# GPT OSS 120B

As of 18 September 2026, GPT OSS 120B costs $0.150 per million input tokens and $0.600 per million output tokens on Groq. Observed on Groq's own published price list on 18 September 2026. This is Groq's resale price, not the model vendor's list price.

Source: Groq (reseller)
Canonical page: https://bertrande.com/en/ai/groq/openai--gpt-oss-120b/
Machine formats: https://bertrande.com/en/ai/groq/openai--gpt-oss-120b/data.json | https://bertrande.com/en/ai/groq/openai--gpt-oss-120b/data.csv
License: CC-BY-4.0, reuse with attribution and a link.

## Parameters

| Parameter | Value | Unit | Observed | Source level | Proof (SHA-256) |
|---|---|---|---|---|---|
| Input price | $0.150 | USD per 1M tokens | 2026-09-18 | L3 | `5cae5bcec35aec0e` |
| Output price | $0.600 | USD per 1M tokens | 2026-09-18 | L3 | `5cae5bcec35aec0e` |
| Context window | 131 072 | tokens | 2026-09-18 | L3 | `5cae5bcec35aec0e` |
| Maximum output | 65 536 | tokens | 2026-09-18 | L3 | `5cae5bcec35aec0e` |
| Cache read price | $0.075 | USD per 1M tokens | 2026-09-18 | L3 | `5cae5bcec35aec0e` |
| Rate limit, requests per minute (developer plan) | 1 000.0 | requests per minute | 2026-09-18 | L3 | `5cae5bcec35aec0e` |
| Rate limit, tokens per minute (developer plan) | 250 000.0 | tokens per minute | 2026-09-18 | L3 | `5cae5bcec35aec0e` |

## How this is verified

Every value above was read from the source URL shown on the canonical page, on the date given. We store a SHA-256 fingerprint of the source content at that moment, which is what lets us show later what the source said that day.

No value here was produced, estimated or completed by a language model. Where we have no verified figure, the row is absent rather than filled in.

Method: https://bertrande.com/en/methodology/
Report an error: https://bertrande.com/en/corrections/