gpt-oss-20b
openai/gpt-oss-20b
Compare with GPT Audio, GPT Audio Mini, GPT Chat Latest
Compare its 12 providers · Incident RSS
Showing only the coreweave/fp4 provider · show all 12
Comparegpt-oss-20b
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 99.95% | 99.31% | 99.25% | 99.25% | 273ms | 9.42s | 87 tps | 131K | $0.030 / $0.130 |
- CoreWeave99.95%Healthy24h 99.31%
- 7d
- 99.25%
- 30d
- 99.25%
- p50
- 273ms
- p99
- 9.42s
- Throughput
- 87 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.130
coreweave/fp4fp4
Measured 5m 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.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one cell per week · up to a year.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC week · 12 endpoints · 24 weeks with data, 42 endpoint-weeks below 90%.