OpenAI gpt-oss 120B
OpenAIgpt-oss-120b
Released Aug 5, 2025
Providers
9
Context
131K
Input
$0.00/M
Output
$0.00/M
BAA-eligible on 2 of 9 providersPHI requires a signed BAA from Concentrate and HIPAA-enabled organization.
Aliases:gpt-ossopenai-gpt-oss-120b
OpenAI's GPT-OSS open-weight model designed for powerful reasoning, agentic tasks, and versatile developer use cases.
azure/gpt-oss-120bQuantUnspecified
- Input
- $0.15/M
- Output
- $0.60/M
- Context
- 131K
- Max out
- 33K
- Caching
- Not offered
- Thinking out
- $0.60/M
FlexPriority / Fast
bluelobster/gpt-oss-120bQuantUnspecified
- Input
- $0.00/M
- Output
- $0.00/M
- Context
- 131K
- Max out
- 66K
- Caching
- Not offered
- Thinking out
- $0.00/M
FlexPriority / Fast
crusoe/gpt-oss-120bQuantUnspecified
- Input
- $0.05/M
- Output
- $0.25/M
- Context
- 131K
- Max out
- 33K
- Caching
- Not offered
- Thinking out
- $0.25/M
FlexPriority / Fast
bedrock/gpt-oss-120bQuantUnspecified
- Input
- $0.15/M
- Output
- $0.60/M
- Context
- 131K
- Max out
- 16K
- Caching
- Not offered
- Thinking out
- $0.60/M
cloudflare/gpt-oss-120bQuantUnspecified
- Input
- $0.35/M
- Output
- $0.75/M
- Context
- 128K
- Max out
- 32K
- Caching
- Not offered
- Thinking out
- $0.75/M
FlexPriority / Fast
deepinfra/gpt-oss-120bQuantbf16
- Input
- $0.04/M
- Output
- $0.17/M
- Context
- 131K
- Max out
- 33K
- Caching
- Not offered
- Thinking out
- $0.17/M
FlexPriority / Fast
Fireworks AIDeprecating on Fireworks AI
fireworks/gpt-oss-120bQuantUnspecified
- Input
- $0.15/M
- Output
- $0.60/M
- Context
- 131K
- Max out
- 33K
- Cache read
- $0.01/M
- Cache write
- $0.15/M
- Thinking out
- $0.60/M
Flex
nebius/gpt-oss-120bQuantfp4
- Input
- $0.15/M
- Output
- $0.60/M
- Context
- 131K
- Max out
- 33K
- Caching
- Not offered
- Thinking out
- $0.60/M
FlexPriority / Fast
novita/gpt-oss-120bQuantfp4
- Input
- $0.05/M
- Output
- $0.25/M
- Context
- 131K
- Max out
- 33K
- Caching
- Not offered
- Thinking out
- $0.25/M
FlexPriority / Fast