Skip to main content
AI Choice Engine

Model comparison

MiniMax M2.7 vs MiniMax M3

Two MiniMax tiers compared on the figures that decide which one a workload actually needs.

Catalog record checked September 26, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

MiniMax

MiniMax M2.7

Balanced · Open weights

vs

MiniMax

MiniMax M3

Frontier · Open weights

AI model capability comparison
SpecificationMiniMax M2.7MiniMax M3
ProviderMiniMaxMiniMax
TierBalancedFrontier
Context window205KWinner: 1M
Max outputNot verifiedUnverifiedNot verifiedUnverified
Input / 1M tokens$0.30$0.30
Output / 1M tokens$1.20$1.20
WeightsOpenOpen
ParametersNot disclosedUnverified428B total / 23B active (MoE)
Reasoning levelsNot verifiedUnverifiedlow, high, max
Modalitiestexttext, image, video
API model idMiniMax-M2.7MiniMax-M3
ReleasedMarch 18, 2026June 1, 2026
Artificial Analysis Intelligence Index (2026-09-26)22.8Winner: 29.2
Terminal-Bench 2.1 (2026-06-01)Not verifiedUnverified66

Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

  • 2026-09-26
    Artificial Analysis

    Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.

    Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check measuredAt.

  • 2026-06-01
    MiniMax blog (vendor, Terminus 2 scaffolding, 2h timeout)

    Agentic terminal work: multi-step tasks executed in a sandboxed shell environment.

    Comparable with caveatNot comparable with Terminal-Bench 3.0 or 4.0 (different task sets) or v1; harness configuration (container, time limits) also shifts results.

Pricing tiers

MiniMax M2.7: $0.30/$1.20 per MTok on MiniMax's pay-as-you-go API; cache read $0.06, cache write $0.375. Open weights on Hugging Face (licence terms not re-verified).

MiniMax M3: $0.30/$1.20 per MTok; open (community license). 428B/23B active MoE, native multimodal. Rate is the ≤512K-prompt tier; higher above.

BalancedOpen weightsRecord checked September 26, 2026

MiniMax M2.7

MiniMax M2.7 is MiniMax's current text-only open-weight model with a 204,800-token context, priced like M3.

Best for

  • Text-only agents
  • Open-weight deployments
  • Cost-sensitive coding

Watch out

Text-only and a 204,800-token context — M3 has 1M context and multimodal input at the same $0.30/$1.20 list price.

FrontierOpen weightsRecord checked September 26, 2026

MiniMax M3

MiniMax M3 is an open-weight (community license) 428B MoE with native multimodal and 1M context.

Best for

  • Open-weight deployments
  • Multimodal
  • Long-context

Watch out

Community license, not fully open; verify terms.

When the cheaper one wins

Both charge $1.20 per million output tokens at standard rates, so output price is not the split. Prefer the row whose “best for” line matches the job, then confirm the live vendor rate.

Run the model picker

Evidence confidence: High

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

  • Pricing verified on both sides — Input and output rates are verified for both models.
  • 2/5 core specs verified on both sides — Not published for at least one side: max output, parameter count, reasoning levels.
  • 1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
  • Verified within the last 90 days — Newest catalog check was 2 days ago.
  • Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Related comparisons

Diving deeper on one model? MiniMax M2.7 · MiniMax M3

Common questions

MiniMax M2.7 vs MiniMax M3

Answered from the verified figures on this page rather than general guidance.

Is MiniMax M2.7 or MiniMax M3 cheaper for input?
Both cost $0.30 per million input tokens at standard rates, so input price is not a deciding factor between them.
Is MiniMax M2.7 or MiniMax M3 cheaper for output?
Both cost $1.20 per million output tokens at standard rates, so output price is not a deciding factor between them.
Which has the larger context window, MiniMax M2.7 or MiniMax M3?
MiniMax M3 accepts 1M tokens against 205K for MiniMax M2.7. This only matters if you routinely send very long documents or large codebases.
Should I use MiniMax M2.7 or MiniMax M3?
MiniMax M2.7 is the balanced tier and MiniMax M3 the frontier tier. The useful question is whether your hardest task actually fails on the cheaper one — most production volume such as classification, extraction and summarisation does not.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

  • Context: MiniMax M3 takes 1M against 205K for MiniMax M2.7 — only decisive if your prompts approach the smaller window.
  • Measured capability: MiniMax M3 leads Artificial Analysis Intelligence Index 29.2 to 22.8 (measured 2026-09-26).
  • Positioning: MiniMax M2.7 sits in the balanced tier, MiniMax M3 in the frontier tier — most production volume (classification, extraction, summarisation) does not need the pricier tier.
Run the model pickerEstimate stack costAll model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.