gpt-oss-120b
openai/gpt-oss-120b
Compare with GPT Audio, GPT Audio Mini, GPT Chat Latest
Comparegpt-oss-120b
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
AkashMLakashml/bf16bf16 | Healthy | 100% | 99.56% | 614ms | 9.61s | 78 tps | 131K | $0.037 / $0.490 |
Amazon Bedrockamazon-bedrock | Healthy | 100% | 99.51% | 411ms | 2.77s | 316 tps | 131K | $0.150 / $0.600 |
Cerebrascerebras/fp16fp16 | Healthy | 100% | 99.99% | 246ms | 2.43s | 733 tps | 131K | $0.350 / $0.750 |
DigitalOceandigitalocean | Healthy | 100% | 99.77% | 655ms | 4.58s | 42 tps | 128K | $0.055 / $0.385 |
Mancer 2mancer/fp8fp8 | Healthy | 100% | 99.83% | 734ms | 6.85s | 63 tps | 131K | $0.085 / $0.500 |
Nebiusnebius/fp4fp4 | Healthy | 100% | 98.51% | 295ms | 2.81s | 209 tps | 131K | $0.150 / $0.600 |
Parasailparasail/fp4fp4 | Healthy | 100% | 99.94% | 388ms | 1.85s | 116 tps | 131K | $0.100 / $0.750 |
Phalaphala | Healthy | 100% | 99.70% | 893ms | 6.84s | 65 tps | 131K | $0.150 / $0.600 |
SiliconFlowsiliconflow/fp8fp8 | Degraded | 100% | 92.03% | 1.79s | 15.0s | 20 tps | 131K | $0.050 / $0.450 |
Togethertogether | Down | 100% | 98.45% | 289ms | 3.13s | 47 tps | 131K | $0.150 / $0.600 |
Groqgroq | Healthy | 99.99% | 99.90% | 267ms | 2.20s | 313 tps | 131K | $0.150 / $0.600 |
DeepInfradeepinfra/bf16bf16 | Healthy | 99.84% | 98.73% | 511ms | 20.0s | 32 tps | 131K | $0.037 / $0.170 |
Maramara | Healthy | 99.70% | 97.63% | 1.04s | 8.27s | 119 tps | 131K | $0.150 / $0.750 |
DeepInfradeepinfra/turbobf16 | Healthy | 99.45% | 94.58% | 454ms | 1.33s | 113 tps | 131K | $0.150 / $0.600 |
Novitanovita/fp4fp4 | Healthy | 98.34% | 97.37% | 556ms | 8.08s | 80 tps | 131K | $0.050 / $0.250 |
BaseTenbaseten/fp4fp4 | Healthy | 95.60% | 98.80% | 224ms | 933ms | 170 tps | 128K | $0.100 / $0.500 |
CoreWeavecoreweave/fp4fp4 | Healthy | 95.31% | 96.31% | 515ms | 12.5s | 30 tps | 131K | $0.030 / $0.170 |
Googlegoogle-vertex/global | Degraded | 90.34% | 89.87% | 474ms | 3.91s | 84 tps | 131K | $0.090 / $0.360 |
SambaNovasambanova | Down | 77.91% | 97.89% | 880ms | 24.5s | 350 tps | 131K | $0.140 / $0.950 |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | — | — | — | 131K | $0.150 / $0.600 |
- AkashML100%Healthy24h 99.56%
- p50
- 614ms
- p99
- 9.61s
- Throughput
- 78 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.490
akashml/bf16bf16 - Amazon Bedrock100%Healthy24h 99.51%
- p50
- 411ms
- p99
- 2.77s
- Throughput
- 316 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock - Cerebras100%Healthy24h 99.99%
- p50
- 246ms
- p99
- 2.43s
- Throughput
- 733 tps
- Context
- 131K
- $/Mtok
- $0.350 / $0.750
cerebras/fp16fp16 - DigitalOcean100%Healthy24h 99.77%
- p50
- 655ms
- p99
- 4.58s
- Throughput
- 42 tps
- Context
- 128K
- $/Mtok
- $0.055 / $0.385
digitalocean - Mancer 2100%Healthy24h 99.83%
- p50
- 734ms
- p99
- 6.85s
- Throughput
- 63 tps
- Context
- 131K
- $/Mtok
- $0.085 / $0.500
mancer/fp8fp8 - Nebius100%Healthy24h 98.51%
- p50
- 295ms
- p99
- 2.81s
- Throughput
- 209 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
nebius/fp4fp4 - Parasail100%Healthy24h 99.94%
- p50
- 388ms
- p99
- 1.85s
- Throughput
- 116 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.750
parasail/fp4fp4 - Phala100%Healthy24h 99.70%
- p50
- 893ms
- p99
- 6.84s
- Throughput
- 65 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
phala - SiliconFlow100%Degraded24h 92.03%
- p50
- 1.79s
- p99
- 15.0s
- Throughput
- 20 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.450
siliconflow/fp8fp8 - Together100%Down24h 98.45%
- p50
- 289ms
- p99
- 3.13s
- Throughput
- 47 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
together - Groq99.99%Healthy24h 99.90%
- p50
- 267ms
- p99
- 2.20s
- Throughput
- 313 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
groq - DeepInfra99.84%Healthy24h 98.73%
- p50
- 511ms
- p99
- 20.0s
- Throughput
- 32 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.170
deepinfra/bf16bf16 - Mara99.70%Healthy24h 97.63%
- p50
- 1.04s
- p99
- 8.27s
- Throughput
- 119 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.750
mara - DeepInfra99.45%Healthy24h 94.58%
- p50
- 454ms
- p99
- 1.33s
- Throughput
- 113 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
deepinfra/turbobf16 - Novita98.34%Healthy24h 97.37%
- p50
- 556ms
- p99
- 8.08s
- Throughput
- 80 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
novita/fp4fp4 - BaseTen95.60%Healthy24h 98.80%
- p50
- 224ms
- p99
- 933ms
- Throughput
- 170 tps
- Context
- 128K
- $/Mtok
- $0.100 / $0.500
baseten/fp4fp4 - CoreWeave95.31%Healthy24h 96.31%
- p50
- 515ms
- p99
- 12.5s
- Throughput
- 30 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.170
coreweave/fp4fp4 - Google90.34%Degraded24h 89.87%
- p50
- 474ms
- p99
- 3.91s
- Throughput
- 84 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.360
google-vertex/global - SambaNova77.91%Down24h 97.89%
- p50
- 880ms
- p99
- 24.5s
- Throughput
- 350 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.950
sambanova - Amazon Bedrock—No data24h 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock/eu-west-1
Measured 53s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.