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 |
|---|---|---|---|---|---|---|---|---|
BaseTenbaseten/fp4fp4 | Healthy | 100% | 98.84% | 246ms | 943ms | 190 tps | 128K | $0.100 / $0.500 |
Cerebrascerebras/fp16fp16 | Healthy | 100% | 99.99% | 262ms | 4.01s | 642 tps | 131K | $0.350 / $0.750 |
DigitalOceandigitalocean | Healthy | 100% | 99.78% | 801ms | 4.12s | 27 tps | 128K | $0.055 / $0.385 |
Phalaphala | Healthy | 100% | 99.72% | 810ms | 2.91s | 72 tps | 131K | $0.150 / $0.600 |
Groqgroq | Healthy | 99.96% | 99.90% | 275ms | 2.18s | 312 tps | 131K | $0.150 / $0.600 |
DeepInfradeepinfra/bf16bf16 | Healthy | 99.94% | 98.75% | 526ms | 16.6s | 43 tps | 131K | $0.037 / $0.170 |
Parasailparasail/fp4fp4 | Healthy | 99.91% | 99.41% | 412ms | 1.87s | 105 tps | 131K | $0.100 / $0.750 |
Amazon Bedrockamazon-bedrock | Healthy | 99.90% | 99.62% | 385ms | 2.17s | 226 tps | 131K | $0.150 / $0.600 |
Nebiusnebius/fp4fp4 | Healthy | 99.87% | 98.16% | 371ms | 8.14s | 187 tps | 131K | $0.150 / $0.600 |
CoreWeavecoreweave/fp4fp4 | Degraded | 99.84% | 95.97% | 538ms | 13.4s | 31 tps | 131K | $0.030 / $0.170 |
Mancer 2mancer/fp8fp8 | Healthy | 99.59% | 99.85% | 755ms | 6.64s | 50 tps | 131K | $0.085 / $0.500 |
DeepInfradeepinfra/turbobf16 | Healthy | 99.50% | 94.95% | 433ms | 1.65s | 157 tps | 131K | $0.150 / $0.600 |
Togethertogether | Healthy | 99.50% | 98.67% | 304ms | 2.55s | 35 tps | 131K | $0.150 / $0.600 |
AkashMLakashml/bf16bf16 | Healthy | 99.47% | 99.42% | 775ms | 5.85s | 63 tps | 131K | $0.037 / $0.490 |
Novitanovita/fp4fp4 | Healthy | 99.33% | 96.74% | 520ms | 6.97s | 66 tps | 131K | $0.050 / $0.250 |
SambaNovasambanova | Healthy | 99.26% | 98.53% | 889ms | 7.32s | 337 tps | 131K | $0.140 / $0.950 |
SiliconFlowsiliconflow/fp8fp8 | Degraded | 95.09% | 91.77% | 1.74s | 16.3s | 12 tps | 131K | $0.050 / $0.450 |
Googlegoogle-vertex/global | Down | 89.51% | 90.06% | 811ms | 5.13s | 60 tps | 131K | $0.090 / $0.360 |
Maramara | Down | 77.40% | 97.20% | 2.08s | 14.0s | 170 tps | 131K | $0.150 / $0.750 |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | — | — | — | 131K | $0.150 / $0.600 |
- BaseTen100%Healthy24h 98.84%
- p50
- 246ms
- p99
- 943ms
- Throughput
- 190 tps
- Context
- 128K
- $/Mtok
- $0.100 / $0.500
baseten/fp4fp4 - Cerebras100%Healthy24h 99.99%
- p50
- 262ms
- p99
- 4.01s
- Throughput
- 642 tps
- Context
- 131K
- $/Mtok
- $0.350 / $0.750
cerebras/fp16fp16 - DigitalOcean100%Healthy24h 99.78%
- p50
- 801ms
- p99
- 4.12s
- Throughput
- 27 tps
- Context
- 128K
- $/Mtok
- $0.055 / $0.385
digitalocean - Phala100%Healthy24h 99.72%
- p50
- 810ms
- p99
- 2.91s
- Throughput
- 72 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
phala - Groq99.96%Healthy24h 99.90%
- p50
- 275ms
- p99
- 2.18s
- Throughput
- 312 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
groq - DeepInfra99.94%Healthy24h 98.75%
- p50
- 526ms
- p99
- 16.6s
- Throughput
- 43 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.170
deepinfra/bf16bf16 - Parasail99.91%Healthy24h 99.41%
- p50
- 412ms
- p99
- 1.87s
- Throughput
- 105 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.750
parasail/fp4fp4 - Amazon Bedrock99.90%Healthy24h 99.62%
- p50
- 385ms
- p99
- 2.17s
- Throughput
- 226 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock - Nebius99.87%Healthy24h 98.16%
- p50
- 371ms
- p99
- 8.14s
- Throughput
- 187 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
nebius/fp4fp4 - CoreWeave99.84%Degraded24h 95.97%
- p50
- 538ms
- p99
- 13.4s
- Throughput
- 31 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.170
coreweave/fp4fp4 - Mancer 299.59%Healthy24h 99.85%
- p50
- 755ms
- p99
- 6.64s
- Throughput
- 50 tps
- Context
- 131K
- $/Mtok
- $0.085 / $0.500
mancer/fp8fp8 - DeepInfra99.50%Healthy24h 94.95%
- p50
- 433ms
- p99
- 1.65s
- Throughput
- 157 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
deepinfra/turbobf16 - Together99.50%Healthy24h 98.67%
- p50
- 304ms
- p99
- 2.55s
- Throughput
- 35 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
together - AkashML99.47%Healthy24h 99.42%
- p50
- 775ms
- p99
- 5.85s
- Throughput
- 63 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.490
akashml/bf16bf16 - Novita99.33%Healthy24h 96.74%
- p50
- 520ms
- p99
- 6.97s
- Throughput
- 66 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
novita/fp4fp4 - SambaNova99.26%Healthy24h 98.53%
- p50
- 889ms
- p99
- 7.32s
- Throughput
- 337 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.950
sambanova - SiliconFlow95.09%Degraded24h 91.77%
- p50
- 1.74s
- p99
- 16.3s
- Throughput
- 12 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.450
siliconflow/fp8fp8 - Google89.51%Down24h 90.06%
- p50
- 811ms
- p99
- 5.13s
- Throughput
- 60 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.360
google-vertex/global - Mara77.40%Down24h 97.20%
- p50
- 2.08s
- p99
- 14.0s
- Throughput
- 170 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.750
mara - Amazon Bedrock—No data24h 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.
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.