gpt-oss-120b
openai/gpt-oss-120bInputOutput
Compare its 28 providersIncident RSSCompare with GPT Audio, GPT Audio Mini, GPT Chat Latest
Comparegpt-oss-120b
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 100% | 100% | 99.95% | 305ms | 1.63s | 147 tps | 131K | $0.030 / $0.187 | |
Amazon Bedrockamazon-bedrock | Healthy | 100% | 100% | 100% | 99.74% | 630ms | 11.0s | 239 tps | 131K | $0.150 / $0.600 |
Amazon Bedrockamazon-bedrock/eu-west-1 | Healthy | 100% | 100% | 100% | 100% | 423ms | 10.4s | 194 tps | 131K | $0.150 / $0.600 |
| Healthy | 100% | 99.78% | 98.71% | 99.61% | 207ms | 796ms | 199 tps | 128K | $0.100 / $0.500 | |
| Healthy | 100% | 99.72% | 98.50% | 99.41% | 184ms | 814ms | 194 tps | 128K | $0.100 / $0.500 | |
| Healthy | 100% | 99.24% | 99.89% | 99.97% | 151ms | 1.23s | 794 tps | 131K | $0.350 / $0.750 | |
| Healthy | 100% | 100% | 99.89% | 99.67% | 256ms | 1.76s | 113 tps | 131K | $0.030 / $0.170 | |
| Healthy | 100% | 100% | 100% | 99.39% | 250ms | 1.13s | 286 tps | 131K | $0.050 / $0.250 | |
| Healthy | 100% | 100% | 98.17% | 98.58% | 483ms | 4.21s | 34 tps | 131K | $0.037 / $0.170 | |
| Degraded | 100% | 83.44% | 87.43% | 87.43% | 1.39s | 10.5s | 58 tps | 131K | $0.200 / $0.950 | |
| Healthy | 100% | 100% | 99.95% | 99.92% | 429ms | 2.60s | 82 tps | 131K | $0.030 / $0.180 | |
DigitalOceandigitalocean | Healthy | 100% | 100% | 100% | 99.91% | 590ms | 2.13s | 65 tps | 128K | $0.060 / $0.420 |
Groqgroq | Healthy | 100% | 99.86% | 99.86% | 99.83% | 168ms | 1.72s | 351 tps | 131K | $0.150 / $0.600 |
| Healthy | 100% | 99.86% | 99.65% | 99.38% | 772ms | 3.32s | 59 tps | 131K | $0.055 / $0.250 | |
Maramara | Healthy | 100% | 92.38% | 96.47% | 95.01% | 754ms | 7.72s | 245 tps | 131K | $0.150 / $0.750 |
| Healthy | 100% | 100% | 100% | 99.62% | 656ms | 2.04s | 49 tps | 131K | $0.030 / $0.150 | |
| Healthy | 100% | 99.24% | 99.92% | 99.37% | 273ms | 1.64s | 291 tps | 131K | $0.150 / $0.600 | |
| Healthy | 100% | 99.86% | 99.67% | 98.37% | 732ms | 1.51s | 127 tps | 131K | $0.050 / $0.250 | |
| Healthy | 100% | 100% | 99.98% | 99.84% | 358ms | 759ms | 121 tps | 131K | $0.100 / $0.750 | |
Phalaphala | Healthy | 100% | 99.56% | 98.84% | 98.62% | 917ms | 1.93s | 127 tps | 131K | $0.150 / $0.600 |
| Healthy | 100% | 99.76% | 99.10% | 99.10% | 667ms | 5.64s | 81 tps | 131K | $0.030 / $0.111 | |
| Healthy | 100% | 100% | 100% | 100% | 602ms | 2.33s | 159 tps | 131K | $0.060 / $0.400 | |
SambaNovasambanova | Healthy | 100% | 99.49% | 99.62% | 97.41% | 752ms | 6.34s | 371 tps | 131K | $0.140 / $0.950 |
| Degraded | 100% | 98.65% | 99.18% | 98.91% | 879ms | 11.6s | 39 tps | 128K | $0.030 / $0.150 | |
Googlegoogle-vertex/global | Down | 0.00% | 4.02% | 2.19% | 32.78% | 591ms | 16.2s | 50 tps | 131K | $0.090 / $0.360 |
| No data | — | — | — | 99.98% | — | — | — | 131K | $0.150 / $0.600 | |
| No data | — | 90.52% | 94.27% | 83.31% | 1.08s | 1.91s | 64 tps | 131K | $0.150 / $0.600 | |
Togethertogether | Down | — | 93.66% | 98.54% | 94.41% | 230ms | 655ms | 153 tps | 131K | $0.150 / $0.600 |
- AkashML100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.95%
- p50
- 305ms
- p99
- 1.63s
- Throughput
- 147 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.187
akashml/bf16bf16 - Amazon Bedrock100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.74%
- p50
- 630ms
- p99
- 11.0s
- Throughput
- 239 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock - Amazon Bedrock100%Healthy24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 423ms
- p99
- 10.4s
- Throughput
- 194 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
amazon-bedrock/eu-west-1 - BaseTen100%Healthy24h 99.78%
- 7d
- 98.71%
- 30d
- 99.61%
- p50
- 207ms
- p99
- 796ms
- Throughput
- 199 tps
- Context
- 128K
- $/Mtok
- $0.100 / $0.500
baseten/fp4fp4 - BaseTen100%Healthy24h 99.72%
- 7d
- 98.50%
- 30d
- 99.41%
- p50
- 184ms
- p99
- 814ms
- Throughput
- 194 tps
- Context
- 128K
- $/Mtok
- $0.100 / $0.500
baseten/fp4/usfp4 - Cerebras100%Healthy24h 99.24%
- 7d
- 99.89%
- 30d
- 99.97%
- p50
- 151ms
- p99
- 1.23s
- Throughput
- 794 tps
- Context
- 131K
- $/Mtok
- $0.350 / $0.750
cerebras/fp16fp16 - CoreWeave100%Healthy24h 100%
- 7d
- 99.89%
- 30d
- 99.67%
- p50
- 256ms
- p99
- 1.76s
- Throughput
- 113 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.170
coreweave/fp4fp4 - Crusoe100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.39%
- p50
- 250ms
- p99
- 1.13s
- Throughput
- 286 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
crusoe/bf16bf16 - DeepInfra100%Healthy24h 100%
- 7d
- 98.17%
- 30d
- 98.58%
- p50
- 483ms
- p99
- 4.21s
- Throughput
- 34 tps
- Context
- 131K
- $/Mtok
- $0.037 / $0.170
deepinfra/bf16bf16 - DeepInfra100%Degraded24h 83.44%
- 7d
- 87.43%
- 30d
- 87.43%
- p50
- 1.39s
- p99
- 10.5s
- Throughput
- 58 tps
- Context
- 131K
- $/Mtok
- $0.200 / $0.950
deepinfra/fp8fp8 - DekaLLM100%Healthy24h 100%
- 7d
- 99.95%
- 30d
- 99.92%
- p50
- 429ms
- p99
- 2.60s
- Throughput
- 82 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.180
dekallm/bf16bf16 - DigitalOcean100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.91%
- p50
- 590ms
- p99
- 2.13s
- Throughput
- 65 tps
- Context
- 128K
- $/Mtok
- $0.060 / $0.420
digitalocean - Groq100%Healthy24h 99.86%
- 7d
- 99.86%
- 30d
- 99.83%
- p50
- 168ms
- p99
- 1.72s
- Throughput
- 351 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
groq - Mancer 2100%Healthy24h 99.86%
- 7d
- 99.65%
- 30d
- 99.38%
- p50
- 772ms
- p99
- 3.32s
- Throughput
- 59 tps
- Context
- 131K
- $/Mtok
- $0.055 / $0.250
mancer/fp8fp8 - Mara100%Healthy24h 92.38%
- 7d
- 96.47%
- 30d
- 95.01%
- p50
- 754ms
- p99
- 7.72s
- Throughput
- 245 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.750
mara - Near AI100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.62%
- p50
- 656ms
- p99
- 2.04s
- Throughput
- 49 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.150
near-ai/fp4fp4 - Nebius100%Healthy24h 99.24%
- 7d
- 99.92%
- 30d
- 99.37%
- p50
- 273ms
- p99
- 1.64s
- Throughput
- 291 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
nebius/fp4fp4 - Novita100%Healthy24h 99.86%
- 7d
- 99.67%
- 30d
- 98.37%
- p50
- 732ms
- p99
- 1.51s
- Throughput
- 127 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.250
novita/fp4fp4 - Parasail100%Healthy24h 100%
- 7d
- 99.98%
- 30d
- 99.84%
- p50
- 358ms
- p99
- 759ms
- Throughput
- 121 tps
- Context
- 131K
- $/Mtok
- $0.100 / $0.750
parasail/fp4fp4 - Phala100%Healthy24h 99.56%
- 7d
- 98.84%
- 30d
- 98.62%
- p50
- 917ms
- p99
- 1.93s
- Throughput
- 127 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
phala - PrimeIntellect100%Healthy24h 99.76%
- 7d
- 99.10%
- 30d
- 99.10%
- p50
- 667ms
- p99
- 5.64s
- Throughput
- 81 tps
- Context
- 131K
- $/Mtok
- $0.030 / $0.111
primeintellect/fp4fp4 - Sail Research100%Healthy24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 602ms
- p99
- 2.33s
- Throughput
- 159 tps
- Context
- 131K
- $/Mtok
- $0.060 / $0.400
sail-research/fp4fp4 - SambaNova100%Healthy24h 99.49%
- 7d
- 99.62%
- 30d
- 97.41%
- p50
- 752ms
- p99
- 6.34s
- Throughput
- 371 tps
- Context
- 131K
- $/Mtok
- $0.140 / $0.950
sambanova - Venice100%Degraded24h 98.65%
- 7d
- 99.18%
- 30d
- 98.91%
- p50
- 879ms
- p99
- 11.6s
- Throughput
- 39 tps
- Context
- 128K
- $/Mtok
- $0.030 / $0.150
venice/int4int4 - Google0.00%Down24h 4.02%
- 7d
- 2.19%
- 30d
- 32.78%
- p50
- 591ms
- p99
- 16.2s
- Throughput
- 50 tps
- Context
- 131K
- $/Mtok
- $0.090 / $0.360
google-vertex/global - No data24h —
- 7d
- —
- 30d
- 99.98%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
deepinfra/turbobf16 - No data24h 90.52%
- 7d
- 94.27%
- 30d
- 83.31%
- p50
- 1.08s
- p99
- 1.91s
- Throughput
- 64 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
siliconflow/fp8fp8 - Down24h 93.66%
- 7d
- 98.54%
- 30d
- 94.41%
- p50
- 230ms
- p99
- 655ms
- Throughput
- 153 tps
- Context
- 131K
- $/Mtok
- $0.150 / $0.600
together
Measured 3m 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.
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 · 77 days with data, 542 endpoint-days below 90%.
Price changes
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.036 → $0.030 / $0.132 → $0.111cache read $0.032 → $0.0272026-11-03 02:05 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.033 → $0.036 / $0.124 → $0.132cache read $0.030 → $0.0322026-11-03 02:00 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.038 → $0.033 / $0.139 → $0.124cache read $0.034 → $0.0302026-11-03 01:55 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.036 → $0.038 / $0.133 → $0.139cache read $0.032 → $0.0342026-11-03 01:50 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.032 → $0.036 / $0.120 → $0.133cache read $0.029 → $0.0322026-11-03 01:45 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.029 → $0.032 / $0.107 → $0.120cache read $0.026 → $0.0292026-11-03 01:40 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.032 → $0.029 / $0.117 → $0.107cache read $0.028 → $0.0262026-11-03 01:35 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.035 → $0.032 / $0.129 → $0.117cache read $0.031 → $0.0282026-11-03 01:30 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.032 → $0.035 / $0.119 → $0.129cache read $0.029 → $0.0312026-11-03 01:25 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.034 → $0.032 / $0.126 → $0.119cache read $0.031 → $0.0292026-11-03 01:20 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.064 → $0.034 / $0.237 → $0.126cache read $0.058 → $0.0312026-11-03 01:15 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.064 / $0.238 → $0.2372026-11-03 01:10 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.064 / $0.235 → $0.238cache read $0.057 → $0.0582026-11-03 01:05 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.056 → $0.064 / $0.209 → $0.235cache read $0.051 → $0.0572026-11-03 01:00 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.049 → $0.056 / $0.182 → $0.209cache read $0.044 → $0.0512026-11-03 00:55 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.051 → $0.049 / $0.189 → $0.182cache read $0.046 → $0.0442026-11-03 00:50 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.051 / $0.190 → $0.1892026-11-03 00:45 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.048 → $0.051 / $0.178 → $0.190cache read $0.043 → $0.0462026-11-03 00:40 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.043 → $0.048 / $0.160 → $0.178cache read $0.039 → $0.0432026-11-03 00:35 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.039 → $0.043 / $0.145 → $0.160cache read $0.035 → $0.0392026-11-03 00:30 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.037 → $0.039 / $0.136 → $0.145cache read $0.033 → $0.0352026-11-03 00:25 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.034 → $0.037 / $0.125 → $0.136cache read $0.030 → $0.0332026-11-03 00:20 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.030 → $0.034 / $0.113 → $0.125cache read $0.027 → $0.0302026-11-03 00:15 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.031 → $0.030 / $0.116 → $0.113cache read $0.028 → $0.0272026-11-03 00:10 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.033 → $0.031 / $0.121 → $0.116cache read $0.029 → $0.0282026-11-03 00:05 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.032 → $0.033 / $0.120 → $0.1212026-11-02 23:55 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.034 → $0.032 / $0.125 → $0.120cache read $0.030 → $0.0292026-11-02 23:50 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.032 → $0.034 / $0.117 → $0.125cache read $0.028 → $0.0302026-11-02 23:45 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.031 → $0.032 / $0.116 → $0.1172026-11-02 23:40 UTC
- gpt-oss-120bPrimeIntellectprimeintellect/fp4$0.035 → $0.031 / $0.128 → $0.116cache read $0.031 → $0.0282026-11-02 23:35 UTC