MiniMax M2.7

Newer version available: MiniMax M3

Released
2026-03-18
Last refreshed
2026-10-17
Status
Researched 30d ago
Open sourceCommercial use: permittedCodingRAGAgentsLong contextClassificationJSON / Tool use
MiniMax releases · 12 in the last 12 months · this family litChangelog →
Specifications
Released
2026-03-18
Context
200K
Parameters
230B (10B active)
Architecture
Decoder Only
Specialization
general
Openness
Open source
License
MITOSI-approvedPermitted
Weights
Unknown
Code
Unknown
Created by

Developing AI for gaming and entertainment.

Minhang, Shanghai, China
Founded 2021
Website
Pricing
Output / 1M
$1.20
Input / 1M
$0.300

Cheapest of 4 routes · Fireworks AI

About

MiniMax M2.7 is MiniMax's self-improving frontier model, released March 18, 2026. It introduces native multi-agent collaboration, complex skill orchestration, and early recursive self-improvement capabilities. The model uses 10B active parameters, supports a 204,800-token context window, and was released alongside MiniMax-M2.7-highspeed, a 66% faster latency-optimized variant. Public provider listings price standard M2.7 at $0.30 per 1M input tokens and $1.20 per 1M output tokens. MiniMax M3 supersedes it for million-token, multimodal, and computer-use workflows, while M2.7 remains the lower-cost text-only route when 200K context is enough.

Providers(4)

Compare all 4

Compare API pricing across 4 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
Fireworks AI$0.300$1.20-
Serverless
Novita AI$0.300$1.20-
Serverless
OpenRouter$0.300$1.20read $0.060
Serverless
Vercel AI Gateway$0.300$1.20read $0.060
Serverless

Available via routers & gateways(1)

Capabilities

ReasoningJSON / Tool useStructured Outputs

Benchmark peer barsfor Coding

Benchmark scores(9)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
51.9pass@1 (best of 5 runs)Observed 2026-05-28—
56.2OpenRouter SWE-Pro listingObserved 2026-06-01—
57.0OpenRouter Terminal Bench 2 listingObserved 2026-06-01—
91.0AIME 2025 (accuracy)Observed 2026-06-07—
79.9LiveCodeBench v6 (accuracy)Observed 2026-06-07—
80.4Third-party Vals (accuracy)Observed 2026-06-07—
0.6xhighObserved 2026-06-30—
1415.0text_style_control overall 2026-10-22 (style control, default view)Observed 2026-10-26
Configuration: MiniMax-M2.7
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena text style control leaderboard, overall category, published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'MiniMax-M2.7': rank 141, Arena Score 1415.0 (95% CI 1411.7-1418.3), 87731 votes. Retrieved 2026-10-26.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

1354.0text creative_writing 2026-10-22Observed 2026-10-22
Configuration: MiniMax-M2.7
Harness: LMArena blind pairwise human votes, Bradley-Terry
Evaluator: LMArena
Confidence: confirmed
Notes: LMArena Text arena, Creative Writing category (no style control), board published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @a467e6b9, text config, latest split). Board entry 'MiniMax-M2.7' (category creative_writing in text/latest-00000-of-00001.parquet): rank 163 of 416, rating 1354.2 (95% CI 1348.2-1360.2), 15100 votes. Source: LMArena (CC BY 4.0). Retrieved 2026-10-27.
Source

Source: LMArena (lmarena.ai), CC BY 4.0

Migration checks

No linked migration route is available for this model yet.

Compare MiniMax M2.7 with other models