GPT-OSS 120B

$0.15
Input / MTok
$0.6
Output / MTok
$0.015
Cache read / MTok

Hosted third-party inference; price is Fireworks' Standard serverless rate, not OpenAI's own API. Optional Priority tier at 1.2x.

API identifier accounts/fireworks/models/gpt-oss-120b · vendor pricing page

Full price sheet

MetricUSD / million tokens
Input$0.15
Output$0.6
Cache read$0.015

Price history

ObservedMetric Price
2026-08-08 07:26:49 Input $0.15
2026-08-08 07:26:49 Output $0.6
2026-08-08 07:26:49 Cache read $0.015

Current prices are free and always will be. The full series — every observation since we started watching, which nobody can reconstruct after the fact — is the part Pro pays for.

Changes affecting this model

coverage
GPT-OSS 120B added to coverage
2026-08-08

Compare with

Models at a similar price point.

ModelInputOutput
GPT-4o mini $0.15$0.6 compare →
Mistral Small 4 $0.15$0.6 compare →
GPT-OSS 120B $0.15$0.6 compare →
GPT-OSS 120B $0.15$0.6 compare →
Command Light $0.3$0.6 compare →
GPT-4.1 nano $0.1$0.4 compare →