MiniMax M2.7

Name: MiniMax M2.7
Price: 0.3 USD
Author: MiniMax

standard

MiniMax

MiniMax's compact 230B MoE reasoning model with only 10B active parameters. Punches well above its weight on intelligence benchmarks with fast inference and two API speed tiers.

Official page

reasoningcost-effectivemoe

Context

200K

Input / 1M

$0.30

Output / 1M

$1.20

Knowledge cutoff

2025-06

Capabilities

Code4/5

Reasoning4/5

Multilingual4/5

Safety3/5

Speed4/5

Modalities & Features

Vision (image input) No

Audio No

Video No

Function / tool calling Yes

JSON mode Yes

Extended thinking Yes

Context & Output

Context window200K

Max output tokens40.96K

Knowledge cutoff2025-06

Release date2026-03

API & Access

Open source No

Streaming Yes

Batch API No

Prompt caching No

Fine-tuning No

Benchmarks

MMLUGeneral knowledge

89.4%

GPQA DiamondHard science Q&A

N/A

MATHMath problem solving

N/A

AIME 2025Advanced math

N/A

GSM8KGrade-school math

N/A

HumanEvalCode generation

93.2%

LiveCodeBenchLive coding problems

N/A

SWE-bench VerifiedReal-world software

56.2%

HellaSwagCommonsense inference

N/A

Source: provider technical reports & independent evaluations. N/A = not yet published for this model.

Pricing (per 1M tokens)

Input$0.30

Output$1.20

Prices shown are list prices and may vary by provider plan. Always check official documentation for the latest pricing.