GLM 5.2
z-ai/glm-5.2
CompareGLM 5.2
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 98.92% | 99.86% | 99.86% | 1.77s | 7.85s | 48 tps | 1.0M | $2.31 / $7.26 | |
| Healthy | 100% | 99.84% | 99.83% | 99.83% | 1.06s | 6.25s | 47 tps | 1.0M | $1.40 / $4.40 | |
| Healthy | 100% | 99.73% | 99.46% | 99.46% | 1.79s | 33.7s | 90 tps | 1.0M | $2.10 / $6.60 | |
| Healthy | 100% | 99.60% | 99.61% | 99.61% | 1.56s | 26.6s | 51 tps | 1.0M | $1.40 / $4.40 | |
Cloudflarecloudflare | Healthy | 100% | 100% | 99.83% | 99.83% | 1.30s | 13.3s | 65 tps | 262K | $1.40 / $4.40 |
Cloudflarecloudflare/fast | Healthy | 100% | 99.91% | 99.92% | 99.92% | 1.11s | 10.9s | 78 tps | 262K | $2.10 / $6.60 |
| Healthy | 100% | 99.91% | 99.81% | 99.81% | 528ms | 10.6s | 142 tps | 262K | $0.760 / $2.42 | |
| Healthy | 100% | 99.68% | 99.77% | 99.77% | 762ms | 16.3s | 74 tps | 1.0M | $1.40 / $4.40 | |
| Healthy | 100% | 99.90% | 99.89% | 99.89% | 662ms | 9.80s | 104 tps | 262K | $1.40 / $4.40 | |
| Healthy | 100% | 96.35% | 99.69% | 99.69% | 1.59s | 10.5s | 38 tps | 1.0M | $1.26 / $3.00 | |
| Healthy | 100% | 98.91% | 99.69% | 99.69% | 1.68s | 23.5s | 58 tps | 1.0M | $1.19 / $3.74 | |
| Healthy | 100% | 98.37% | 98.62% | 98.62% | 1.71s | 31.1s | 45 tps | 1.0M | $1.40 / $4.40 | |
| Healthy | 100% | 99.86% | 99.61% | 99.61% | 1.29s | 15.9s | 48 tps | 1.0M | $1.40 / $4.40 | |
| Healthy | 99.93% | 99.64% | 99.61% | 99.61% | 1.27s | 12.3s | 31 tps | 1.0M | $0.500 / $3.15 | |
| Healthy | 99.88% | 99.59% | 99.39% | 99.39% | 1.58s | 12.4s | 47 tps | 1.0M | $0.741 / $2.33 | |
Friendlifriendli | Healthy | 99.80% | 99.69% | 99.18% | 99.18% | 394ms | 7.90s | 110 tps | 1.0M | $1.40 / $4.40 |
| Healthy | 99.65% | 96.16% | 96.66% | 96.66% | 760ms | 17.6s | 88 tps | 1.0M | $0.750 / $2.90 | |
Fireworksfireworks | Healthy | 99.39% | 98.28% | 98.74% | 98.74% | 1.78s | 24.4s | 44 tps | 1.0M | $1.40 / $4.40 |
| Degraded | 99.35% | 98.96% | 98.78% | 98.78% | 2.30s | 27.6s | 47 tps | 1.0M | $0.684 / $2.28 | |
DigitalOceandigitalocean | Healthy | 98.80% | 99.20% | 99.10% | 99.10% | 1.12s | 15.3s | 40 tps | 262K | $0.700 / $2.20 |
| Healthy | 98.52% | 99.12% | 99.78% | 99.78% | 922ms | 7.51s | 38 tps | 1.0M | $1.26 / $3.96 | |
| Healthy | 97.81% | 99.50% | 99.28% | 99.28% | 1.17s | 21.2s | 38 tps | 1.0M | $0.750 / $2.40 | |
Fireworksfireworks/fast | Healthy | 97.30% | 95.82% | 97.33% | 97.33% | 1.09s | 7.19s | 85 tps | 1.0M | $2.10 / $6.60 |
| Healthy | 97.10% | 98.92% | 98.77% | 98.77% | 4.35s | 8.93s | 53 tps | 1.0M | $1.26 / $3.96 | |
Fireworksfireworks/fast-us | Healthy | 96.97% | 94.71% | 96.44% | 96.44% | 1.47s | 21.8s | 87 tps | 1.0M | $2.10 / $6.60 |
| Healthy | 96.39% | 90.69% | 92.51% | 92.51% | 1.15s | 12.8s | 28 tps | 203K | $0.600 / $2.00 | |
| Degraded | 92.45% | 92.29% | 95.85% | 95.85% | 1.66s | 29.5s | 17 tps | 1.0M | $0.842 / $3.14 | |
Togethertogether | Down | 88.24% | 90.80% | 95.55% | 95.55% | 832ms | 19.0s | 54 tps | 512K | $1.40 / $4.40 |
| Down | 86.29% | 99.19% | 99.74% | 99.74% | 1.37s | 10.1s | 47 tps | 1.0M | $0.734 / $2.31 | |
| Down | 77.59% | 98.69% | 99.63% | 99.63% | 865ms | 10.5s | 54 tps | 1.0M | $0.966 / $3.04 | |
| Down | 77.03% | 95.44% | 99.48% | 99.48% | 1.49s | 9.76s | 32 tps | 1.0M | $0.742 / $2.33 | |
| No data | — | — | 97.12% | 97.12% | — | — | — | 97K | $0.770 / $2.42 |
- Alibaba100%Healthy24h 98.92%
- 7d
- 99.86%
- 30d
- 99.86%
- p50
- 1.77s
- p99
- 7.85s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $2.31 / $7.26
alibaba/fastfp8 - Baidu100%Healthy24h 99.84%
- 7d
- 99.83%
- 30d
- 99.83%
- p50
- 1.06s
- p99
- 6.25s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
baidu/fp8fp8 - BaseTen100%Healthy24h 99.73%
- 7d
- 99.46%
- 30d
- 99.46%
- p50
- 1.79s
- p99
- 33.7s
- Throughput
- 90 tps
- Context
- 1.0M
- $/Mtok
- $2.10 / $6.60
baseten/fastfp8 - BaseTen100%Healthy24h 99.60%
- 7d
- 99.61%
- 30d
- 99.61%
- p50
- 1.56s
- p99
- 26.6s
- Throughput
- 51 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
baseten/fp8fp8 - Cloudflare100%Healthy24h 100%
- 7d
- 99.83%
- 30d
- 99.83%
- p50
- 1.30s
- p99
- 13.3s
- Throughput
- 65 tps
- Context
- 262K
- $/Mtok
- $1.40 / $4.40
cloudflare - Cloudflare100%Healthy24h 99.91%
- 7d
- 99.92%
- 30d
- 99.92%
- p50
- 1.11s
- p99
- 10.9s
- Throughput
- 78 tps
- Context
- 262K
- $/Mtok
- $2.10 / $6.60
cloudflare/fast - CoreWeave100%Healthy24h 99.91%
- 7d
- 99.81%
- 30d
- 99.81%
- p50
- 528ms
- p99
- 10.6s
- Throughput
- 142 tps
- Context
- 262K
- $/Mtok
- $0.760 / $2.42
coreweave/fp4fp4 - Crusoe100%Healthy24h 99.68%
- 7d
- 99.77%
- 30d
- 99.77%
- p50
- 762ms
- p99
- 16.3s
- Throughput
- 74 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
crusoe/fp8fp8 - Parasail100%Healthy24h 99.90%
- 7d
- 99.89%
- 30d
- 99.89%
- p50
- 662ms
- p99
- 9.80s
- Throughput
- 104 tps
- Context
- 262K
- $/Mtok
- $1.40 / $4.40
parasail/fp4fp4 - Phala100%Healthy24h 96.35%
- 7d
- 99.69%
- 30d
- 99.69%
- p50
- 1.59s
- p99
- 10.5s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $1.26 / $3.00
phala/fp8fp8 - SiliconFlow100%Healthy24h 98.91%
- 7d
- 99.69%
- 30d
- 99.69%
- p50
- 1.68s
- p99
- 23.5s
- Throughput
- 58 tps
- Context
- 1.0M
- $/Mtok
- $1.19 / $3.74
siliconflow/fp8fp8 - Venice100%Healthy24h 98.37%
- 7d
- 98.62%
- 30d
- 98.62%
- p50
- 1.71s
- p99
- 31.1s
- Throughput
- 45 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
venice/fp8fp8 - Z.AI100%Healthy24h 99.86%
- 7d
- 99.61%
- 30d
- 99.61%
- p50
- 1.29s
- p99
- 15.9s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
z-ai/fp8fp8 - Sail Research99.93%Healthy24h 99.64%
- 7d
- 99.61%
- 30d
- 99.61%
- p50
- 1.27s
- p99
- 12.3s
- Throughput
- 31 tps
- Context
- 1.0M
- $/Mtok
- $0.500 / $3.15
sail-research/fp8fp8 - Novita99.88%Healthy24h 99.59%
- 7d
- 99.39%
- 30d
- 99.39%
- p50
- 1.58s
- p99
- 12.4s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $0.741 / $2.33
novita/fp8fp8 - Friendli99.80%Healthy24h 99.69%
- 7d
- 99.18%
- 30d
- 99.18%
- p50
- 394ms
- p99
- 7.90s
- Throughput
- 110 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
friendli - Inceptron99.65%Healthy24h 96.16%
- 7d
- 96.66%
- 30d
- 96.66%
- p50
- 760ms
- p99
- 17.6s
- Throughput
- 88 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $2.90
inceptron/fp4fp4 - Fireworks99.39%Healthy24h 98.28%
- 7d
- 98.74%
- 30d
- 98.74%
- p50
- 1.78s
- p99
- 24.4s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $1.40 / $4.40
fireworks - Decart99.35%Degraded24h 98.96%
- 7d
- 98.78%
- 30d
- 98.78%
- p50
- 2.30s
- p99
- 27.6s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $0.684 / $2.28
decart/fp4fp4 - DigitalOcean98.80%Healthy24h 99.20%
- 7d
- 99.10%
- 30d
- 99.10%
- p50
- 1.12s
- p99
- 15.3s
- Throughput
- 40 tps
- Context
- 262K
- $/Mtok
- $0.700 / $2.20
digitalocean - AtlasCloud98.52%Healthy24h 99.12%
- 7d
- 99.78%
- 30d
- 99.78%
- p50
- 922ms
- p99
- 7.51s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $1.26 / $3.96
atlas-cloud/fp8fp8 - DeepInfra97.81%Healthy24h 99.50%
- 7d
- 99.28%
- 30d
- 99.28%
- p50
- 1.17s
- p99
- 21.2s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $0.750 / $2.40
deepinfra/fp4fp4 - Fireworks97.30%Healthy24h 95.82%
- 7d
- 97.33%
- 30d
- 97.33%
- p50
- 1.09s
- p99
- 7.19s
- Throughput
- 85 tps
- Context
- 1.0M
- $/Mtok
- $2.10 / $6.60
fireworks/fast - Wafer97.10%Healthy24h 98.92%
- 7d
- 98.77%
- 30d
- 98.77%
- p50
- 4.35s
- p99
- 8.93s
- Throughput
- 53 tps
- Context
- 1.0M
- $/Mtok
- $1.26 / $3.96
waferfp4 - Fireworks96.97%Healthy24h 94.71%
- 7d
- 96.44%
- 30d
- 96.44%
- p50
- 1.47s
- p99
- 21.8s
- Throughput
- 87 tps
- Context
- 1.0M
- $/Mtok
- $2.10 / $6.60
fireworks/fast-us - Ambient96.39%Healthy24h 90.69%
- 7d
- 92.51%
- 30d
- 92.51%
- p50
- 1.15s
- p99
- 12.8s
- Throughput
- 28 tps
- Context
- 203K
- $/Mtok
- $0.600 / $2.00
ambient/fp8fp8 - Morph92.45%Degraded24h 92.29%
- 7d
- 95.85%
- 30d
- 95.85%
- p50
- 1.66s
- p99
- 29.5s
- Throughput
- 17 tps
- Context
- 1.0M
- $/Mtok
- $0.842 / $3.14
morph/fp4fp4 - Together88.24%Down24h 90.80%
- 7d
- 95.55%
- 30d
- 95.55%
- p50
- 832ms
- p99
- 19.0s
- Throughput
- 54 tps
- Context
- 512K
- $/Mtok
- $1.40 / $4.40
together - StreamLake86.29%Down24h 99.19%
- 7d
- 99.74%
- 30d
- 99.74%
- p50
- 1.37s
- p99
- 10.1s
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $0.734 / $2.31
streamlake/fp8fp8 - Alibaba77.59%Down24h 98.69%
- 7d
- 99.63%
- 30d
- 99.63%
- p50
- 865ms
- p99
- 10.5s
- Throughput
- 54 tps
- Context
- 1.0M
- $/Mtok
- $0.966 / $3.04
alibaba/fp8fp8 - GMICloud77.03%Down24h 95.44%
- 7d
- 99.48%
- 30d
- 99.48%
- p50
- 1.49s
- p99
- 9.76s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $0.742 / $2.33
gmicloud/fp8fp8 - No data24h —
- 7d
- 97.12%
- 30d
- 97.12%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 97K
- $/Mtok
- $0.770 / $2.42
akashml/fp8fp8
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- GLM 5.2Morphmorph/fp4$0.935 / $3.48 → $0.842 / $3.142026-08-21 08:31 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.210 / $0.660 → $0.734 / $2.312026-08-21 02:31 UTC
- GLM 5.2Morphmorph/fp4$1.10 / $4.10 → $0.935 / $3.482026-08-21 01:16 UTC
- GLM 5.2Baidubaidu/fp8$0.490 / $1.54 → $1.40 / $4.402026-08-20 23:36 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.140 / $0.440 → $0.210 / $0.6602026-08-20 17:26 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.280 / $0.880 → $0.140 / $0.4402026-08-20 17:06 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.734 / $2.31 → $0.280 / $0.8802026-08-20 16:06 UTC
- GLM 5.2Baidubaidu/fp8$1.18 / $3.70 → $0.490 / $1.542026-08-20 13:46 UTC
- GLM 5.2Baidubaidu/fp8$1.40 / $4.40 → $1.18 / $3.702026-08-20 12:51 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.658 / $2.07 → $0.734 / $2.312026-08-20 06:41 UTC
- GLM 5.2Novitanovita/fp8$0.665 / $2.09 → $0.741 / $2.332026-08-20 06:26 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.666 / $2.09 → $0.658 / $2.072026-08-20 06:11 UTC
- GLM 5.2Novitanovita/fp8$0.673 / $2.12 → $0.665 / $2.092026-08-20 05:46 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.675 / $2.12 → $0.666 / $2.092026-08-20 05:26 UTC
- GLM 5.2Novitanovita/fp8$0.682 / $2.14 → $0.673 / $2.122026-08-20 05:11 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.683 / $2.15 → $0.675 / $2.122026-08-20 05:01 UTC
- GLM 5.2Novitanovita/fp8$0.690 / $2.17 → $0.682 / $2.142026-08-20 04:46 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.692 / $2.17 → $0.683 / $2.152026-08-20 04:26 UTC
- GLM 5.2Novitanovita/fp8$0.699 / $2.20 → $0.690 / $2.172026-08-20 04:11 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.700 / $2.20 → $0.692 / $2.172026-08-20 03:51 UTC
- GLM 5.2Novitanovita/fp8$0.707 / $2.22 → $0.699 / $2.202026-08-20 03:21 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.708 / $2.23 → $0.700 / $2.202026-08-20 03:01 UTC
- GLM 5.2Novitanovita/fp8$0.715 / $2.25 → $0.707 / $2.222026-08-20 02:46 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.717 / $2.25 → $0.708 / $2.232026-08-20 02:36 UTC
- GLM 5.2Novitanovita/fp8$0.724 / $2.27 → $0.715 / $2.252026-08-20 01:16 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.725 / $2.28 → $0.717 / $2.252026-08-20 01:06 UTC
- GLM 5.2Novitanovita/fp8$0.732 / $2.30 → $0.724 / $2.272026-08-20 00:51 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.734 / $2.31 → $0.725 / $2.282026-08-20 00:36 UTC
- GLM 5.2Novitanovita/fp8$0.741 / $2.33 → $0.732 / $2.302026-08-20 00:20 UTC
- GLM 5.2StreamLakestreamlake/fp8$0.735 / $2.31 → $0.734 / $2.312026-08-19 23:40 UTC
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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.