gpt-oss-120b vs Grok 4
Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.
OpenAI · Aug 2025
OpenAI's open-weights MoE reasoning model under Apache 2.0 — near o4-mini quality, runnable on a single 80GB GPU.
xAI · Jul 2025
xAI's mid-2025 flagship, trained on the 200K-GPU Colossus cluster — a math and science reasoning standout of its generation.
The verdict
Grok 4 wins 2 of the 3 benchmarks these models share, against 1 for gpt-oss-120b. On price the gap is dramatic: gpt-oss-120b works out roughly 30x cheaper per blended million tokens. Grok 4 also takes 256K of context versus 131K for gpt-oss-120b. And gpt-oss-120b is open-weights (Apache 2.0), so it can be self-hosted — a structural advantage if data control or vendor independence matters.
Benchmark head-to-head 1–2
Specs & pricing
| gpt-oss-120b | Grok 4 | |
|---|---|---|
| modhub Index | — | — |
| Input price / 1M | $0.1 | $3 |
| Output price / 1M | $0.5 | $15 |
| Context window | 131K | 256K |
| Max output | 131K | — |
| Open weights | yes (Apache 2.0) | no |
| Reasoning model | yes | yes |
| Multimodal input | text | text, image |
| Knowledge cutoff | Jun 2024 | Jul 2025 |
| Released | Aug 2025 | Jul 2025 |
| Example monthly cost* | $1.75 | $52.50 |
* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.
Frequently asked questions
- Which is better, gpt-oss-120b or Grok 4?
- Grok 4 wins 2 of the 3 benchmarks these models share, against 1 for gpt-oss-120b. On price the gap is dramatic: gpt-oss-120b works out roughly 30x cheaper per blended million tokens. Grok 4 also takes 256K of context versus 131K for gpt-oss-120b. And gpt-oss-120b is open-weights (Apache 2.0), so it can be self-hosted — a structural advantage if data control or vendor independence matters.
- Which is cheaper, gpt-oss-120b or Grok 4?
- gpt-oss-120b costs $0.1/$0.5 per million input/output tokens, while Grok 4 costs $3/$15. For a typical workload of 10M input and 1.5M output tokens per month, that's $1.75 versus $52.50.
- Which model is better for coding, gpt-oss-120b or Grok 4?
- We don't yet track SWE-bench Verified results for both models; check their individual pages for coding-related scores.