All Models
OpenAI: GPT OSS 20B
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.
Available Providers (4)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Kilo Gateway | openai/gpt-oss-20b | $0.03/MTok | $0.14/MTok | 131.1K | 26.2K | |
 NovitaAI | openai/gpt-oss-20b | $0.04/MTok | $0.15/MTok | 131.1K | 32.8K | |
 SiliconFlow | openai/gpt-oss-20b | $0.04/MTok | $0.18/MTok | 131K | 8K | |
 Helicone | gpt-oss-20b | $0.05/MTok | $0.20/MTok | 131.1K | 131.1K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output