Open-weight GPT model for self-hosted reasoning and instruction-following workloads
Specification
most-agreed values
Context
131K
Max output
33K
Released
2025-08-05
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · most-agreed
Input
$0.07
Output
$0.25
Cache read
$0.007
Available from 2 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| google-vertex | $0.07 | $0.25 | $0.007 | — | 131K | 33K | — |
| vertex_ai-openai_models | $0.07 | $0.25 | $0.007 | — | 131K | 33K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | vertex_ai-openai_models | Input | $0.075 |
| 2026-09-13 | vertex_ai-openai_models | Input | $0.07 |
| 2026-09-02 | vertex_ai-openai_models | Output | $0.30 |
| 2026-09-13 | vertex_ai-openai_models | Output | $0.25 |
Other listings of this model
this page is one of them
The corpus files GPT OSS 20B under several keys. This page is the gpt-oss-20b-maas listing. The full record — every host, every price and every benchmark score — is on the main GPT OSS 20B page.
More from OpenAI
most-hosted first