Catalog Changes · 2026-10-13 18:02:53.513647

MiniMaxAI/MiniMax-M3 · 2026-10-13 18:02:53.513647 UTC

Current Model Listing

Hugging Face

8 Changed Fields

Field / Array Position Previous Value Observed Value
Providers[0] · First Token Latency Ms 884.6 908.2
Providers[0] · Throughput 72.53277697313348 65.0706417441477
Providers[1] · First Token Latency Ms 327.6 1394
Providers[1] · Throughput 42.78203700487718 28.485095689129917
Providers[2] · First Token Latency Ms 902.8 728.2
Providers[2] · Throughput 104.27615797659146 95.24579282248374
Providers[4] · First Token Latency Ms 395 643.6
Providers[4] · Throughput 25.234045774559036 21.941955584193614
← Back To Results

MiniMaxAI/MiniMax-M3

MiniMaxAI/MiniMax-M3

Hugging Face Catalog Changes

Last Observed: 2026-10-13 18:02:53.513647 UTC

    Catalog Identity And Metadata · 4
    Created
    API Details

    /created

    1780386571

    1780386571
    Id
    API Details

    /id

    MiniMaxAI/MiniMax-M3

    MiniMaxAI/MiniMax-M3
    Object
    API Details

    /object

    model

    model
    Reported Owner
    API Details

    /owned_by

    MiniMaxAI

    MiniMaxAI
    API Structure And Container Types
    Architecture
    API Details

    /architecture

    Object · See Fields

    Object · See Fields
    Architecture · Input Modalities
    API Details

    /architecture/input_modalities

    Array · See Items

    Array · See Items
    Architecture · Output Modalities
    API Details

    /architecture/output_modalities

    Array · See Items

    Array · See Items
    Hosting Providers
    API Details

    /providers

    Array · See Items

    Array · See Items

    Architecture · Input Modalities

    2 items · source order preserved

    • text
    • image
    API Details
    Item /architecture/input_modalities/*
    1 text
    2 image

    Architecture · Output Modalities

    1 items · source order preserved

    • text
    API Details
    Item /architecture/output_modalities/*
    1 text

    Hosting Providers

    Input and output prices are USD per million tokens. Latency is reported in milliseconds; other values retain their API units.

    5 items · source order preserved

    novita

    Input Price · Native Units: 0.3 Output Price · Native Units: 1.2 Context Tokens: 1,000,000 First Token Latency · ms: 908.20 Throughput · Native Units: 65.07 Supports Tools: True

    Record Details
    Context Tokens
    1000000
    First Token Latency · ms
    908.2
    Is Free
    False
    Is Model Author
    False
    Provider
    novita
    Status
    live
    Supports Structured Output
    False
    Supports Tools
    True
    Throughput · Native Units
    65.0706417441477
    Pricing
    Input Price · Native Units
    0.3
    Output Price · Native Units
    1.2

    together

    Input Price · Native Units: 0.3 Output Price · Native Units: 1.2 Context Tokens: 524,288 First Token Latency · ms: 1,394.00 Throughput · Native Units: 28.49 Supports Tools: True

    Record Details
    Context Tokens
    524288
    First Token Latency · ms
    1394
    Is Free
    False
    Is Model Author
    False
    Provider
    together
    Status
    live
    Supports Structured Output
    False
    Supports Tools
    True
    Throughput · Native Units
    28.485095689129917
    Pricing
    Input Price · Native Units
    0.3
    Output Price · Native Units
    1.2

    fireworks-ai

    Input Price · Native Units: 0.3 Output Price · Native Units: 1.2 Context Tokens: 512,000 First Token Latency · ms: 728.20 Throughput · Native Units: 95.25 Supports Tools: True

    Record Details
    Context Tokens
    512000
    First Token Latency · ms
    728.2
    Is Free
    False
    Is Model Author
    False
    Provider
    fireworks-ai
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    95.24579282248374
    Pricing
    Input Price · Native Units
    0.3
    Output Price · Native Units
    1.2

    featherless-ai

    Record Details
    Is Free
    False
    Is Model Author
    False
    Provider
    featherless-ai
    Status
    live

    deepinfra

    Input Price · Native Units: 0.28 Output Price · Native Units: 1.1 Context Tokens: 524,288 First Token Latency · ms: 643.60 Throughput · Native Units: 21.94 Supports Tools: True

    Record Details
    Context Tokens
    524288
    First Token Latency · ms
    643.6
    Is Free
    False
    Is Model Author
    False
    Provider
    deepinfra
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    21.941955584193614
    Pricing
    Input Price · Native Units
    0.28
    Output Price · Native Units
    1.1
    API Details
    Item /providers/*/context_length /providers/*/first_token_latency_ms /providers/*/is_free /providers/*/is_model_author /providers/*/pricing /providers/*/pricing/input /providers/*/pricing/output /providers/*/provider /providers/*/status /providers/*/supports_structured_output /providers/*/supports_tools /providers/*/throughput
    1 1000000 908.2 False False Object · See Fields 0.3 1.2 novita live False True 65.0706417441477
    2 524288 1394 False False Object · See Fields 0.3 1.2 together live False True 28.485095689129917
    3 512000 728.2 False False Object · See Fields 0.3 1.2 fireworks-ai live True True 95.24579282248374
    4 Not Reported Not Reported False False Not Reported Not Reported Not Reported featherless-ai live Not Reported Not Reported Not Reported
    5 524288 643.6 False False Object · See Fields 0.28 1.1 deepinfra live True True 21.941955584193614