GPT-OSS Models by OpenAI

OpenAIApache 2.0Open source
OpenAI releases · 51 in the last 12 monthsChangelog →
4 models2025Up to 131k ctxFrom $0.030/1M input

Last refreshed 2026-05-22. Next refresh: weekly.

Details

ResearcherOpenAI
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models4
Released2025
Max context131k

Capabilities

JSON / Tool use3 of 4 models
Structured OutputsAll models

About

GPT-OSS (gpt-oss) is OpenAI’s open-weight language-model pair, gpt-oss-120b and gpt-oss-20b, aimed at local and self-hosted reasoning and agent workflows. Both are text MoE Transformers with adjustable reasoning effort, tool use, and full chain-of-thought for developers; OpenAI highlights efficient single-GPU or edge-style deployment depending on size. Weights are distributed for download and third-party hosting, with a model card covering architecture and safety evaluation.

Decision facts

Best fit
safetyJSON / Tool usestructured outputs
Capability starting point
gpt-oss-120b with 131k context and JSON / Tool use and structured outputs
Lowest tracked input
gpt-oss-20b · $0.030/1M · OpenRouter
Closest related family
GPT-5

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

4 in view
OpenAI GPT OSS Safeguard 120BCurrent

Use when the workload needs safety, 120B parameters, and structured outputs.

2025-09safety120B parametersstructured outputs
gpt-oss-120bCurrent

Use when the workload needs 131k context, 120B parameters, and JSON / Tool use.

2025-08131k context120B parametersJSON / Tool use
gpt-oss-20bCurrent

Use when the workload needs 131k context, 20B parameters, and JSON / Tool use.

2025-08131k context20B parametersJSON / Tool use
GPT OSS Safeguard 20BCurrent

Use when the workload needs safety, 131k context, and 20B parameters.

2025-08safety131k context20B parameters

Release Timeline

2 release groups
2025-09
1 current
OpenAI GPT OSS Safeguard 120B
safety120B parametersstructured outputs
Current
2025-08
3 current
GPT OSS Safeguard 20B
safety131k context20B parameters
Current
gpt-oss-120b
131k context120B parametersJSON / Tool use
Current
gpt-oss-20b
131k context20B parametersJSON / Tool use
Current

Specifications(4 models)

GPT-OSS model specifications comparison
ModelReleasedContextParametersJSON / Tool useStructured Outputs
OpenAI GPT OSS Safeguard 120B2025-09—120BNoYes
gpt-oss-120b2025-08131k120BYesYes
gpt-oss-20b2025-08131k20BYesYes
GPT OSS Safeguard 20B2025-08131k20BYesYes

Pricing

GPT-OSS model pricing by provider
ModelProviderInput / 1MOutput / 1MType
gpt-oss-20bOpenRouter$0.03$0.14Serverless
gpt-oss-120bOpenRouter$0.039$0.18Serverless
gpt-oss-20bNovita AI$0.04$0.15Serverless
gpt-oss-20bFeatherless$0.04$0.15Serverless
gpt-oss-20bVercel AI Gateway$0.05$0.2Serverless
gpt-oss-120bNovita AI$0.05$0.25Serverless
gpt-oss-20bFireworks AI$0.07$0.3Serverless
gpt-oss-20bGCP Vertex AI$0.07$0.25Serverless
GPT OSS Safeguard 20BAWS Bedrock$0.07$0.2Serverless
gpt-oss-20bGroqCloud$0.075$0.3Serverless
GPT OSS Safeguard 20BGroqCloud$0.075$0.3Serverless
GPT OSS Safeguard 20BOpenRouter$0.075$0.3Serverless
GPT OSS Safeguard 20BVercel AI Gateway$0.075$0.3Serverless
gpt-oss-120bGCP Vertex AI$0.09$0.36Serverless
gpt-oss-20bReplicate API$0.09$0.36Serverless
gpt-oss-120bTogether AI$0.15$0.6Serverless
gpt-oss-120bFireworks AI$0.15$0.6Serverless
gpt-oss-120bGroqCloud$0.15$0.6Serverless
OpenAI GPT OSS Safeguard 120BAWS Bedrock$0.15$0.6Serverless
gpt-oss-120bFeatherless$0.15$0.6Serverless
gpt-oss-120bReplicate API$0.18$0.72Serverless
gpt-oss-20bCloudflare Workers AI$0.2$0.3Serverless
gpt-oss-120bCloudflare Workers AI$0.35$0.75Serverless
gpt-oss-120bVercel AI Gateway$0.35$0.75Serverless

Popular comparisons in this family