LIVE Cheapest: GLM-4.7-Flash $0.000/Mtok in 153 models tracked Updated Jun 24, 2026
Jun 24, 2026
ModelPriceWatch$/Mtok
Pricing / Fireworks / GPT OSS 120B

GPT OSS 120B

by Fireworks · 120B parameters

Current budget Open weights cheap tier

Pricing · per 1M tokens

Input
$0.150
per million tokens
Output
$0.600
per million tokens
Cached input$0.015/Mtok (10% of input — prompt caching)
Blended avg cost*$0.375/Mtok

Overview

OpenAI's GPT OSS 120B on Fireworks. $0.15/$0.60 per 1M; cached $0.015.

Specifications

ProviderFireworks
Context window128K tokens
Modalitytext
Parameters120B
Open sourceYes — open weights available
ReleasedJan 1, 2026
StatusCurrent
Last updatedJun 24, 2026
Tagsopen-weights budget caching

Cost calculator

1K tokens (in)$0.0001
1K tokens (out)$0.0006
100K tokens (in)$0.015
100K tokens (out)$0.06
1M tokens (in)$0.150
1M tokens (out)$0.600
10M tokens (blended)$3.8
Full calculator →

At a glance

Input$0.150/M
Output$0.600/M
Blended$0.375/M
Context128K
Tiercheap

Price history

Jun 24, 2026 Baseline · $0.15/$0.6/M

Tracking since Jun 24, 2026 · 1 data points

Related models