by OpenAI Community
gpt-oss-120b is a community-developed model with clean IP lineage. High throughput inference at 45-60K TPS. Excellent price/performance ratio.
Parameters
120B
Architecture
Dense Transformer
Context
32K
Provider
OpenAI Community
Drop-in replacement for OpenAI API. Just change the base URL.
Only pay for actual GPU compute time. No idle costs.
99.9% uptime SLA, SOC 2 compliant, dedicated support.
Scales from zero to thousands of requests automatically.
| Fleek | Fireworks | Together | Baseten | |
|---|---|---|---|---|
| Input | $0.02 | $0.15 | $0.15 | $0.10 |
| Output | $0.09 | $0.60 | $0.60 | $0.50 |
| Savings | 70% | 70% | 70% |
Prices are per million tokens. Fleek pricing based on $0.0025/GPU-second.
See how much you'd save running gpt-oss-120b on Fleek
| Model Name | gpt-oss-120b |
| Total Parameters | 120B |
| Active Parameters | N/A |
| Architecture | Dense Transformer |
| Context Length | 32K tokens |
| Inference Speed | 23,000 tokens/sec |
| Provider | OpenAI Community |
| Release Date | Oct 1, 2025 |
| License | Apache 2.0 |
| HuggingFace | https://huggingface.co/openai-community/gpt-oss-120b |
Click any benchmark to view the official leaderboard. Rankings among open-source models.
Join the waitlist for early access. Start free with $5 in credits.