Provider reliability · tracked daily
OpenAI: gpt-oss-120b: which provider is most reliable?
Across 20 providers, BaseTen is the most reliable way to run OpenAI: gpt-oss-120b, at 100.0% uptime and 245ms median latency. Measured directly from OpenRouter's endpoint data, tracked daily.
- BaseTen - 100.0% uptime · 245ms
- Parasail - 100.0% uptime · 497ms
- DigitalOcean - 100.0% uptime · 621ms
- Cerebras - 100.0% uptime · 219ms
- Groq - 100.0% uptime · 273ms
- CoreWeave - 100.0% uptime · 375ms
- Together - 100.0% uptime · 283ms
- AkashML - 99.9% uptime · 827ms
- DekaLLM - 99.9% uptime · 735ms
- Mancer 2 - 99.9% uptime · 654ms
Uptime is OpenRouter's own trailing-30-minute metric, captured once at our last daily sync - a snapshot of that window, not a live/real-time feed.
| # | Provider | Uptime (30m) | Latency p50 | Throughput |
|---|---|---|---|---|
| 01 | BaseTen | 100.0% | 245ms | 171 tok/s |
| 02 | Parasail | 100.0% | 497ms | 129 tok/s |
| 03 | DigitalOcean | 100.0% | 621ms | 51 tok/s |
| 04 | Cerebras | 100.0% | 219ms | 622 tok/s |
| 05 | Groq | 100.0% | 273ms | 323 tok/s |
| 06 | CoreWeave | 100.0% | 375ms | 43 tok/s |
| 07 | Together | 100.0% | 283ms | 156 tok/s |
| 08 | AkashML | 99.9% | 827ms | 35 tok/s |
| 09 | DekaLLM | 99.9% | 735ms | 34 tok/s |
| 10 | Mancer 2 | 99.9% | 654ms | 50 tok/s |
| 11 | Crusoe | 99.7% | 262ms | 214 tok/s |
| 12 | DeepInfra | 97.2% | 784ms | 23 tok/s |
| 13 | 95.4% | 527ms | 89 tok/s | |
| 14 | SambaNova | 94.9% | 626ms | 387 tok/s |
| 15 | Mara | 90.9% | 1090ms | 179 tok/s |
| 16 | SiliconFlow | 64.6% | 1969ms | 22 tok/s |
| 17 | Novita | 37.5% | 1069ms | 22 tok/s |
| 18 | Phala | 29.0% | 1137ms | 98 tok/s |
| 19 | Nebius | 22.5% | 6099ms | 11 tok/s |
| 20 | Amazon Bedrock | - | 470ms | 99 tok/s |
Uptime over time
- AkashML
- Amazon Bedrock
- BaseTen
- Cerebras
- CoreWeave
- Crusoe
Frequently asked questions
Which provider is most reliable for OpenAI: gpt-oss-120b?
BaseTen is the most reliable provider for OpenAI: gpt-oss-120b, at 100.0% uptime (OpenRouter's trailing-30-minute metric, snapshotted at our last daily sync) and 245ms median latency, out of 20 providers tracked.
What is OpenAI: gpt-oss-120b's uptime?
The best-performing provider for OpenAI: gpt-oss-120b reports 100.0% uptime, tracked daily.