gpt-oss-120b
openai/gpt-oss-120bInputOutput
Compare its 28 providersIncident RSSCompare with GPT Audio, GPT Audio Mini, GPT Chat Latest
Showing only the deepinfra/fp8 provider · show all 28
Comparegpt-oss-120b
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Degraded | 100% | 85.04% | 87.75% | 87.75% | 1.28s | 8.26s | 60 tps | 131K | $0.200 / $0.950 |
- DeepInfra100%Degraded24h 85.04%
- 7d
- 87.75%
- 30d
- 87.75%
- p50
- 1.28s
- p99
- 8.26s
- Throughput
- 60 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.950
deepinfra/fp8fp8
Measured 1m 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 dot per day · last 90 days.
Aug
Sep
Oct
Nov
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 28 endpoints · 76 days with data, 524 endpoint-days below 90%. Tables and charts above are filtered to deepinfra/fp8.
Price changes
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.030 → $0.038 / $0.113 → $0.139cache read $0.027 → $0.0342026-11-02 00:00 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.029 → $0.030 / $0.106 → $0.113cache read $0.026 → $0.0272026-11-01 23:55 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.032 → $0.029 / $0.117 → $0.106cache read $0.029 → $0.0262026-11-01 23:50 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.031 → $0.032 / $0.115 → $0.117cache read $0.028 → $0.0292026-11-01 23:45 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.037 → $0.031 / $0.138 → $0.115cache read $0.033 → $0.0282026-11-01 23:40 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.038 → $0.037 / $0.142 → $0.138cache read $0.034 → $0.0332026-11-01 23:35 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.038 / $0.139 → $0.1422026-11-01 23:30 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.025 → $0.038 / $0.094 → $0.139cache read $0.023 → $0.0342026-11-01 23:25 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.030 → $0.025 / $0.111 → $0.094cache read $0.027 → $0.0232026-11-01 23:20 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.041 → $0.030 / $0.150 → $0.111cache read $0.037 → $0.0272026-11-01 23:15 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.042 → $0.041 / $0.154 → $0.1502026-11-01 23:10 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.039 → $0.042 / $0.144 → $0.154cache read $0.035 → $0.0372026-11-01 23:05 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.036 → $0.039 / $0.132 → $0.144cache read $0.032 → $0.0352026-11-01 23:00 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.037 → $0.036 / $0.138 → $0.132cache read $0.034 → $0.0322026-11-01 22:55 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.035 → $0.037 / $0.128 → $0.138cache read $0.031 → $0.0342026-11-01 22:50 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.032 → $0.035 / $0.120 → $0.128cache read $0.029 → $0.0312026-11-01 22:45 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.031 → $0.032 / $0.115 → $0.120cache read $0.028 → $0.0292026-11-01 22:40 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.029 → $0.031 / $0.107 → $0.115cache read $0.026 → $0.0282026-11-01 22:35 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.023 → $0.029 / $0.086 → $0.107cache read $0.021 → $0.0262026-11-01 22:30 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.019 → $0.023 / $0.069 → $0.086cache read $0.017 → $0.0212026-11-01 22:25 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.018 → $0.019 / $0.068 → $0.0692026-11-01 22:15 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.017 → $0.018 / $0.062 → $0.068cache read $0.015 → $0.0172026-11-01 22:10 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.016 → $0.017 / $0.061 → $0.0622026-11-01 22:00 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.015 → $0.016 / $0.054 → $0.061cache read $0.013 → $0.0152026-11-01 21:55 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.014 → $0.015 / $0.052 → $0.0542026-11-01 21:05 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.015 → $0.014 / $0.057 → $0.052cache read $0.014 → $0.0132026-11-01 21:00 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.016 → $0.015 / $0.059 → $0.0572026-11-01 20:55 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.018 → $0.016 / $0.065 → $0.059cache read $0.016 → $0.0142026-11-01 20:45 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.015 → $0.018 / $0.057 → $0.065cache read $0.014 → $0.0162026-11-01 20:40 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.018 → $0.015 / $0.067 → $0.057cache read $0.016 → $0.0142026-11-01 20:35 UTC