gpt-oss-120b
openai/gpt-oss-120bInputOutput
Compare its 23 providersIncident RSSCompare with GPT Audio, GPT Audio Mini, GPT Chat Latest
Comparegpt-oss-120b
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.39% | 99.82% | 99.68% | 699ms | 17.7s | 30 tps | 131K | $0.030 / $0.170 | |
Amazon Bedrockamazon-bedrock | Healthy | 100% | 40.64% | 93.77% | 98.06% | 794ms | 16.8s | 62 tps | 131K | $0.150 / $0.600 |
| Healthy | 100% | 99.95% | 99.99% | 99.87% | 274ms | 5.23s | 146 tps | 128K | $0.100 / $0.500 | |
| Healthy | 100% | 99.99% | 99.99% | 99.97% | 223ms | 1.91s | 740 tps | 131K | $0.350 / $0.750 | |
| Healthy | 100% | 98.12% | 98.65% | 98.99% | 3.60s | 15.1s | 27 tps | 131K | $0.037 / $0.170 | |
| Healthy | 100% | 99.99% | 99.97% | 99.81% | 334ms | 3.81s | 124 tps | 131K | $0.150 / $0.600 | |
DigitalOceandigitalocean | Healthy | 100% | 99.96% | 99.97% | 99.53% | 480ms | 2.32s | 39 tps | 128K | $0.060 / $0.420 |
| Healthy | 100% | 99.22% | 99.42% | 99.31% | 694ms | 15.4s | 67 tps | 131K | $0.050 / $0.400 | |
| Healthy | 100% | 99.55% | 99.42% | 98.97% | 285ms | 1.85s | 238 tps | 131K | $0.150 / $0.600 | |
| Healthy | 100% | 93.00% | 92.96% | 91.98% | 1.53s | 15.2s | 37 tps | 131K | $0.050 / $0.250 | |
| Healthy | 100% | 99.98% | 97.64% | 99.39% | 752ms | 1.93s | 91 tps | 131K | $0.100 / $0.750 | |
Phalaphala | Healthy | 100% | 94.72% | 93.40% | 94.57% | 1.58s | 11.5s | 41 tps | 131K | $0.150 / $0.600 |
Groqgroq | Healthy | 99.99% | 99.98% | 99.99% | 99.98% | 416ms | 2.57s | 251 tps | 131K | $0.150 / $0.600 |
| Healthy | 99.98% | 99.87% | 99.90% | 99.50% | 401ms | 9.81s | 36 tps | 131K | $0.030 / $0.170 | |
| Healthy | 99.71% | 99.83% | 99.18% | 99.18% | 769ms | 6.92s | 25 tps | 131K | $0.030 / $0.180 | |
Maramara | Degraded | 98.73% | 90.12% | 79.44% | 90.72% | 1.65s | 16.7s | 149 tps | 131K | $0.150 / $0.750 |
| Healthy | 98.21% | 99.07% | 99.18% | 99.18% | 272ms | 1.09s | 194 tps | 131K | $0.050 / $0.250 | |
SambaNovasambanova | Degraded | 98.17% | 97.26% | 94.69% | 96.41% | 598ms | 13.9s | 376 tps | 131K | $0.140 / $0.950 |
Googlegoogle-vertex/global | Degraded | 96.17% | 95.50% | 97.69% | 91.41% | 9.59s | 23.7s | 30 tps | 131K | $0.090 / $0.360 |
| Down | 85.71% | 93.12% | 95.40% | 93.01% | 1.61s | 5.67s | 38 tps | 131K | $0.150 / $0.600 | |
Togethertogether | Down | 81.41% | 94.96% | 92.52% | 94.14% | 272ms | 2.04s | 37 tps | 131K | $0.150 / $0.600 |
| Down | 78.17% | 60.58% | 85.39% | 83.49% | 2.02s | 11.3s | 123 tps | 131K | $0.200 / $0.950 | |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | 100% | 100% | 415ms | 2.69s | 128 tps | 131K | $0.150 / $0.600 |
- AkashML100%Healthy24h 99.39%
- 7d
- 99.82%
- 30d
- 99.68%
- p50
- 699ms
- p99
- 17.7s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.170
akashml/bf16bf16 - Amazon Bedrock100%Healthy24h 40.64%
- 7d
- 93.77%
- 30d
- 98.06%
- p50
- 794ms
- p99
- 16.8s
- Throughput
- 62 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock - BaseTen100%Healthy24h 99.95%
- 7d
- 99.99%
- 30d
- 99.87%
- p50
- 274ms
- p99
- 5.23s
- Throughput
- 146 tps
- Context
- 128K
- $/Mtok
- $0.100 / $0.500
baseten/fp4fp4 - Cerebras100%Healthy24h 99.99%
- 7d
- 99.99%
- 30d
- 99.97%
- p50
- 223ms
- p99
- 1.91s
- Throughput
- 740 tps
- Context
- 131K
- $/Mtok
- $0.350 / $0.750
cerebras/fp16fp16 - DeepInfra100%Healthy24h 98.12%
- 7d
- 98.65%
- 30d
- 98.99%
- p50
- 3.60s
- p99
- 15.1s
- Throughput
- 27 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.170
deepinfra/bf16bf16 - DeepInfra100%Healthy24h 99.99%
- 7d
- 99.97%
- 30d
- 99.81%
- p50
- 334ms
- p99
- 3.81s
- Throughput
- 124 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
deepinfra/turbobf16 - DigitalOcean100%Healthy24h 99.96%
- 7d
- 99.97%
- 30d
- 99.53%
- p50
- 480ms
- p99
- 2.32s
- Throughput
- 39 tps
- Context
- 128K
- $/Mtok
- $0.060 / $0.420
digitalocean - Mancer 2100%Healthy24h 99.22%
- 7d
- 99.42%
- 30d
- 99.31%
- p50
- 694ms
- p99
- 15.4s
- Throughput
- 67 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.400
mancer/fp8fp8 - Nebius100%Healthy24h 99.55%
- 7d
- 99.42%
- 30d
- 98.97%
- p50
- 285ms
- p99
- 1.85s
- Throughput
- 238 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
nebius/fp4fp4 - Novita100%Healthy24h 93.00%
- 7d
- 92.96%
- 30d
- 91.98%
- p50
- 1.53s
- p99
- 15.2s
- Throughput
- 37 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
novita/fp4fp4 - Parasail100%Healthy24h 99.98%
- 7d
- 97.64%
- 30d
- 99.39%
- p50
- 752ms
- p99
- 1.93s
- Throughput
- 91 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.750
parasail/fp4fp4 - Phala100%Healthy24h 94.72%
- 7d
- 93.40%
- 30d
- 94.57%
- p50
- 1.58s
- p99
- 11.5s
- Throughput
- 41 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
phala - Groq99.99%Healthy24h 99.98%
- 7d
- 99.99%
- 30d
- 99.98%
- p50
- 416ms
- p99
- 2.57s
- Throughput
- 251 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
groq - CoreWeave99.98%Healthy24h 99.87%
- 7d
- 99.90%
- 30d
- 99.50%
- p50
- 401ms
- p99
- 9.81s
- Throughput
- 36 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.170
coreweave/fp4fp4 - DekaLLM99.71%Healthy24h 99.83%
- 7d
- 99.18%
- 30d
- 99.18%
- p50
- 769ms
- p99
- 6.92s
- Throughput
- 25 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.180
dekallm/bf16bf16 - Mara98.73%Degraded24h 90.12%
- 7d
- 79.44%
- 30d
- 90.72%
- p50
- 1.65s
- p99
- 16.7s
- Throughput
- 149 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.750
mara - Crusoe98.21%Healthy24h 99.07%
- 7d
- 99.18%
- 30d
- 99.18%
- p50
- 272ms
- p99
- 1.09s
- Throughput
- 194 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
crusoe/bf16bf16 - SambaNova98.17%Degraded24h 97.26%
- 7d
- 94.69%
- 30d
- 96.41%
- p50
- 598ms
- p99
- 13.9s
- Throughput
- 376 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.950
sambanova - Google96.17%Degraded24h 95.50%
- 7d
- 97.69%
- 30d
- 91.41%
- p50
- 9.59s
- p99
- 23.7s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.360
google-vertex/global - SiliconFlow85.71%Down24h 93.12%
- 7d
- 95.40%
- 30d
- 93.01%
- p50
- 1.61s
- p99
- 5.67s
- Throughput
- 38 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
siliconflow/fp8fp8 - Together81.41%Down24h 94.96%
- 7d
- 92.52%
- 30d
- 94.14%
- p50
- 272ms
- p99
- 2.04s
- Throughput
- 37 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
together - DeepInfra78.17%Down24h 60.58%
- 7d
- 85.39%
- 30d
- 83.49%
- p50
- 2.02s
- p99
- 11.3s
- Throughput
- 123 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.950
deepinfra/fp8fp8 - No data24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 415ms
- p99
- 2.69s
- Throughput
- 128 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock/eu-west-1
Measured 2m 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 · 23 endpoints · 30 days with data, 214 endpoint-days below 90%.
Price changes
- gpt-oss-120bMancer 2mancer/fp8$0.055 → $0.050 / $0.500 → $0.4002026-09-16 08:20 UTC
- gpt-oss-120bDigitalOceandigitalocean$0.055 → $0.060 / $0.385 → $0.420cache read $0.020 → $0.0122026-09-14 15:15 UTC
- gpt-oss-120bSiliconFlowsiliconflow/fp8$0.050 → $0.150 / $0.450 → $0.600cache read — → $0.0752026-09-10 05:40 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.050 → $0.055 / $0.5002026-09-08 09:30 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.060 → $0.050 / $0.5002026-09-05 17:35 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.050 → $0.060 / $0.5002026-09-05 10:35 UTC
- gpt-oss-120bPhalaphala$0.200 → $0.150 / $0.750 → $0.6002026-09-05 08:15 UTC
- gpt-oss-120bPhalaphala$0.150 → $0.200 / $0.600 → $0.7502026-09-05 08:10 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.060 → $0.050 / $0.5002026-09-05 03:40 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.055 → $0.060 / $0.5002026-09-04 20:20 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.050 → $0.055 / $0.5002026-09-04 20:15 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.055 → $0.050 / $0.5002026-09-04 20:10 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.050 → $0.055 / $0.5002026-09-04 20:05 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.055 → $0.050 / $0.5002026-09-04 20:00 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.060 → $0.055 / $0.5002026-09-03 20:46 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.065 → $0.060 / $0.5002026-09-03 09:20 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.070 → $0.065 / $0.5002026-08-31 08:21 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.050 → $0.070 / $0.5002026-08-30 23:50 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.070 → $0.050 / $0.5002026-08-30 23:20 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.060 → $0.070 / $0.5002026-08-30 08:35 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.070 → $0.060 / $0.5002026-08-30 05:45 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.075 → $0.070 / $0.5002026-08-30 00:36 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.085 → $0.075 / $0.5002026-08-30 00:26 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.075 → $0.085 / $0.5002026-08-29 03:35 UTC
- gpt-oss-120bDigitalOceandigitalocean$0.100 → $0.055 / $0.700 → $0.3852026-08-28 22:05 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.085 → $0.075 / $0.5002026-08-28 22:05 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.090 → $0.085 / $0.5002026-08-28 06:55 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.080 → $0.090 / $0.5002026-08-28 06:20 UTC
- gpt-oss-120bDigitalOceandigitalocean$0.055 → $0.100 / $0.385 → $0.7002026-08-27 22:50 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.070 → $0.080 / $0.5002026-08-27 04:50 UTC