gpt-oss-120b
openai/gpt-oss-120b
Compare with GPT Audio, GPT Audio Mini, GPT Chat Latest
Comparegpt-oss-120b
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Amazon Bedrockamazon-bedrock | Healthy | 100% | 99.08% | 99.25% | 99.25% | 566ms | 1.40s | 82 tps | 131K | $0.150 / $0.600 |
| Healthy | 100% | 99.60% | 99.18% | 99.18% | 198ms | 765ms | 287 tps | 128K | $0.100 / $0.500 | |
| Healthy | 100% | 99.99% | 99.99% | 99.99% | 166ms | 1.51s | 939 tps | 131K | $0.350 / $0.750 | |
| Healthy | 100% | 99.73% | 98.94% | 98.94% | 411ms | 1.35s | 117 tps | 131K | $0.150 / $0.600 | |
DigitalOceandigitalocean | Healthy | 100% | 99.90% | 99.90% | 99.90% | 755ms | 4.00s | 26 tps | 128K | $0.055 / $0.385 |
| Degraded | 100% | 99.34% | 99.75% | 99.75% | 838ms | 31.5s | 41 tps | 131K | $0.085 / $0.500 | |
Maramara | Healthy | 100% | 97.70% | 95.33% | 95.33% | 1.28s | 9.15s | 204 tps | 131K | $0.150 / $0.750 |
| Healthy | 100% | 99.52% | 98.74% | 98.74% | 221ms | 1.63s | 300 tps | 131K | $0.150 / $0.600 | |
| Healthy | 100% | 99.66% | 99.83% | 99.83% | 318ms | 2.09s | 118 tps | 131K | $0.100 / $0.750 | |
Phalaphala | Healthy | 100% | 97.31% | 97.47% | 97.47% | 894ms | 3.54s | 109 tps | 131K | $0.150 / $0.600 |
Togethertogether | Degraded | 100% | 96.28% | 97.39% | 97.39% | 563ms | 6.50s | 68 tps | 131K | $0.150 / $0.600 |
Groqgroq | Healthy | 99.35% | 99.95% | 99.93% | 99.93% | 224ms | 2.63s | 362 tps | 131K | $0.150 / $0.600 |
| Healthy | 99.02% | 94.86% | 95.98% | 95.98% | 397ms | 9.43s | 30 tps | 131K | $0.030 / $0.170 | |
| Healthy | 98.73% | 85.98% | 92.60% | 92.60% | 1.23s | 12.8s | 22 tps | 131K | $0.050 / $0.450 | |
SambaNovasambanova | Degraded | 96.30% | 88.52% | 86.26% | 86.26% | 774ms | 12.5s | 367 tps | 131K | $0.140 / $0.950 |
| Healthy | 95.86% | 97.46% | 98.23% | 98.23% | 5.23s | 10.9s | 21 tps | 131K | $0.037 / $0.170 | |
| Degraded | 94.88% | 99.36% | 99.65% | 99.65% | 1.21s | 11.5s | 49 tps | 131K | $0.037 / $0.490 | |
| Degraded | 91.18% | 91.51% | 94.17% | 94.17% | 658ms | 12.8s | 49 tps | 131K | $0.050 / $0.250 | |
Googlegoogle-vertex/global | Down | 85.80% | 89.83% | 89.70% | 89.70% | 474ms | 9.97s | 98 tps | 131K | $0.090 / $0.360 |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | — | 100% | 100% | — | — | — | 131K | $0.150 / $0.600 |
- Amazon Bedrock100%Healthy24h 99.08%
- 7d
- 99.25%
- 30d
- 99.25%
- p50
- 566ms
- p99
- 1.40s
- Throughput
- 82 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock - BaseTen100%Healthy24h 99.60%
- 7d
- 99.18%
- 30d
- 99.18%
- p50
- 198ms
- p99
- 765ms
- Throughput
- 287 tps
- Context
- 128K
- $/Mtok
- $0.100 / $0.500
baseten/fp4fp4 - Cerebras100%Healthy24h 99.99%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 166ms
- p99
- 1.51s
- Throughput
- 939 tps
- Context
- 131K
- $/Mtok
- $0.350 / $0.750
cerebras/fp16fp16 - DeepInfra100%Healthy24h 99.73%
- 7d
- 98.94%
- 30d
- 98.94%
- p50
- 411ms
- p99
- 1.35s
- Throughput
- 117 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
deepinfra/turbobf16 - DigitalOcean100%Healthy24h 99.90%
- 7d
- 99.90%
- 30d
- 99.90%
- p50
- 755ms
- p99
- 4.00s
- Throughput
- 26 tps
- Context
- 128K
- $/Mtok
- $0.055 / $0.385
digitalocean - Mancer 2100%Degraded24h 99.34%
- 7d
- 99.75%
- 30d
- 99.75%
- p50
- 838ms
- p99
- 31.5s
- Throughput
- 41 tps
- Context
- 131K
- $/Mtok
- $0.085 / $0.500
mancer/fp8fp8 - Mara100%Healthy24h 97.70%
- 7d
- 95.33%
- 30d
- 95.33%
- p50
- 1.28s
- p99
- 9.15s
- Throughput
- 204 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.750
mara - Nebius100%Healthy24h 99.52%
- 7d
- 98.74%
- 30d
- 98.74%
- p50
- 221ms
- p99
- 1.63s
- Throughput
- 300 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
nebius/fp4fp4 - Parasail100%Healthy24h 99.66%
- 7d
- 99.83%
- 30d
- 99.83%
- p50
- 318ms
- p99
- 2.09s
- Throughput
- 118 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.750
parasail/fp4fp4 - Phala100%Healthy24h 97.31%
- 7d
- 97.47%
- 30d
- 97.47%
- p50
- 894ms
- p99
- 3.54s
- Throughput
- 109 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
phala - Together100%Degraded24h 96.28%
- 7d
- 97.39%
- 30d
- 97.39%
- p50
- 563ms
- p99
- 6.50s
- Throughput
- 68 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
together - Groq99.35%Healthy24h 99.95%
- 7d
- 99.93%
- 30d
- 99.93%
- p50
- 224ms
- p99
- 2.63s
- Throughput
- 362 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
groq - CoreWeave99.02%Healthy24h 94.86%
- 7d
- 95.98%
- 30d
- 95.98%
- p50
- 397ms
- p99
- 9.43s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.170
coreweave/fp4fp4 - SiliconFlow98.73%Healthy24h 85.98%
- 7d
- 92.60%
- 30d
- 92.60%
- p50
- 1.23s
- p99
- 12.8s
- Throughput
- 22 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.450
siliconflow/fp8fp8 - SambaNova96.30%Degraded24h 88.52%
- 7d
- 86.26%
- 30d
- 86.26%
- p50
- 774ms
- p99
- 12.5s
- Throughput
- 367 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.950
sambanova - DeepInfra95.86%Healthy24h 97.46%
- 7d
- 98.23%
- 30d
- 98.23%
- p50
- 5.23s
- p99
- 10.9s
- Throughput
- 21 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.170
deepinfra/bf16bf16 - AkashML94.88%Degraded24h 99.36%
- 7d
- 99.65%
- 30d
- 99.65%
- p50
- 1.21s
- p99
- 11.5s
- Throughput
- 49 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.490
akashml/bf16bf16 - Novita91.18%Degraded24h 91.51%
- 7d
- 94.17%
- 30d
- 94.17%
- p50
- 658ms
- p99
- 12.8s
- Throughput
- 49 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
novita/fp4fp4 - Google85.80%Down24h 89.83%
- 7d
- 89.70%
- 30d
- 89.70%
- p50
- 474ms
- p99
- 9.97s
- Throughput
- 98 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.360
google-vertex/global - No data24h —
- 7d
- 100%
- 30d
- 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock/eu-west-1
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- gpt-oss-120bMancer 2mancer/fp8$0.080 / $0.500 → $0.085 / $0.5002026-08-20 23:41 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.083 / $0.500 → $0.080 / $0.5002026-08-20 22:26 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.085 / $0.500 → $0.083 / $0.5002026-08-20 21:56 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.080 / $0.500 → $0.085 / $0.5002026-08-20 21:21 UTC
- gpt-oss-120bMancer 2mancer/fp8$0.085 / $0.500 → $0.080 / $0.5002026-08-19 19:25 UTC
History
1 endpoint reporting no data is omitted from the charts.
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.