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. 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.
Modalities
In / out price
$0.03 / $0.14
per 1M
Context
131K
Max output
131K
Released
–
Updated
Sep 19, 2026
Providers
1 routeThe same model can have different pricing and privacy guarantees depending on who serves it. Only routes currently callable through AnonRouter are shown.
| Provider | Privacy | Input / 1M | Output / 1M | Cache read / 1M | Context | Max output | Uptime | Latency | Throughput |
|---|---|---|---|---|---|---|---|---|---|
| Private | $0.03 | $0.14 | — | 131K | 131K | — | — | — |
Privacy
2 / 4Private routing
Private tier
- Anonymous
- Private
- TEE
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more