gpt-oss-20b
openai/gpt-oss-20bInputOutput
Compare its 16 providersIncident RSSCompare with GPT Audio, GPT Audio Mini, GPT Chat Latest
Showing only the darkbloom/fp8 provider · show all 16
Comparegpt-oss-20b
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 99.77% | 99.68% | 99.40% | 98.57% | 2.81s | 21.4s | 35 tps | 131K | $0.020 / $0.100 |
- Darkbloom99.77%Healthy24h 99.68%
- 7d
- 99.40%
- 30d
- 98.57%
- p50
- 2.81s
- p99
- 21.4s
- Throughput
- 35 tps
- Context
- 131K
- $/Mtok
- $0.020 / $0.100
darkbloom/fp8fp8
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 16 endpoints · 31 days with data, 94 endpoint-days below 90%. Tables and charts above are filtered to darkbloom/fp8.
Price changes
- gpt-oss-20bAkashMLakashml/bf16$0.030 → $0.020 / $0.130 → $0.1002026-09-01 23:25 UTC