OpenAI/ GPT
GPT OSS 120B
openai/gpt/oss-120b
Open GPT reasoning model for self-hosted agents and controllable deployments
Released
2025-08-05
Context window
131K
Max output
33K
Weights
Open weight
Modalities
Input
Text
Output
Text
Identity
- Version
- gpt-oss-120b
- Knowledge cutoff
- 2024-06-30
- Aliases
- GPT OSS 120B
Resources
Providers
| Provider | Provider model ID | Protocol | Context | Max output | Input | Output | Capabilities | Notes | Pricing | Streaming |
|---|---|---|---|---|---|---|---|---|---|---|
| GreenPT | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.228/M output $0.798/M | Yes |
| Weights & Biases | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.03/M · cache read $0.03/M output $0.17/M | Yes |
| Baseten | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.1/M output $0.5/M | Yes |
| Nvidia | openai/gpt-oss-120b | custom | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0/M output $0/M | Yes |
| Nebius Token Factory | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $0.15/M · cache read $0.015/M output $0.6/M · cache write $0.18/M | Yes |
| NanoGPT | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.35/M output $0.75/M | Yes |
| FastRouter | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.15/M output $0.6/M | Yes |
| NEAR AI Cloud | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.15/M output $0.55/M | Yes |
| QVAC | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0/M output $0/M | Yes |
| LLM Gateway | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.032/M · cache read $0.032/M output $0.14/M | Yes |
| Kenari | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0/M output $0/M | Yes |
| Cloudflare Workers AI | @cf/openai/gpt-oss-120b | custom | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.35/M output $0.75/M | Yes |
| Helicone | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.04/M output $0.16/M | Yes |
| submodel | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.1/M output $0.5/M | Yes |
| Neon | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.072/M output $0.28/M | Yes |
| DInference | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.0675/M output $0.27/M | Yes |
| Privatemode AI | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0/M output $0/M | Yes |
| FrogBot | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.15/M output $0.6/M | Yes |
| Regolo AI | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $1/M output $4.2/M | Yes |
| ai& | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.15/M output $0.6/M | Yes |
| Pioneer | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Interleaved output | input $0.15/M · cache read $0.015/M output $0.6/M · cache write $0.15/M | Yes |
| SiliconFlow | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.05/M output $0.45/M | Yes |
| evroc | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.23/M output $0.92/M | Yes |
| Abacus | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.08/M output $0.44/M | Yes |
| Scaleway | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.15/M output $0.6/M | Yes |
| Together AI | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.15/M output $0.6/M | Yes |
| OVHcloud AI Endpoints | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.09/M output $0.47/M | Yes |
| Berget.AI | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.22/M output $0.83/M | Yes |
| IO.NET | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.04/M · cache read $0.02/M output $0.4/M · cache write $0.08/M | Yes |
| AKI.IO | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.15/M output $0.55/M | Yes |
| Groq | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.15/M · cache read $0.075/M output $0.6/M | Yes |
| TensorX | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.04/M · cache read $0.01/M output $0.2/M · cache write $0.05/M | Yes |
| Kilo Gateway | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.03/M · cache read $0.03/M output $0.17/M | Yes |
| Merge Gateway | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.09/M output $0.36/M | Yes |
| CloudFerro Sherlock | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $2.92/M output $2.92/M | Yes |
| Charm Hyper | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.188/M output $0.7/M · cache write $0.094/M | Yes |
| Vercel AI Gateway | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.1/M output $0.5/M | Yes |
| NovitaAI | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.05/M output $0.25/M | Yes |
| OpenRouter | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | Default reasoning: medium, Hugging Face: openai/gpt-oss-120b | input $0.037/M output $0.17/M | Yes |
| Hugging Face | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.25/M output $0.69/M | Yes |
| Tinfoil | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.15/M output $0.6/M | Yes |
| STACKIT | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.53/M output $0.76/M | Yes |
| Deep Infra | openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.037/M output $0.17/M | Yes |
| Cloudflare AI Gateway | workers-ai/@cf/openai/gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.35/M output $0.75/M | Yes |
| Cerebras | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0.35/M output $0.75/M | Yes |
| Qiniu | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | - | Yes |
| Cortecs | gpt-oss-120b | openai_chat | 131K | 33K | Text | Text | ReasoningTool callStructuredTemperatureOpen weight | - | input $0/M output $0/M | Yes |
Capabilities
ReasoningTool callStructuredTemperatureOpen weight
Official price
input $0/M
output $0/M