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...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.000000024 | $0.024 |
| completion | 0.000000112 | $0.112 |
{
"temperature": null,
"top_p": null,
"frequency_penalty": null
}