Using gpt-oss-120b on Open Inference

Implementation guide · GPT-OSS · OpenAI

ServerlessOpen Source

Quick Start

1
Create an account at Open Inference and generate an API key.
2
Use the Open Inference SDK or REST API to call gpt-oss-120b.
3
You'll be billed Free/1M input, Free/1M output tokens.

API Portal Model Card

Code Examples

Code examples for this provider have not been sourced yet.

About Open Inference

Open Inference provides an OpenAI-compatible API for hosted text-generation model inference.

View all models on Open Inference →

Pricing on Open Inference

Type	Price (per 1M)
Input tokens	Free
Output tokens	Free

Capabilities

Function CallingTool UseStructured Outputs

About gpt-oss-120b

OpenAI open-weight model with 120 billion parameters. Text-only model supporting reasoning, function calling, and structured outputs. Free for self-hosting. Released August 5, 2025.

Full model details →

Model Specs

Released2025-08-05

Parameters120B

Context131k

ArchitectureDecoder Only

Knowledge cutoff2025-08