Appndo
All models

gpt-oss-120b

OpenAIOpen weights131K contextTool callingReasoningWeb search

LMArena score 1365 · #191 overall · #191 in coding (2026-10-13)

Lowest price, from W&B Inference

Pricing page

Per million tokens

Input
$0.03
Output
$0.17
Cached input
—
Batch input / output
—
  • Up to 131K output tokens per request.

Estimate your monthly cost

Est. per month = input tokens × input price + output tokens × output price. Prices are per million tokens, so 10M input tokens at $3.00 cost $30.

From W&B Inference: $0.64 a month.

Where to buy it (21)

Sorted by your monthly estimate. Prices per million tokens.

  • W&B InferenceCheapest

    Input / output
    $0.03 / $0.17
    Context
    131K
    Per month
    $0.64

    wandb/openai/gpt-oss-120b

  • DeepInfra

    Input / output
    $0.037 / $0.17
    Context
    131K
    Per month
    $0.71

    deepinfra/openai/gpt-oss-120b

  • Novita AI

    Input / output
    $0.05 / $0.25
    Context
    131K
    Per month
    $1.00

    novita/openai/gpt-oss-120b

  • Sail

    Input / output
    $0.06 / $0.40
    Context
    131K
    Per month
    $1.40

    sail/openai/gpt-oss-120b

  • Ovhcloud

    Input / output
    $0.08 / $0.40
    Context
    131K
    Per month
    $1.60

    ovhcloud/gpt-oss-120b

  • Google Vertex AI

    Input / output
    $0.09 / $0.36
    Context
    131K
    Per month
    $1.62

    vertex_ai/openai/gpt-oss-120b-maas

  • Baseten

    Input / output
    $0.10 / $0.50
    Context
    128K
    Per month
    $2.00

    baseten/openai/gpt-oss-120b

  • Microsoft Foundry

    Input / output
    $0.15 / $0.60
    Context
    131K
    Per month
    $2.70

    azure_ai/gpt-oss-120b

  • Amazon Bedrock Mantle

    Input / output
    $0.15 / $0.60
    Context
    131K
    Per month
    $2.70

    bedrock_mantle/openai.gpt-oss-120b

  • Fireworks AI

    Input / output
    $0.15 / $0.60
    Context
    131K
    Per month
    $2.70

    fireworks_ai/accounts/fireworks/models/gpt-oss-120b

  • Fireworks AI

    Input / output
    $0.15 / $0.60
    Context
    131K
    Per month
    $2.70

    fireworks_ai/gpt-oss-120b

  • Groq

    Input / output
    $0.15 / $0.60
    Context
    131K
    Per month
    $2.70

    groq/openai/gpt-oss-120b

  • Nebius

    Input / output
    $0.15 / $0.60
    Context
    131K
    Per month
    $2.70

    nebius/openai/gpt-oss-120b

  • Scaleway

    Input / output
    $0.15 / $0.60
    Context
    128K
    Per month
    $2.70

    scaleway/openai/gpt-oss-120b

  • Tensormesh

    Input / output
    $0.15 / $0.60
    Context
    131K
    Per month
    $2.70

    tensormesh/openai/gpt-oss-120b

  • Together AI

    Input / output
    $0.15 / $0.60
    Context
    131K
    Per month
    $2.70

    together_ai/openai/gpt-oss-120b

  • IBM watsonx

    Input / output
    $0.159 / $0.636
    Context
    131K
    Per month
    $2.86

    watsonx/openai/gpt-oss-120b

  • Replicate

    Input / output
    $0.18 / $0.72
    Context
    —
    Per month
    $3.24

    replicate/openai/gpt-oss-120b

  • SambaNova

    Input / output
    $0.22 / $0.59
    Context
    131K
    Per month
    $3.38

    sambanova/gpt-oss-120b

  • Cerebras

    Input / output
    $0.35 / $0.75
    Context
    131K
    Per month
    $5.00

    cerebras/gpt-oss-120b

  • Cloudflare Workers AI

    Input / output
    $0.35 / $0.75
    Context
    128K
    Per month
    $5.00

    cloudflare/@cf/openai/gpt-oss-120b

  • Crusoe

    Input / output
    $0.80 / $0.80
    Context
    131K
    Per month
    $9.60

    crusoe/openai/gpt-oss-120b

Cloud and hosted sellers may add regional pricing, minimums or platform fees. Supports: Tool calling, Reasoning, Web search.

Similar models