All Models
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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
Available Providers (6)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Kilo Gateway | openai/gpt-oss-120b | $0.04/MTok | $0.19/MTok | 131.1K | 26.2K | |
 Helicone | gpt-oss-120b | $0.04/MTok | $0.16/MTok | 131.1K | 131.1K | |
 NovitaAI | openai/gpt-oss-120b | $0.05/MTok | $0.25/MTok | 131.1K | 32.8K | |
 SiliconFlow | openai/gpt-oss-120b | $0.05/MTok | $0.45/MTok | 131K | 8K | |
 Venice AI | openai-gpt-oss-120b | $0.07/MTok | $0.30/MTok | 128K | 16.4K | |
 CloudFerro Sherlock | openai/gpt-oss-120b | $2.92/MTok | $2.92/MTok | 131K | 131K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output