GPT-OSS 120B (Groq)
| Maker | OpenAI |
|---|---|
| Released | 2025-08-05 |
| Context | 131.1K |
| Max output | 65.5K |
| Open weights | Apache-2.0 |
|---|---|
| Modalities | text → text |
| Input / 1M | $0.15 |
| Output / 1M | $0.60 |
| Review call | $0.0054 |
|---|---|
| Reasoning efforts | low, medium, high |
| Hosts | Groq |
| Model id | openai/gpt-oss-120b |
CodePanel's benchmark has not run GPT-OSS 120B (Groq) as a pull-request reviewer yet, so this page has no recall, false-alarm or measured-cost figures for it. The methodology explains how ranked models are scored.
The same model is ranked on Workers AI, as GPT-OSS 120B (Workers AI): it caught 40% [29%–52%] of the known bugs at rank 8 of 17, with a measured review cost of $0.0075. Those results are for that host's copy, not for this listing. At list price, a typical review call (26.2K tokens in and 2.4K out) costs $0.0054 on GPT-OSS 120B (Groq) and $0.011 on GPT-OSS 120B (Workers AI), so this model's call is 51% less than that one's.
| Host | Model id | Input / 1M | Output / 1M |
|---|---|---|---|
| Groq | openai/gpt-oss-120b | $0.15 | $0.60 |
Source: Groq pricing, Oct 16, 2026
| Model | Maker | Input / 1M | Output / 1M | Review call | Context | Bugs caught |
|---|---|---|---|---|---|---|
| GLM-5.3 Flash (Workers AI) | Z.ai | $0.15 | $0.50 | $0.0051 | 1M | 61% |
| Claude Haiku 5.5 | Anthropic | $0.10 | $0.50 | $0.0038 | 1M | 64% |
| GPT-6 Luna | OpenAI | $0.10 | $0.50 | $0.0038 | 1.1M | 67% |
| Gemini 2.5 Flash-Lite | $0.10 | $0.40 | $0.0036 | 1M | – |
Updated Oct 23, 2026