Alibaba
99.99%Context1M
Max output128K
p50 latency2,882 ms
Throughput67.0 t/s
Input price$1.4
Output price$4.4
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
zai/glm-5.2
GLM 5.2
GLM-5.2 delivers powerful coding capabilities, usable 1M-context support, and continued strengths in long-horizon tasks.
Input / 1M tokens$0.7
Output / 1M tokens$2.2
Maximum context1M
Inference providers18
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Baseten
99.16%Context1M
Max output128K
p50 latency1,598 ms
Throughput123.0 t/s
Input price$1.4
Output price$4.4
Zero retentionNo trainingCaching
Blackbox
50.40%Context1M
Max output128K
p50 latency—
Throughput—
Input price$0.8
Output price$2.55
Caching
Crusoe
97.30%Context262.1K
Max output128K
p50 latency463 ms
Throughput390.5 t/s
Input price$1.4
Output price$4.4
Caching
Deepinfra
99.95%Context1M
Max output128K
p50 latency450 ms
Throughput92.5 t/s
Input price$0.75
Output price$2.4
Zero retentionNo trainingCaching
Digitalocean
99.74%Context262.1K
Max output52.4K
p50 latency388 ms
Throughput141.0 t/s
Input price$0.7
Output price$2.2
Zero retentionNo trainingCaching
Fireworks
100.00%Context1M
Max output128K
p50 latency722 ms
Throughput104.0 t/s
Input price$1.4
Output price$4.4
Zero retentionNo trainingCaching
Friendli
100.00%Context1M
Max output128K
p50 latency198 ms
Throughput152.5 t/s
Input price$1.4
Output price$4.4
Caching
Gmicloud
96.66%Context1M
Max output1M
p50 latency3,633 ms
Throughput61.0 t/s
Input price$1.05
Output price$3.3
Caching
Inceptron
100.00%Context1M
Max output1M
p50 latency603 ms
Throughput60.5 t/s
Input price$1.2
Output price$4.2
No trainingCaching
Morph
100.00%Context1M
Max output128K
p50 latency868 ms
Throughput224.5 t/s
Input price$0.842
Output price$3.14
Zero retentionNo trainingCaching
Nebius
100.00%Context1M
Max output1M
p50 latency729 ms
Throughput578.0 t/s
Input price$1.4
Output price$4.4
Zero retentionNo trainingCaching
Novita
99.98%Context1M
Max output128K
p50 latency1,507 ms
Throughput65.5 t/s
Input price$0.904
Output price$2.84
No trainingCaching
Parasail
98.27%Context262.1K
Max output128K
p50 latency592 ms
Throughput155.0 t/s
Input price$1.4
Output price$4.4
Zero retentionNo trainingCaching
Runware
99.83%Context1M
Max output128K
p50 latency2,295 ms
Throughput77.0 t/s
Input price$0.8
Output price$2.55
Caching
Streamlake
99.93%Context1M
Max output128K
p50 latency1,943 ms
Throughput105.0 t/s
Input price$0.803
Output price$2.52
Caching
Togetherai
99.94%Context256K
Max output128K
p50 latency178 ms
Throughput214.0 t/s
Input price$1.4
Output price$4.4
Zero retentionNo trainingCaching
Zai
100.00%Context1M
Max output128K
p50 latency2,767 ms
Throughput86.0 t/s
Input price$1.4
Output price$4.4
Caching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Alibaba | 1M | 128K | 2,882 ms | 67.0 t/s | 99.992% | $1.4 | $4.4 | |
Baseten | 1M | 128K | 1,598 ms | 123.0 t/s | 99.162% | $1.4 | $4.4 | |
Blackbox | 1M | 128K | — | — | 50.404% | $0.8 | $2.55 | |
Crusoe | 262.1K | 128K | 463 ms | 390.5 t/s | 97.295% | $1.4 | $4.4 | |
Deepinfra | 1M | 128K | 450 ms | 92.5 t/s | 99.947% | $0.75 | $2.4 | |
Digitalocean | 262.1K | 52.4K | 388 ms | 141.0 t/s | 99.743% | $0.7 | $2.2 | |
Fireworks | 1M | 128K | 722 ms | 104.0 t/s | 99.996% | $1.4 | $4.4 | |
Friendli | 1M | 128K | 198 ms | 152.5 t/s | 100.000% | $1.4 | $4.4 | |
Gmicloud | 1M | 1M | 3,633 ms | 61.0 t/s | 96.661% | $1.05 | $3.3 | |
Inceptron | 1M | 1M | 603 ms | 60.5 t/s | 100.000% | $1.2 | $4.2 | |
Morph | 1M | 128K | 868 ms | 224.5 t/s | 100.000% | $0.842 | $3.14 | |
Nebius | 1M | 1M | 729 ms | 578.0 t/s | 100.000% | $1.4 | $4.4 | |
Novita | 1M | 128K | 1,507 ms | 65.5 t/s | 99.981% | $0.904 | $2.84 | |
Parasail | 262.1K | 128K | 592 ms | 155.0 t/s | 98.266% | $1.4 | $4.4 | |
Runware | 1M | 128K | 2,295 ms | 77.0 t/s | 99.830% | $0.8 | $2.55 | |
Streamlake | 1M | 128K | 1,943 ms | 105.0 t/s | 99.931% | $0.803 | $2.52 | |
Togetherai | 256K | 128K | 178 ms | 214.0 t/s | 99.936% | $1.4 | $4.4 | |
Zai | 1M | 128K | 2,767 ms | 86.0 t/s | 100.000% | $1.4 | $4.4 |
What can this model do?
Available modalities and capabilities across inference providers.
TextAdvanced reasoningTool useAutomatic cachingTools
Reasoning options
HighXhigh
Technical profile
- Model type
- Language model
- Release date
- Jun 16, 2026
- Knowledge cutoff
- —
- Regions
- US
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
zai/glm-5.2Model profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.