GLM 5.2
z-ai/glm-5.2
CompareGLM 5.2
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Alibabaalibaba/fastfp8 | Healthy | 100% | 99.92% | 1.72s | 11.1s | 35 tps | 1.0M | $2.31 / $7.26 |
Ambientambient/fp8fp8 | Healthy | 100% | 87.43% | 1.77s | 16.0s | 51 tps | 203K | $0.600 / $2.00 |
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 100% | 99.04% | 2.05s | 12.3s | 38 tps | 1.0M | $1.26 / $3.96 |
Cloudflarecloudflare/fast | Healthy | 100% | 99.83% | 888ms | 10.0s | 73 tps | 262K | $2.10 / $6.60 |
CoreWeavecoreweave/fp4fp4 | Healthy | 100% | 99.82% | 1.22s | 7.55s | 54 tps | 262K | $0.760 / $2.42 |
Parasailparasail/fp4fp4 | Healthy | 100% | 99.83% | 899ms | 7.64s | 92 tps | 262K | $1.40 / $4.40 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 100% | 99.95% | 2.13s | 28.1s | 44 tps | 1.0M | $1.19 / $3.74 |
Waferwaferfp4 | Healthy | 100% | 97.24% | 3.25s | 12.4s | 51 tps | 1.0M | $1.26 / $3.96 |
Alibabaalibaba/fp8fp8 | Healthy | 99.90% | 99.45% | 1.04s | 11.5s | 53 tps | 1.0M | $0.966 / $3.04 |
Novitanovita/fp8fp8 | Healthy | 99.84% | 99.01% | 3.06s | 27.0s | 37 tps | 1.0M | $0.461 / $1.45 |
StreamLakestreamlake/fp8fp8 | Healthy | 99.84% | 99.81% | 1.66s | 7.94s | 46 tps | 1.0M | $0.560 / $1.76 |
Decartdecart/fp4fp4 | Healthy | 99.79% | 99.47% | 2.61s | 14.0s | 37 tps | 1.0M | $0.684 / $2.28 |
Baidubaidu/fp8fp8 | Healthy | 99.78% | 99.91% | 1.07s | 5.53s | 64 tps | 1.0M | $0.448 / $1.41 |
Crusoecrusoe/fp8fp8 | Healthy | 99.76% | 99.82% | 689ms | 6.89s | 59 tps | 1.0M | $1.40 / $4.40 |
Z.AIz-ai/fp8fp8 | Healthy | 99.73% | 99.22% | 4.39s | 15.7s | 53 tps | 1.0M | $1.40 / $4.40 |
DigitalOceandigitalocean | Healthy | 99.65% | 98.29% | 2.50s | 16.2s | 20 tps | 262K | $0.700 / $2.20 |
Phalaphala/fp8fp8 | Healthy | 99.47% | 99.63% | 1.59s | 10.9s | 44 tps | 1.0M | $1.26 / $3.00 |
GMICloudgmicloud/fp8fp8 | Healthy | 99.47% | 99.12% | 3.00s | 13.0s | 29 tps | 1.0M | $0.742 / $2.33 |
Inceptroninceptron/fp4fp4 | Degraded | 99.45% | 96.14% | 497ms | 8.95s | 122 tps | 1.0M | $0.750 / $2.90 |
Friendlifriendli | Healthy | 99.33% | 99.17% | 1.24s | 13.5s | 61 tps | 1.0M | $1.40 / $4.40 |
DeepInfradeepinfra/fp4fp4 | Healthy | 99.21% | 99.22% | 1.62s | 24.4s | 29 tps | 1.0M | $0.750 / $2.40 |
Sail Researchsail-research/fp8fp8 | Healthy | 98.98% | 99.56% | 3.43s | 40.6s | 7.0 tps | 1.0M | $0.500 / $3.15 |
Morphmorph/fp4fp4 | Healthy | 98.34% | 98.97% | 1.59s | 13.8s | 35 tps | 1.0M | $1.10 / $4.10 |
Fireworksfireworks/fast | Down | 96.97% | 97.00% | 1.19s | 12.7s | 117 tps | 1.0M | $2.10 / $6.60 |
Fireworksfireworks | Healthy | 96.38% | 97.79% | 1.79s | 27.8s | 39 tps | 1.0M | $1.40 / $4.40 |
Venicevenice/fp8fp8 | Degraded | 95.65% | 98.61% | 2.46s | 27.5s | 40 tps | 1.0M | $1.40 / $4.40 |
Togethertogether | Degraded | 90.83% | 94.00% | 646ms | 19.3s | 60 tps | 512K | $1.40 / $4.40 |
BaseTenbaseten/fp8fp8 | Down | 69.60% | 99.58% | 2.10s | 18.2s | 68 tps | 1.0M | $1.40 / $4.40 |
BaseTenbaseten/fastfp8 | Down | 20.09% | 99.36% | 2.05s | 69.0s | 95 tps | 1.0M | $2.10 / $6.60 |
AkashMLakashml/fp8fp8 | No data | — | — | — | — | — | 97K | $0.770 / $2.42 |
Cloudflarecloudflare | No data | — | 99.01% | 2.14s | 11.4s | 59 tps | 262K | $1.40 / $4.40 |
- Alibaba100%Healthy24h 99.92%
- p50
- 1.72s
- p99
- 11.1s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $2.31 / $7.26
alibaba/fastfp8 - Ambient100%Healthy24h 87.43%
- p50
- 1.77s
- p99
- 16.0s
- Throughput
- 51 tps
- Context
- 203K
- $/Mtok
- $0.600 / $2.00
ambient/fp8fp8 - AtlasCloud100%Healthy24h 99.04%
- p50
- 2.05s
- p99
- 12.3s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $1.26 / $3.96
atlas-cloud/fp8fp8 - Cloudflare100%Healthy24h 99.83%
- p50
- 888ms
- p99
- 10.0s
- Throughput
- 73 tps
- Context
- 262K
- $/Mtok
- $2.10 / $6.60
cloudflare/fast - CoreWeave100%Healthy24h 99.82%
- p50
- 1.22s
- p99
- 7.55s
- Throughput
- 54 tps
- Context
- 262K
- $/Mtok
- $0.760 / $2.42
coreweave/fp4fp4 - Parasail100%Healthy24h 99.83%
- p50
- 899ms
- p99
- 7.64s
- Throughput
- 92 tps
- Context
- 262K
- $/Mtok
- $1.40 / $4.40
parasail/fp4fp4 - SiliconFlow100%Healthy24h 99.95%
- p50
- 2.13s
- p99
- 28.1s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $1.19 / $3.74
siliconflow/fp8fp8 - Wafer100%Healthy24h 97.24%
- p50
- 3.25s
- p99
- 12.4s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $1.26 / $3.96
waferfp4 - Alibaba99.90%Healthy24h 99.45%
- p50
- 1.04s
- p99
- 11.5s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $0.966 / $3.04
alibaba/fp8fp8 - Novita99.84%Healthy24h 99.01%
- p50
- 3.06s
- p99
- 27.0s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $0.461 / $1.45
novita/fp8fp8 - StreamLake99.84%Healthy24h 99.81%
- p50
- 1.66s
- p99
- 7.94s
- Throughput
- 46 tps
- Context
- 1.0M
- $/Mtok
- $0.560 / $1.76
streamlake/fp8fp8 - Decart99.79%Healthy24h 99.47%
- p50
- 2.61s
- p99
- 14.0s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $0.684 / $2.28
decart/fp4fp4 - Baidu99.78%Healthy24h 99.91%
- p50
- 1.07s
- p99
- 5.53s
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $0.448 / $1.41
baidu/fp8fp8 - Crusoe99.76%Healthy24h 99.82%
- p50
- 689ms
- p99
- 6.89s
- Throughput
- 59 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
crusoe/fp8fp8 - Z.AI99.73%Healthy24h 99.22%
- p50
- 4.39s
- p99
- 15.7s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
z-ai/fp8fp8 - DigitalOcean99.65%Healthy24h 98.29%
- p50
- 2.50s
- p99
- 16.2s
- Throughput
- 20 tps
- Context
- 262K
- $/Mtok
- $0.700 / $2.20
digitalocean - Phala99.47%Healthy24h 99.63%
- p50
- 1.59s
- p99
- 10.9s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $1.26 / $3.00
phala/fp8fp8 - GMICloud99.47%Healthy24h 99.12%
- p50
- 3.00s
- p99
- 13.0s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $0.742 / $2.33
gmicloud/fp8fp8 - Inceptron99.45%Degraded24h 96.14%
- p50
- 497ms
- p99
- 8.95s
- Throughput
- 122 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $2.90
inceptron/fp4fp4 - Friendli99.33%Healthy24h 99.17%
- p50
- 1.24s
- p99
- 13.5s
- Throughput
- 61 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
friendli - DeepInfra99.21%Healthy24h 99.22%
- p50
- 1.62s
- p99
- 24.4s
- Throughput
- 29 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $2.40
deepinfra/fp4fp4 - Sail Research98.98%Healthy24h 99.56%
- p50
- 3.43s
- p99
- 40.6s
- Throughput
- 7.0 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.15
sail-research/fp8fp8 - Morph98.34%Healthy24h 98.97%
- p50
- 1.59s
- p99
- 13.8s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $1.10 / $4.10
morph/fp4fp4 - Fireworks96.97%Down24h 97.00%
- p50
- 1.19s
- p99
- 12.7s
- Throughput
- 117 tps
- Context
- 1.0M
- $/Mtok
- $2.10 / $6.60
fireworks/fast - Fireworks96.38%Healthy24h 97.79%
- p50
- 1.79s
- p99
- 27.8s
- Throughput
- 39 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
fireworks - Venice95.65%Degraded24h 98.61%
- p50
- 2.46s
- p99
- 27.5s
- Throughput
- 40 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
venice/fp8fp8 - Together90.83%Degraded24h 94.00%
- p50
- 646ms
- p99
- 19.3s
- Throughput
- 60 tps
- Context
- 512K
- $/Mtok
- $1.40 / $4.40
together - BaseTen69.60%Down24h 99.58%
- p50
- 2.10s
- p99
- 18.2s
- Throughput
- 68 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
baseten/fp8fp8 - BaseTen20.09%Down24h 99.36%
- p50
- 2.05s
- p99
- 69.0s
- Throughput
- 95 tps
- Context
- 1.0M
- $/Mtok
- $2.10 / $6.60
baseten/fastfp8 - AkashML—No data24h —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 97K
- $/Mtok
- $0.770 / $2.42
akashml/fp8fp8 - Cloudflare—No data24h 99.01%
- p50
- 2.14s
- p99
- 11.4s
- Throughput
- 59 tps
- Context
- 262K
- $/Mtok
- $1.40 / $4.40
cloudflare
Measured 4m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 endpoints reporting no data are 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.