Catalog Changes · 2026-10-14 00:06:23.691182

openai/gpt-oss-120b · 2026-10-14 00:06:23.691182 UTC

Current Model Listing

Hugging Face

70 Changed Fields

Field / Array Position Previous Value Observed Value
Providers[0] · First Token Latency Ms 517.4 304
Providers[0] · Throughput 382.48772684554103 421.8469517894887
Providers[1] · First Token Latency Ms 375.6 1949
Providers[1] · Pricing · Input 0.35 0.05
Providers[1] · Pricing · Output 0.75 0.25
Providers[1] · Provider cerebras novita
Providers[1] · Throughput 914.9654239990439 25.188916876574307
Providers[2] · First Token Latency Ms 193.6 292.2
Providers[2] · Pricing · Input 0.15 0.35
Providers[2] · Pricing · Output 0.6 0.75
Providers[2] · Provider together cerebras
Providers[2] · Throughput 103.63953255945133 1045.4414549707574
Providers[3] · First Token Latency Ms 438 202
Providers[3] · Provider fireworks-ai together
Providers[3] · Throughput 106.75279947530721 205.8231397274504
Providers[4] · Provider featherless-ai fireworks-ai
Providers[5] · First Token Latency Ms 407.8 Not Reported
Providers[5] · Pricing Object · See Fields Not Reported
Providers[5] · Pricing · Input 0.171 Not Reported
Providers[5] · Pricing · Output 0.684 Not Reported
Providers[5] · Provider scaleway featherless-ai
Providers[5] · Supports Structured Output True Not Reported
Providers[5] · Supports Tools True Not Reported
Providers[5] · Throughput 64.98311728662357 Not Reported
Providers[6] · Context Length 128072 Not Reported
Providers[6] · First Token Latency Ms 277 380
Providers[6] · Pricing · Input 0.1 0.171
Providers[6] · Pricing · Output 0.5 0.684
Providers[6] · Provider baseten scaleway
Providers[6] · Throughput 196.60113158966382 99.6831414409302
Providers[7] · Context Length 131072 128072
Providers[7] · First Token Latency Ms 333.5 404
Providers[7] · Pricing · Input 0.09 0.1
Providers[7] · Pricing · Output 0.47 0.5
Providers[7] · Provider ovhcloud baseten
Providers[7] · Throughput 39.117853504428766 216.3720684528861
Providers[4] · Context Length Not Reported 131072
Providers[4] · First Token Latency Ms Not Reported 385.6
Providers[4] · Pricing Not Reported Object · See Fields
Providers[4] · Pricing · Input Not Reported 0.15
Providers[4] · Pricing · Output Not Reported 0.6
Providers[4] · Supports Structured Output Not Reported True
Providers[4] · Supports Tools Not Reported True
Providers[4] · Throughput Not Reported 175.06425653586092
Providers[8] · @item Type Not Reported 5
Providers[8] · Context Length Not Reported 131072
Providers[8] · First Token Latency Ms Not Reported 381.4
Providers[8] · Is Free Not Reported False
Providers[8] · Is Model Author Not Reported False
Providers[8] · Pricing Not Reported Object · See Fields
Providers[8] · Pricing · Input Not Reported 0.09
Providers[8] · Pricing · Output Not Reported 0.47
Providers[8] · Provider Not Reported ovhcloud
Providers[8] · Status Not Reported live
Providers[8] · Supports Structured Output Not Reported True
Providers[8] · Supports Tools Not Reported True
Providers[8] · Throughput Not Reported 72.63190079516161
Providers[9] · @item Type Not Reported 5
Providers[9] · Context Length Not Reported 131072
Providers[9] · First Token Latency Ms Not Reported 3867
Providers[9] · Is Free Not Reported False
Providers[9] · Is Model Author Not Reported False
Providers[9] · Pricing Not Reported Object · See Fields
Providers[9] · Pricing · Input Not Reported 0.037
Providers[9] · Pricing · Output Not Reported 0.16999999999999998
Providers[9] · Provider Not Reported deepinfra
Providers[9] · Status Not Reported live
Providers[9] · Supports Structured Output Not Reported True
Providers[9] · Supports Tools Not Reported True
Providers[9] · Throughput Not Reported 48.21833261005835
← Back To Results

openai/gpt-oss-120b

openai/gpt-oss-120b

Hugging Face Catalog Changes

Last Observed: 2026-10-14 00:06:23.691182 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.

    10 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: 304.00 Throughput · Native Units: 421.85 Supports Tools: True

    Record Details
    Context Tokens
    131072
    First Token Latency · ms
    304
    Is Free
    False
    Is Model Author
    False
    Provider
    groq
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    421.8469517894887
    Pricing
    Input Price · Native Units
    0.15
    Output Price · Native Units
    0.75

    novita

    Input Price · Native Units: 0.05 Output Price · Native Units: 0.25 Context Tokens: 131,072 First Token Latency · ms: 1,949.00 Throughput · Native Units: 25.19 Supports Tools: True

    Record Details
    Context Tokens
    131072
    First Token Latency · ms
    1949
    Is Free
    False
    Is Model Author
    False
    Provider
    novita
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    25.188916876574307
    Pricing
    Input Price · Native Units
    0.05
    Output Price · Native Units
    0.25

    cerebras

    Input Price · Native Units: 0.35 Output Price · Native Units: 0.75 Context Tokens: 131,072 First Token Latency · ms: 292.20 Throughput · Native Units: 1,045.44 Supports Tools: True

    Record Details
    Context Tokens
    131072
    First Token Latency · ms
    292.2
    Is Free
    False
    Is Model Author
    False
    Provider
    cerebras
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    1045.4414549707574
    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: 202.00 Throughput · Native Units: 205.82 Supports Tools: True

    Record Details
    Context Tokens
    131072
    First Token Latency · ms
    202
    Is Free
    False
    Is Model Author
    False
    Provider
    together
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    205.8231397274504
    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: 385.60 Throughput · Native Units: 175.06 Supports Tools: True

    Record Details
    Context Tokens
    131072
    First Token Latency · ms
    385.6
    Is Free
    False
    Is Model Author
    False
    Provider
    fireworks-ai
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    175.06425653586092
    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: 380.00 Throughput · Native Units: 99.68 Supports Tools: True

    Record Details
    First Token Latency · ms
    380
    Is Free
    False
    Is Model Author
    False
    Provider
    scaleway
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    99.6831414409302
    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: 404.00 Throughput · Native Units: 216.37 Supports Tools: True

    Record Details
    Context Tokens
    128072
    First Token Latency · ms
    404
    Is Free
    False
    Is Model Author
    False
    Provider
    baseten
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    216.3720684528861
    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: 381.40 Throughput · Native Units: 72.63 Supports Tools: True

    Record Details
    Context Tokens
    131072
    First Token Latency · ms
    381.4
    Is Free
    False
    Is Model Author
    False
    Provider
    ovhcloud
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    72.63190079516161
    Pricing
    Input Price · Native Units
    0.09
    Output Price · Native Units
    0.47

    deepinfra

    Input Price · Native Units: 0.037 Output Price · Native Units: 0.16999999999999998 Context Tokens: 131,072 First Token Latency · ms: 3,867.00 Throughput · Native Units: 48.22 Supports Tools: True

    Record Details
    Context Tokens
    131072
    First Token Latency · ms
    3867
    Is Free
    False
    Is Model Author
    False
    Provider
    deepinfra
    Status
    live
    Supports Structured Output
    True
    Supports Tools
    True
    Throughput · Native Units
    48.21833261005835
    Pricing
    Input Price · Native Units
    0.037
    Output Price · Native Units
    0.16999999999999998
    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 304 False False Object · See Fields 0.15 0.75 groq live True True 421.8469517894887
    2 131072 1949 False False Object · See Fields 0.05 0.25 novita live True True 25.188916876574307
    3 131072 292.2 False False Object · See Fields 0.35 0.75 cerebras live True True 1045.4414549707574
    4 131072 202 False False Object · See Fields 0.15 0.6 together live True True 205.8231397274504
    5 131072 385.6 False False Object · See Fields 0.15 0.6 fireworks-ai live True True 175.06425653586092
    6 Not Reported Not Reported False False Not Reported Not Reported Not Reported featherless-ai live Not Reported Not Reported Not Reported
    7 Not Reported 380 False False Object · See Fields 0.171 0.684 scaleway live True True 99.6831414409302
    8 128072 404 False False Object · See Fields 0.1 0.5 baseten live True True 216.3720684528861
    9 131072 381.4 False False Object · See Fields 0.09 0.47 ovhcloud live True True 72.63190079516161
    10 131072 3867 False False Object · See Fields 0.037 0.16999999999999998 deepinfra live True True 48.21833261005835