GPT-OSS Models by OpenAI
4 models2025Up to 131K ctxFrom $0.03/1M input
About
GPT-OSS is a family of 4 AI models by OpenAI, released in 2025.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
4 in view
Use when the workload needs structured outputs.
2025-09structured outputs
gpt-oss-120bCurrent
Use when the workload needs 131K context, 120B parameters, and tool use.
2025-08131K context120B parameterstool use
gpt-oss-20bCurrent
Use when the workload needs 131K context, 20B parameters, and tool use.
2025-08131K context20B parameterstool use
GPT OSS Safeguard 20BCurrent
Use when the workload needs safety, 131K context, and 20B parameters.
2025-08safety131K context20B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| OpenAI GPT OSS Safeguard 120B | Use when the workload needs structured outputs. | 2025-09 | structured outputs | Current |
| gpt-oss-120b | Use when the workload needs 131K context, 120B parameters, and tool use. | 2025-08 | 131K context120B parameterstool use | Current |
| gpt-oss-20b | Use when the workload needs 131K context, 20B parameters, and tool use. | 2025-08 | 131K context20B parameterstool use | Current |
| GPT OSS Safeguard 20B | Use when the workload needs safety, 131K context, and 20B parameters. | 2025-08 | safety131K context20B parameters | Current |
Release Timeline
2 release groups2025-09
1 current
OpenAI GPT OSS Safeguard 120B
Currentstructured outputs
2025-08
3 current
GPT OSS Safeguard 20B
Currentsafety131K context20B parameters
gpt-oss-120b
Current131K context120B parameterstool use
gpt-oss-20b
Current131K context20B parameterstool use
Specifications(4 models)
| Model | Released | Context | Parameters | Fn Calling | Tool Use | Structured Outputs |
|---|---|---|---|---|---|---|
| OpenAI GPT OSS Safeguard 120B | 2025-09 | — | — | No | No | Yes |
| gpt-oss-120b | 2025-08 | 131K | 120B | Yes | Yes | Yes |
| gpt-oss-20b | 2025-08 | 131K | 20B | Yes | Yes | Yes |
| GPT OSS Safeguard 20B | 2025-08 | 131K | 20B | Yes | Yes | Yes |
Available From(8 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| gpt-oss-20b | OpenRouter | $0.03 | $0.14 | Serverless |
| gpt-oss-120b | OpenRouter | $0.039 | $0.18 | Serverless |
| gpt-oss-20b | Fireworks AI | $0.07 | $0.3 | Serverless |
| gpt-oss-20b | GCP Vertex AI | $0.07 | $0.25 | Serverless |
| GPT OSS Safeguard 20B | AWS Bedrock | $0.07 | $0.2 | Serverless |
| gpt-oss-20b | GroqCloud | $0.075 | $0.3 | Serverless |
| GPT OSS Safeguard 20B | GroqCloud | $0.075 | $0.3 | Serverless |
| GPT OSS Safeguard 20B | OpenRouter | $0.075 | $0.3 | Serverless |
| gpt-oss-120b | GCP Vertex AI | $0.09 | $0.36 | Serverless |
| gpt-oss-20b | Replicate API | $0.09 | $0.36 | Serverless |
| gpt-oss-120b | Together AI | $0.15 | $0.6 | Serverless |
| gpt-oss-120b | Fireworks AI | $0.15 | $0.6 | Serverless |
| gpt-oss-120b | GroqCloud | $0.15 | $0.6 | Serverless |
| OpenAI GPT OSS Safeguard 120B | AWS Bedrock | $0.15 | $0.6 | Serverless |
| gpt-oss-120b | Replicate API | $0.18 | $0.72 | Serverless |
Frequently Asked Questions
- What is GPT-OSS used for?
- GPT-OSS is used for safety, agent workflows and tool use, and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does GPT-OSS compare to GPT Realtime 2?
- GPT-OSS by OpenAI is strongest where you need safety, while GPT Realtime 2 by OpenAI is the closest related family to check for translation. GPT-OSS has 4 listed variants and reaches up to 131K context, while GPT Realtime 2 reaches up to 131K context, so compare the specs and pricing tables before choosing a production model.
- Which GPT-OSS model should I use?
- For the lowest listed input price, start with gpt-oss-20b through OpenRouter at $0.03/1M input tokens. For the most capable/latest local choice, evaluate gpt-oss-120b with 131K context and tool use, function calling, and structured outputs.
