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% | 1.61s | 6.70s | 39 tps | 1.0M | $2.31 / $7.26 |
Ambientambient/fp8fp8 | Healthy | 100% | 86.23% | 1.35s | 10.7s | 84 tps | 203K | $0.600 / $2.00 |
AtlasCloudatlas-cloud/fp8fp8 | Healthy | 100% | 99.01% | 1.53s | 6.80s | 50 tps | 1.0M | $1.26 / $3.96 |
Baidubaidu/fp8fp8 | Healthy | 100% | 99.94% | 991ms | 8.26s | 66 tps | 1.0M | $0.420 / $1.32 |
BaseTenbaseten/fastfp8 | Healthy | 100% | 99.17% | 2.01s | 14.6s | 99 tps | 1.0M | $2.10 / $6.60 |
BaseTenbaseten/fp8fp8 | Healthy | 100% | 99.44% | 1.90s | 27.3s | 75 tps | 1.0M | $1.40 / $4.40 |
Cloudflarecloudflare/fast | Healthy | 100% | 99.81% | 851ms | 4.18s | 95 tps | 262K | $2.10 / $6.60 |
Morphmorph/fp4fp4 | Healthy | 100% | 98.90% | 2.32s | 21.2s | 21 tps | 1.0M | $1.10 / $4.10 |
Parasailparasail/fp4fp4 | Healthy | 100% | 99.83% | 872ms | 7.84s | 68 tps | 262K | $1.40 / $4.40 |
Phalaphala/fp8fp8 | Healthy | 100% | 99.63% | 2.46s | 8.67s | 38 tps | 1.0M | $1.26 / $3.00 |
Sail Researchsail-research/fp8fp8 | Healthy | 100% | 99.56% | 2.21s | 37.9s | 8.0 tps | 1.0M | $0.500 / $3.15 |
SiliconFlowsiliconflow/fp8fp8 | Healthy | 100% | 99.95% | 1.96s | 32.1s | 49 tps | 1.0M | $1.19 / $3.74 |
DigitalOceandigitalocean | Healthy | 99.95% | 98.46% | 896ms | 11.5s | 57 tps | 262K | $0.700 / $2.20 |
Decartdecart/fp4fp4 | Healthy | 99.93% | 99.47% | 2.22s | 12.9s | 35 tps | 1.0M | $0.684 / $2.28 |
StreamLakestreamlake/fp8fp8 | Healthy | 99.93% | 99.83% | 1.91s | 8.99s | 41 tps | 1.0M | $0.735 / $2.31 |
Alibabaalibaba/fp8fp8 | Healthy | 99.86% | 99.47% | 1.46s | 11.8s | 44 tps | 1.0M | $0.966 / $3.04 |
DeepInfradeepinfra/fp4fp4 | Healthy | 99.77% | 99.22% | 1.54s | 19.2s | 30 tps | 1.0M | $0.750 / $2.40 |
Z.AIz-ai/fp8fp8 | Healthy | 99.63% | 99.26% | 3.98s | 22.6s | 53 tps | 1.0M | $1.40 / $4.40 |
Friendlifriendli | Healthy | 99.41% | 99.14% | 547ms | 9.10s | 108 tps | 1.0M | $1.40 / $4.40 |
Inceptroninceptron/fp4fp4 | Healthy | 99.24% | 96.26% | 576ms | 10.9s | 108 tps | 1.0M | $0.750 / $2.90 |
Fireworksfireworks | Healthy | 99.24% | 97.81% | 1.70s | 15.1s | 44 tps | 1.0M | $1.40 / $4.40 |
Fireworksfireworks/fast | Healthy | 99.02% | 97.24% | 1.14s | 9.79s | 79 tps | 1.0M | $2.10 / $6.60 |
GMICloudgmicloud/fp8fp8 | Healthy | 98.80% | 99.10% | 1.54s | 11.6s | 36 tps | 1.0M | $0.742 / $2.33 |
Crusoecrusoe/fp8fp8 | Healthy | 98.72% | 99.78% | 695ms | 12.5s | 62 tps | 1.0M | $1.40 / $4.40 |
Novitanovita/fp8fp8 | Healthy | 97.80% | 99.30% | 3.06s | 21.6s | 35 tps | 1.0M | $0.742 / $2.33 |
Togethertogether | Degraded | 91.87% | 94.27% | 822ms | 26.5s | 54 tps | 512K | $1.40 / $4.40 |
Venicevenice/fp8fp8 | Down | 71.43% | 98.59% | 1.38s | 19.1s | 48 tps | 1.0M | $1.40 / $4.40 |
AkashMLakashml/fp8fp8 | No data | — | — | — | — | — | 97K | $0.770 / $2.42 |
Cloudflarecloudflare | No data | — | 97.82% | 1.55s | 9.77s | 80 tps | 262K | $1.40 / $4.40 |
CoreWeavecoreweave/fp4fp4 | No data | — | 99.84% | 1.13s | 11.2s | 64 tps | 262K | $0.760 / $2.42 |
Waferwaferfp4 | No data | — | 97.24% | 4.44s | 16.6s | 59 tps | 1.0M | $1.26 / $3.96 |
- Alibaba100%Healthy24h 99.92%
- p50
- 1.61s
- p99
- 6.70s
- Throughput
- 39 tps
- Context
- 1.0M
- $/Mtok
- $2.31 / $7.26
alibaba/fastfp8 - Ambient100%Healthy24h 86.23%
- p50
- 1.35s
- p99
- 10.7s
- Throughput
- 84 tps
- Context
- 203K
- $/Mtok
- $0.600 / $2.00
ambient/fp8fp8 - AtlasCloud100%Healthy24h 99.01%
- p50
- 1.53s
- p99
- 6.80s
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $1.26 / $3.96
atlas-cloud/fp8fp8 - Baidu100%Healthy24h 99.94%
- p50
- 991ms
- p99
- 8.26s
- Throughput
- 66 tps
- Context
- 1.0M
- $/Mtok
- $0.420 / $1.32
baidu/fp8fp8 - BaseTen100%Healthy24h 99.17%
- p50
- 2.01s
- p99
- 14.6s
- Throughput
- 99 tps
- Context
- 1.0M
- $/Mtok
- $2.10 / $6.60
baseten/fastfp8 - BaseTen100%Healthy24h 99.44%
- p50
- 1.90s
- p99
- 27.3s
- Throughput
- 75 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
baseten/fp8fp8 - Cloudflare100%Healthy24h 99.81%
- p50
- 851ms
- p99
- 4.18s
- Throughput
- 95 tps
- Context
- 262K
- $/Mtok
- $2.10 / $6.60
cloudflare/fast - Morph100%Healthy24h 98.90%
- p50
- 2.32s
- p99
- 21.2s
- Throughput
- 21 tps
- Context
- 1.0M
- $/Mtok
- $1.10 / $4.10
morph/fp4fp4 - Parasail100%Healthy24h 99.83%
- p50
- 872ms
- p99
- 7.84s
- Throughput
- 68 tps
- Context
- 262K
- $/Mtok
- $1.40 / $4.40
parasail/fp4fp4 - Phala100%Healthy24h 99.63%
- p50
- 2.46s
- p99
- 8.67s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $1.26 / $3.00
phala/fp8fp8 - Sail Research100%Healthy24h 99.56%
- p50
- 2.21s
- p99
- 37.9s
- Throughput
- 8.0 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.15
sail-research/fp8fp8 - SiliconFlow100%Healthy24h 99.95%
- p50
- 1.96s
- p99
- 32.1s
- Throughput
- 49 tps
- Context
- 1.0M
- $/Mtok
- $1.19 / $3.74
siliconflow/fp8fp8 - DigitalOcean99.95%Healthy24h 98.46%
- p50
- 896ms
- p99
- 11.5s
- Throughput
- 57 tps
- Context
- 262K
- $/Mtok
- $0.700 / $2.20
digitalocean - Decart99.93%Healthy24h 99.47%
- p50
- 2.22s
- p99
- 12.9s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $0.684 / $2.28
decart/fp4fp4 - StreamLake99.93%Healthy24h 99.83%
- p50
- 1.91s
- p99
- 8.99s
- Throughput
- 41 tps
- Context
- 1.0M
- $/Mtok
- $0.735 / $2.31
streamlake/fp8fp8 - Alibaba99.86%Healthy24h 99.47%
- p50
- 1.46s
- p99
- 11.8s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $0.966 / $3.04
alibaba/fp8fp8 - DeepInfra99.77%Healthy24h 99.22%
- p50
- 1.54s
- p99
- 19.2s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $2.40
deepinfra/fp4fp4 - Z.AI99.63%Healthy24h 99.26%
- p50
- 3.98s
- p99
- 22.6s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
z-ai/fp8fp8 - Friendli99.41%Healthy24h 99.14%
- p50
- 547ms
- p99
- 9.10s
- Throughput
- 108 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
friendli - Inceptron99.24%Healthy24h 96.26%
- p50
- 576ms
- p99
- 10.9s
- Throughput
- 108 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $2.90
inceptron/fp4fp4 - Fireworks99.24%Healthy24h 97.81%
- p50
- 1.70s
- p99
- 15.1s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
fireworks - Fireworks99.02%Healthy24h 97.24%
- p50
- 1.14s
- p99
- 9.79s
- Throughput
- 79 tps
- Context
- 1.0M
- $/Mtok
- $2.10 / $6.60
fireworks/fast - GMICloud98.80%Healthy24h 99.10%
- p50
- 1.54s
- p99
- 11.6s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $0.742 / $2.33
gmicloud/fp8fp8 - Crusoe98.72%Healthy24h 99.78%
- p50
- 695ms
- p99
- 12.5s
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
crusoe/fp8fp8 - Novita97.80%Healthy24h 99.30%
- p50
- 3.06s
- p99
- 21.6s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $0.742 / $2.33
novita/fp8fp8 - Together91.87%Degraded24h 94.27%
- p50
- 822ms
- p99
- 26.5s
- Throughput
- 54 tps
- Context
- 512K
- $/Mtok
- $1.40 / $4.40
together - Venice71.43%Down24h 98.59%
- p50
- 1.38s
- p99
- 19.1s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
venice/fp8fp8 - AkashML—No data24h —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 97K
- $/Mtok
- $0.770 / $2.42
akashml/fp8fp8 - Cloudflare—No data24h 97.82%
- p50
- 1.55s
- p99
- 9.77s
- Throughput
- 80 tps
- Context
- 262K
- $/Mtok
- $1.40 / $4.40
cloudflare - CoreWeave—No data24h 99.84%
- p50
- 1.13s
- p99
- 11.2s
- Throughput
- 64 tps
- Context
- 262K
- $/Mtok
- $0.760 / $2.42
coreweave/fp4fp4 - Wafer—No data24h 97.24%
- p50
- 4.44s
- p99
- 16.6s
- Throughput
- 59 tps
- Context
- 1.0M
- $/Mtok
- $1.26 / $3.96
waferfp4
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
4 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, averaged over the hour.
Throughput
Median tokens per second.