OpenAI

gpt-oss-120b

openai/gpt-oss-120b

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

gpt-oss-120b

reasoning open weights tools

OpenAI openai/gpt-oss-120b

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

Input $/1M: $0.04
Output $/1M: $0.17
Context: 131K
Max output: 118K
Released: Aug 5, 2025
Modalities: text

Intelligence index16

Coding index30

Agentic index6

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs gpt-oss-120b
targets:
  - id: gpt-oss-120b
    kind: llm
    name: gpt-oss-120b
    metadata:
      model: openai/gpt-oss-120b          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 131072
    cost:
      usd_per_1k_tokens: 0.000104

Price among OpenAI models

Input list price per million tokens; gpt-oss-120b is the cheapest of 13 listed.

More from OpenAI

Other models by the same vendor in the catalogue.