Baseten
99.99%Context1M
Max output131K
p50 latency889 ms
Throughput229.0 t/s
Input price$0.15
Output price$0.5
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
zai/glm-5.3-flash
GLM 5.3 Flash
GLM-5.3-Flash is Z.ai’s native multimodal coding model, featuring 320B total parameters, 18B activated parameters, and a 1M-token context window. Its efficient hybrid attention architecture supports visual coding, tool use, and end-to-end professional workflows across code, browsers, documents, and graphical interfaces.
Input / 1M tokens$0.05
Output / 1M tokens$0.2
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.
Deepinfra
99.91%Context1M
Max output1M
p50 latency1,603 ms
Throughput16.0 t/s
Input price$0.075
Output price$0.25
Zero retentionNo trainingCaching
Digitalocean
100.00%Context1M
Max output1M
p50 latency434 ms
Throughput109.0 t/s
Input price$0.15
Output price$0.5
Zero retentionNo trainingCaching
Fireworks
100.00%Context1M
Max output131K
p50 latency1,289 ms
Throughput122.0 t/s
Input price$0.15
Output price$0.5
Zero retentionNo trainingCaching
Friendli
99.94%Context1M
Max output131K
p50 latency360 ms
Throughput96.0 t/s
Input price$0.15
Output price$0.5
Caching
Gmicloud
99.53%Context1M
Max output1M
p50 latency4,174 ms
Throughput60.0 t/s
Input price$0.15
Output price$0.5
Caching
Modal
99.96%Context1M
Max output1M
p50 latency382 ms
Throughput75.5 t/s
Input price$0.45
Output price$1.5
Zero retentionNo trainingCaching
Morph
100.00%Context1M
Max output1M
p50 latency965 ms
Throughput73.0 t/s
Input price$0.39
Output price$1.36
Zero retentionNo trainingCaching
Novita
100.00%Context1M
Max output128K
p50 latency1,704 ms
Throughput105.0 t/s
Input price$0.15
Output price$0.5
No trainingCaching
Parasail
100.00%Context1M
Max output1M
p50 latency723 ms
Throughput107.5 t/s
Input price$0.15
Output price$0.5
Zero retentionNo trainingCaching
Particle
100.00%Context1M
Max output131K
p50 latency1,126 ms
Throughput78.0 t/s
Input price$0.05
Output price$0.2
Zero retentionNo trainingCaching
Relace
99.84%Context1M
Max output131.1K
p50 latency1,356 ms
Throughput61.0 t/s
Input price$0.071
Output price$0.238
Caching
Runinfra
99.88%Context1M
Max output1M
p50 latency979 ms
Throughput48.0 t/s
Input price$0.1
Output price$0.4
Caching
Runware
99.60%Context131.1K
Max output131.1K
p50 latency650 ms
Throughput142.0 t/s
Input price$0.15
Output price$0.5
Caching
Streamlake
99.83%Context1M
Max output128K
p50 latency1,415 ms
Throughput82.0 t/s
Input price$0.15
Output price$0.5
Caching
Togetherai
99.92%Context1M
Max output1M
p50 latency725 ms
Throughput95.0 t/s
Input price$0.15
Output price$0.5
Zero retentionNo trainingCaching
Wafer
99.91%Context1M
Max output1M
p50 latency607 ms
Throughput28.0 t/s
Input price$0.1
Output price$0.35
Zero retentionNo trainingCaching
Zai
99.95%Context1M
Max output131K
p50 latency5,924 ms
Throughput54.0 t/s
Input price$0.15
Output price$0.5
Caching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Baseten | 1M | 131K | 889 ms | 229.0 t/s | 99.991% | $0.15 | $0.5 | |
Deepinfra | 1M | 1M | 1,603 ms | 16.0 t/s | 99.908% | $0.075 | $0.25 | |
Digitalocean | 1M | 1M | 434 ms | 109.0 t/s | 100.000% | $0.15 | $0.5 | |
Fireworks | 1M | 131K | 1,289 ms | 122.0 t/s | 99.998% | $0.15 | $0.5 | |
Friendli | 1M | 131K | 360 ms | 96.0 t/s | 99.943% | $0.15 | $0.5 | |
Gmicloud | 1M | 1M | 4,174 ms | 60.0 t/s | 99.526% | $0.15 | $0.5 | |
Modal | 1M | 1M | 382 ms | 75.5 t/s | 99.956% | $0.45 | $1.5 | |
Morph | 1M | 1M | 965 ms | 73.0 t/s | 100.000% | $0.39 | $1.36 | |
Novita | 1M | 128K | 1,704 ms | 105.0 t/s | 100.000% | $0.15 | $0.5 | |
Parasail | 1M | 1M | 723 ms | 107.5 t/s | 100.000% | $0.15 | $0.5 | |
Particle | 1M | 131K | 1,126 ms | 78.0 t/s | 99.999% | $0.05 | $0.2 | |
Relace | 1M | 131.1K | 1,356 ms | 61.0 t/s | 99.845% | $0.071 | $0.238 | |
Runinfra | 1M | 1M | 979 ms | 48.0 t/s | 99.876% | $0.1 | $0.4 | |
Runware | 131.1K | 131.1K | 650 ms | 142.0 t/s | 99.603% | $0.15 | $0.5 | |
Streamlake | 1M | 128K | 1,415 ms | 82.0 t/s | 99.831% | $0.15 | $0.5 | |
Togetherai | 1M | 1M | 725 ms | 95.0 t/s | 99.922% | $0.15 | $0.5 | |
Wafer | 1M | 1M | 607 ms | 28.0 t/s | 99.912% | $0.1 | $0.35 | |
Zai | 1M | 131K | 5,924 ms | 54.0 t/s | 99.946% | $0.15 | $0.5 |
What can this model do?
Available modalities and capabilities across inference providers.
TextImageAdvanced reasoningTool useAutomatic cachingVisionTools
Reasoning options
LowHighMax
Technical profile
- Model type
- Language model
- Release date
- Aug 26, 2026
- Knowledge cutoff
- —
- Regions
- US
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
zai/glm-5.3-flashModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.