Skip to main content

    MiniMax

    MiniMax M2.5

    MiniMax M2.5 is a text model for coding agents with a 204,800-token context and published weights. MiniMax reported 51.3% on Multi-SWE-Bench at launch. Current first-party standard API pricing is $0.30/$1.20 per MTok (input/output); the separately served highspeed variant costs $0.60/$2.40. Serving speed and prices depend on the selected variant.

    204K tokens
    Text only
    Pro
    Provider
    MiniMax
    Context
    204K
    Catalog · As of Aug 11, 2026Stale · 31d old
    yno subscription tier
    Pro
    Released
    Feb 12, 2026
    Speed
    Fast
    Reasoning
    Advanced
    Modality
    Text only

    Benchmarks

    Quality

    AA Intelligence Index
    22.8points
    Artificial Analysis · Date unknownAge unknown
    GPQA Diamond
    84.8%
    Artificial Analysis · Date unknownAge unknown

    Speed and latency

    Output speed
    145tokens/s
    Artificial Analysis · As of Aug 11, 2026Stale · 31d old

    API pricing

    API input cost
    $0.30/ 1M tokens
    Artificial Analysis · Date unknownAge unknown
    API output cost
    $1.20/ 1M tokens
    Artificial Analysis · Date unknownAge unknown

    Benchmark variant: MiniMax-M2.5

    AA data retrieved Sep 11, 2026 · Artificial Analysis

    Indexes use points; evaluations use accuracy percentages. API measurements do not measure yno application performance. Methodology

    Capabilities

    • Code
    • Cost-Effective
    • High Throughput
    • Software Engineering

    Use cases

    • High-volume coding
    • Budget AI
    • Batch processing
    • Startup development

    Strengths

    • Vendor-reported Multi-SWE-Bench 51.3
    • 204,800-token context
    • Published weights
    • Standard and highspeed API variants

    Best for

    Teams selecting a text coding model and API serving variant for their workload

    Use MiniMax M2.5 in yno.ai

    No credit card required

    Related models

    MiniMax H3

    MiniMax

    MiniMax M3

    MiniMax

    MiniMax M2.7

    MiniMax

    Frequently asked

    What is MiniMax M2.5?
    MiniMax M2.5 is a text model for coding agents with a 204,800-token context and published weights. MiniMax reported 51.3% on Multi-SWE-Bench at launch. Current first-party standard API pricing is $0.30/$1.20 per MTok (input/output); the separately served highspeed variant costs $0.60/$2.40. Serving speed and prices depend on the selected variant.
    How much does MiniMax M2.5 cost in yno.ai?
    MiniMax M2.5 is available on the Pro tier of yno.ai.
    What can MiniMax M2.5 do?
    MiniMax M2.5 is best for Teams selecting a text coding model and API serving variant for their workload. Its main capabilities include Code, Cost-Effective, High Throughput, Software Engineering.
    How does MiniMax M2.5 compare to other models?
    MiniMax M2.5 excels at Vendor-reported Multi-SWE-Bench 51.3 and is recommended for High-volume coding, Budget AI, Batch processing, Startup development. See related models below.
    How do I use MiniMax M2.5 in yno.ai?
    Sign up for yno.ai, select MiniMax M2.5 from the model picker, and start chatting.