Catalog Changes · 2026-10-13 18:02:53.393958

openai/gpt-oss-120b · 2026-10-13 18:02:53.393958 UTC

Current Model Listing

Hugging Face

70 Changed Fields

Field / Array Position Previous Value Observed Value
Providers[0] · First Token Latency Ms 648.2 517.4
Providers[0] · Throughput 389.1689417922172 382.48772684554103
Providers[1] · First Token Latency Ms 769.2 375.6
Providers[1] · Pricing · Input 0.05 0.35
Providers[1] · Pricing · Output 0.25 0.75
Providers[1] · Provider novita cerebras
Providers[1] · Throughput 220.95203461685674 914.9654239990439
Providers[2] · First Token Latency Ms 272 193.6
Providers[2] · Pricing · Input 0.35 0.15
Providers[2] · Pricing · Output 0.75 0.6
Providers[2] · Provider cerebras together
Providers[2] · Throughput 1031.9330639557775 103.63953255945133
Providers[3] · First Token Latency Ms 220.6 438
Providers[3] · Provider together fireworks-ai
Providers[3] · Throughput 178.59802056300728 106.75279947530721
Providers[4] · Context Length 131072 Not Reported
Providers[4] · First Token Latency Ms 344 Not Reported
Providers[4] · Pricing Object · See Fields Not Reported
Providers[4] · Pricing · Input 0.15 Not Reported
Providers[4] · Pricing · Output 0.6 Not Reported
Providers[4] · Provider fireworks-ai featherless-ai
Providers[4] · Supports Structured Output True Not Reported
Providers[4] · Supports Tools True Not Reported
Providers[4] · Throughput 150.2226129026179 Not Reported
Providers[5] · Provider featherless-ai scaleway
Providers[6] · First Token Latency Ms 451.6 277
Providers[6] · Pricing · Input 0.171 0.1
Providers[6] · Pricing · Output 0.684 0.5
Providers[6] · Provider scaleway baseten
Providers[6] · Throughput 66.1010103729553 196.60113158966382
Providers[7] · Context Length 128072 131072
Providers[7] · First Token Latency Ms 287.6 333.5
Providers[7] · Pricing · Input 0.1 0.09
Providers[7] · Pricing · Output 0.5 0.47
Providers[7] · Provider baseten ovhcloud
Providers[7] · Throughput 212.74091291682436 39.117853504428766
Providers[8] · @item Type 5 Not Reported
Providers[8] · Context Length 131072 Not Reported
Providers[8] · First Token Latency Ms 403.8 Not Reported
Providers[8] · Is Free False Not Reported
Providers[8] · Is Model Author False Not Reported
Providers[8] · Pricing Object · See Fields Not Reported
Providers[8] · Pricing · Input 0.09 Not Reported
Providers[8] · Pricing · Output 0.47 Not Reported
Providers[8] · Provider ovhcloud Not Reported
Providers[8] · Status live Not Reported
Providers[8] · Supports Structured Output True Not Reported
Providers[8] · Supports Tools True Not Reported
Providers[8] · Throughput 33.53534207051955 Not Reported
Providers[9] · @item Type 5 Not Reported
Providers[9] · Context Length 131072 Not Reported
Providers[9] · First Token Latency Ms 475 Not Reported
Providers[9] · Is Free False Not Reported
Providers[9] · Is Model Author False Not Reported
Providers[9] · Pricing Object · See Fields Not Reported
Providers[9] · Pricing · Input 0.037 Not Reported
Providers[9] · Pricing · Output 0.16999999999999998 Not Reported
Providers[9] · Provider deepinfra Not Reported
Providers[9] · Status live Not Reported
Providers[9] · Supports Structured Output True Not Reported
Providers[9] · Supports Tools True Not Reported
Providers[9] · Throughput 35.074342923048526 Not Reported
Providers[5] · First Token Latency Ms Not Reported 407.8
Providers[5] · Pricing Not Reported Object · See Fields
Providers[5] · Pricing · Input Not Reported 0.171
Providers[5] · Pricing · Output Not Reported 0.684
Providers[5] · Supports Structured Output Not Reported True
Providers[5] · Supports Tools Not Reported True
Providers[5] · Throughput Not Reported 64.98311728662357
Providers[6] · Context Length Not Reported 128072
← Back To Results

openai/gpt-oss-120b

openai/gpt-oss-120b

Hugging Face Catalog Changes

Last Observed: 2026-10-13 18:02:53.393958 UTC

    Catalog Identity And Metadata · 4
    Created
    API Details

    /created

    1754346786

    		 1754346786
    Id
    API Details

    /id

    openai/gpt-oss-120b

    		 openai/gpt-oss-120b
    Object
    API Details

    /object

    model

    		 model
    Reported Owner
    API Details

    /owned_by

    openai

    		 openai
    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

    1 items · source order preserved

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

    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.

    8 items · source order preserved

    groq

    Input Price · Native Units: 0.15 Output Price · Native Units: 0.75 Context Tokens: 131,072 First Token Latency · ms: 517.40 Throughput · Native Units: 382.49 Supports Tools: True

    Record Details
    Context Tokens
    131072
    First Token Latency · ms
    517.4
    Is Free
    False
    Is Model Author
    False
    Provider
    groq
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    382.48772684554103
    Pricing
    Input Price · Native Units
    0.15
    Output Price · Native Units
    0.75

    cerebras

    Input Price · Native Units: 0.35 Output Price · Native Units: 0.75 Context Tokens: 131,072 First Token Latency · ms: 375.60 Throughput · Native Units: 914.97 Supports Tools: True

    Record Details
    Context Tokens
    131072
    First Token Latency · ms
    375.6
    Is Free
    False
    Is Model Author
    False
    Provider
    cerebras
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    914.9654239990439
    Pricing
    Input Price · Native Units
    0.35
    Output Price · Native Units
    0.75

    together

    Input Price · Native Units: 0.15 Output Price · Native Units: 0.6 Context Tokens: 131,072 First Token Latency · ms: 193.60 Throughput · Native Units: 103.64 Supports Tools: True

    Record Details
    Context Tokens
    131072
    First Token Latency · ms
    193.6
    Is Free
    False
    Is Model Author
    False
    Provider
    together
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    103.63953255945133
    Pricing
    Input Price · Native Units
    0.15
    Output Price · Native Units
    0.6

    fireworks-ai

    Input Price · Native Units: 0.15 Output Price · Native Units: 0.6 Context Tokens: 131,072 First Token Latency · ms: 438.00 Throughput · Native Units: 106.75 Supports Tools: True

    Record Details
    Context Tokens
    131072
    First Token Latency · ms
    438
    Is Free
    False
    Is Model Author
    False
    Provider
    fireworks-ai
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    106.75279947530721
    Pricing
    Input Price · Native Units
    0.15
    Output Price · Native Units
    0.6

    featherless-ai

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

    scaleway

    Input Price · Native Units: 0.171 Output Price · Native Units: 0.684 First Token Latency · ms: 407.80 Throughput · Native Units: 64.98 Supports Tools: True

    Record Details
    First Token Latency · ms
    407.8
    Is Free
    False
    Is Model Author
    False
    Provider
    scaleway
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    64.98311728662357
    Pricing
    Input Price · Native Units
    0.171
    Output Price · Native Units
    0.684

    baseten

    Input Price · Native Units: 0.1 Output Price · Native Units: 0.5 Context Tokens: 128,072 First Token Latency · ms: 277.00 Throughput · Native Units: 196.60 Supports Tools: True

    Record Details
    Context Tokens
    128072
    First Token Latency · ms
    277
    Is Free
    False
    Is Model Author
    False
    Provider
    baseten
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    196.60113158966382
    Pricing
    Input Price · Native Units
    0.1
    Output Price · Native Units
    0.5

    ovhcloud

    Input Price · Native Units: 0.09 Output Price · Native Units: 0.47 Context Tokens: 131,072 First Token Latency · ms: 333.50 Throughput · Native Units: 39.12 Supports Tools: True

    Record Details
    Context Tokens
    131072
    First Token Latency · ms
    333.5
    Is Free
    False
    Is Model Author
    False
    Provider
    ovhcloud
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    39.117853504428766
    Pricing
    Input Price · Native Units
    0.09
    Output Price · Native Units
    0.47
    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 131072 517.4 False False Object · See Fields 0.15 0.75 groq live True True 382.48772684554103
    2 131072 375.6 False False Object · See Fields 0.35 0.75 cerebras live True True 914.9654239990439
    3 131072 193.6 False False Object · See Fields 0.15 0.6 together live True True 103.63953255945133
    4 131072 438 False False Object · See Fields 0.15 0.6 fireworks-ai live True True 106.75279947530721
    5 Not Reported Not Reported False False Not Reported Not Reported Not Reported featherless-ai live Not Reported Not Reported Not Reported
    6 Not Reported 407.8 False False Object · See Fields 0.171 0.684 scaleway live True True 64.98311728662357
    7 128072 277 False False Object · See Fields 0.1 0.5 baseten live True True 196.60113158966382
    8 131072 333.5 False False Object · See Fields 0.09 0.47 ovhcloud live True True 39.117853504428766