Model profile
minimax
New in 2026

MiniMax: MiniMax M2.5

MiniMax: MiniMax M2.5 is a budget text-first model from minimax with a heavy runtime profile, extended context posture, and the clearest fit around long-context research / agent workflows.

Best for: Long-context research / Agent workflowsHeavy latencyExtended contextBudget pricing
Intelligence
41.9

Benchmark blend

Coding
37.4

Dev workflow signal

Context
197K Tokens

Extended

Input Price
$0.30

Budget tier

Decision snapshot
53

MiniMax: MiniMax M2.5 currently reads as a budget text-first option with extended context and a heavy runtime profile.

Overall profile
Use-case specific
Best for
Long-context research / Agent workflows
Latency tier
Heavy
Price tier
Budget
Source coverage
OpenRouterArtificial Analysis

Decision Strip

Decision rail before the raw tables

Core buy-side signals stay in one pass. The rest of the page expands only after intelligence, speed, context, and price are clear.

Intelligence
41.9
42

General reasoning and benchmark headroom.

Limited
Speed
43 tok/s
38

TTFT 2.37s

Limited
Context
197K Tokens
76

How much prompt and task state can stay in view.

Competitive
Price
$0.30
86

$1.20 output / 1M

Efficient

Editorial Profile

MiniMax: MiniMax M2.5 in one narrative

Positioning, tradeoffs, and fit are consolidated into one read instead of repeating the same story across separate cards.

Use-case specificCoding score 37Math score 36

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon the coding expertise of M2.1 to extend into general office work, reaching fluency in generating and operating Word, Excel, and Powerpoint files, context switching between diverse software environments, and working across different agent and human teams. Scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp, M2.5 is also more token efficient than previous generations, having been trained to optimize its actions and output through planning.

Identity

minimax text-first profile

Positioning

Long-context research / Agent workflows with extended context and heavy runtime.

Cost posture

Efficient spend profile. More comfortable for sustained prompt volume if the capability fit is right.

Strengths
  • Large context headroom supports repo-wide prompts and long research sessions.

Tradeoffs
  • Budget-friendly input pricing is a strength, but raw capability may vary by workload.

  • Latency profile is better for deliberate runs than rapid back-and-forth chat.

  • Current metadata points to a text-first profile rather than a broad multimodal one.

Best fit
  • Long-context summarization, repo analysis, and policy or document review.

Compare Next

Similar profiles worth opening next

minimax

MiniMax: MiniMax M2.1

Intelligence
39.4
Context
197K Tokens
Input Price
$0.30
minimax

MiniMax: MiniMax M2

Intelligence
36.1
Context
197K Tokens
Input Price
$0.30
minimax

MiniMax: MiniMax M2-her

Intelligence
N/A
Context
66K Tokens
Input Price
$0.30

Benchmarks

Grouped by job-to-be-done

Only benchmark categories with actual signal are shown. Secondary values stay as simple definitions instead of nested micro-cards.

General intelligence

Broad reasoning, knowledge depth, and flagship benchmark posture.

Intelligence Index
41.9
GPQA
84.8%
HLE
19.1%
Coding

Software implementation, debugging quality, and coding benchmark signal.

Coding Index
37.4
SciCode
42.6%
Agent / tool use

Long-horizon execution quality and interactive benchmark evidence.

IFBench
71.6%
TAU2
95.3%
TerminalBench Hard
34.8%
LCR
66.0%

Specs & Pricing

Technical snapshot and cost posture

Specs stay neutral, pricing gets emphasis through values rather than extra containers. Raw provider internals remain in metadata at the end.

Technical snapshot
Context Window
197K Tokens
Vision
Text-first
Modalities
text->text, text
Tokenizer
Other
Max Completion
196608
Moderation
No
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Input Modalities
text
Output Modalities
text
Price architecture
Input
per 1M input tokens
$0.30
Output
per 1M output tokens
$1.20
Blended
AA 3:1 mix
$0.53

This model is relatively efficient on price. It is the easier fit when sustained prompt volume matters.

OR Cache Read
$0.00

Metadata

Raw source tables at the end

Verification details remain available, but the page no longer forces them ahead of the editorial read.