gpt-oss-120b

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.

Reasoning
Speed
Context
131K
Max output
40K
Input price
$0.35
/1M tokens
Output price
$0.75
/1M tokens
Capabilities
vision
tool call
structured output
reasoning
json mode
streaming
fine tuning
batch
Details
Provider Cerebras
Creator OpenAI
Familygpt-oss
Statusactive
Input modalitiestext
Output modalitiestext
Knowledge cutoff—
Release date—
Deprecation date—
Sourceofficial
Last updated2026-03-21
Max input—
Pricing per 1M tokens
Input
$0.35
Output
$0.75
Cached
—
Batch in
—
Batch out
—
API
GET/v1/models/cerebras/gpt-oss-120b