest published price per one million tokens. Accent is input price and violet is output price. The vertical scale starts at zero.$0$0.513$1.03Aug 21, 2026Sep 1, 2026Sep 14, 2026
Best input priceBest output priceAug 21, 2026 → Sep 14, 2026

Price badge

Current price badge for MiniMax-M2.5
![MiniMax-M2.5 price](https://www.vaanalytics.in/badge/minimax/MiniMax-M2.5.svg)
https://www.vaanalytics.in/badge/minimax/MiniMax-M2.5.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Recent changes

Changelog →
  • contextvia kilo · Sep 13, 2026
    • context: 205K → 200K tokens
    • output: 131K → 128K tokens
  • capabilityvia amazon-bedrock · Sep 13, 2026
    • name: MiniMax M2.5 → MiniMax-M2.5
    • description: MiniMax model for chat, coding, office work, and agentic tasks → Prior MiniMax coding model for agent workflows, office edits, and automation
    • structured_output: false → true
    • release_date: 2026-03-18 → 2026-02-12
  • repricedvia openrouter · Sep 13, 2026
    • output: 131K → 128K tokens
    • input: $0.3 → $0.27
    • output: $1.20 → $1.08
    • cache_read: $0.03 → $0.027
  • contextvia kilo · Sep 10, 2026
    • context: 200K → 205K tokens
    • output: 128K → 131K tokens
  • repricedvia openrouter · Sep 10, 2026
    • output: 128K → 131K tokens
    • input: $0.27 → $0.3
    • output: $1.08 → $1.20
    • cache_read: $0.027 → $0.03
  • new modelvia 302ai · Sep 9, 2026

Benchmarks

Scores a lab published about its own model are claims, not measurements. Rankings elsewhere on this site use independently measured scores only.

Weights

Licence unclearother229B params

No machine-readable licence on the model card. Check it before you rely on this. Weights download without an access request.

licence and gating from the Hugging Face model card ↗ — the card is authoritative, this is a summary

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.