Model Price Index
Updated 2026-07-14 · Changelog

GPT OSS 120B

Cerebras

Large open-source model running on Cerebras wafer-scale hardware for high-performance inference at scale

$0.35

Input

$0.75

Output

per 1M tokens

Ratesper 1M tokens

Input$0.35
Output$0.75

Estimate Your Monthly Cost

A request with input and output tokens, requests / month at a % cache hit rate $32.75/mo

Compare all models at this workload →

Excludes cache writes and batch discounts.

Same Model, Other Providersper 1M tokens

Provider comparison for GPT OSS 120B
ProviderInput / 1MOutput / 1MCache Read / 1MCache Write / 1Mvs This Page
Together AI$0.15$0.60−57%
Groq$0.15$0.60$0.075−57%
CerebrasThis page$0.35$0.75

Specifications

API Model IDgpt-oss-120b
Context Window128K tokens
Max Output8K tokens
Modalitiestext
Capabilitiestool-use · streaming · json-mode · code

More Cerebras Text / Chat Models

Llama 3.1 8B