gpt-oss-120b alternatives
Best gpt-oss-120b alternatives
10 models that can stand in for gpt-oss-120b, ranked by benchmark score, with what each one does better.
Current Model
gpt-oss-120b
- Input / 1M
- $0.04
- Output / 1M
- $0.17
- Context
- 131K
- Intelligence
- 11.6
Quick picks
The best alternative depends on what you need
Why people switch away from gpt-oss-120b, and the model that fits each reason best.
Ranked
Top gpt-oss-120b alternatives
Each model is scored against gpt-oss-120b. Green means better, red means worse.
| Model | Input / 1M | Output / 1M | Context | Intelligence | Compare |
|---|---|---|---|---|---|
gpt-oss-120b OpenAI | Input / 1M$0.04 | Output / 1M$0.17 | Context131K | Intelligence11.6 | Reference model |
| Input / 1M$0.09+143% | Output / 1M$0.34+100% | Context262K+100% | Intelligence14.7+27% | Compare | |
Why switch:Higher intelligence scoreLarger 262K contextAccepts image and videoNewer release | |||||
| Input / 1M$0.10+170% | Output / 1M$0.15-12% | Context262K+100% | Intelligence13.3+15% | Compare | |
Why switch:1.1x cheaper outputHigher intelligence scoreLarger 262K contextAccepts image and videoNewer release | |||||
| Input / 1M$0.05+35% | Output / 1M$0.40+135% | Context400K+205% | Intelligence13+12% | Compare | |
Why switch:Higher intelligence scoreLarger 400K contextAccepts image and fileNewer release | |||||
| Input / 1M$0.05+27% | Output / 1M$0.13-21% | Context262K+100% | Intelligence12.9+11% | Compare | |
Why switch:1.3x cheaper outputHigher intelligence scoreLarger 262K contextNewer release | |||||
| Input / 1M$0.04+8% | Output / 1M$0.15-12% | Context260K+98% | Intelligence12.3+6% | Compare | |
Why switch:1.1x cheaper outputHigher intelligence scoreLarger 260K contextNewer release | |||||
| Input / 1M$0.09+143% | Output / 1M$0.55+224% | Context262K+100% | Intelligence12+3% | Compare | |
Why switch:Higher intelligence scoreLarger 262K context | |||||
| Input / 1M$0.06+62% | Output / 1M$0.25+47% | Context131K | Intelligence11.1-4% | Compare | |
Why switch:Newer release | |||||
| Input / 1M$0.10+170% | Output / 1M$0.40+135% | Context1.05M+700% | Intelligence10.4-10% | Compare | |
Why switch:Larger 1.05M contextAccepts image and file and audio and video | |||||
| Input / 1M$0.02-51% | Output / 1M$0.09-47% | Context131K | Intelligence10-14% | Compare | |
Why switch:1.9x cheaper output | |||||
| Input / 1M$0.10+170% | Output / 1M$0.40+135% | Context1.05M+699% | Intelligence7.8-33% | Compare | |
Why switch:Larger 1.05M contextAccepts image and file | |||||
FAQ
Frequently asked questions
What is the best alternative to gpt-oss-120b?
Gemma 4 31B from Google ranks first, based on independent benchmark scores. It costs $0.34 per 1M output tokens, compared with $0.17 for gpt-oss-120b.
Is there a cheaper alternative to gpt-oss-120b?
Yes. gpt-oss-20b charges $0.09 per 1M output tokens, versus $0.17 for gpt-oss-120b.
Can I try gpt-oss-120b and its alternatives at the same time?
Yes. Shortcut Chat sends one prompt to several models at once, so you can compare gpt-oss-120b with any of these alternatives on your own tasks.
Not sure which to pick? Try them all.
Send one prompt to gpt-oss-120b and its alternatives at the same time, and keep the answer you like best.