gpt-oss-120b

proprietary120B

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. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.

Intelligence
Reasoning
Speed
Context
131K
Max output
131K
Input price
$0.04/1M tokens
Output price
$0.17/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Batch Processing

Details

Provider DeepInfra
Creator OpenAI
Familygpt-oss
Licenseproprietary
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters120B
Architecture—
Context window131K tokens
Max input—
Max output131K tokens
Reasoning tokensYes
Knowledge cutoff
Release date—
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.deepinfra.com/v1/openai/v1/chat/completions

Pricing

Input
$0.04
Output
$0.17
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: gpt-oss

ModelContextMax outPricing
gpt-oss-20b131K131K$0.03$0.14
gpt-oss-120b131K131K$0.04$0.17
gpt-oss-120b-Turbo131K—$0.15$0.6
gpt-oss-120b-Ultra131K—$0.2$0.95

API

GET/v1/models/deepinfra/openai/gpt-oss-120b