Open GPT reasoning model for self-hosted agents and controllable deployments
Specification
most-agreed values
Context
131K
Max output
128K
Released
2025-08-05
Knowledge cutoff
2024-06
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.15
Output
$0.60
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | bedrock_converse | $0.075 |
| Batch output | bedrock_converse | $0.30 |
| Priority input | bedrock_converse | $0.2625 |
| Priority output | bedrock_converse | $1.05 |
Batch input is 50% below the interactive input price at the same listing.
Available from 3 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| amazon-bedrock | $0.15 | $0.60 | — | — | 131K | 128K | — |
| bedrock_converse | $0.15 | $0.60 | — | — | 128K | 16K | — |
| bedrock | $0.18 | $0.72 | — | — | 128K | 16K | — |
Other listings of this model
this page is one of them
The corpus files gpt-oss-120b under several keys. This page is the gpt-oss-120b-1-0 listing. The full record — every host, every price and every benchmark score — is on the main gpt-oss-120b page.
More from OpenAI
most-hosted first