Alibaba
100.00%Context1M
Max output128K
p50 latency487 ms
Throughput169.0 t/s
Input price$2.8
Output price$8.8
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
zai/glm-5.2-fast
GLM 5.2 Fast
GLM-5.2-Fast-Preview is the high-speed variant of Zhipu AI's GLM-5.2, with 1M context and capabilities on par with the standard version. Inference-optimized to deliver 1.5–2× the output TPS, it fits latency-sensitive use cases such as real-time chat, multi-turn agents, and streaming code generation.
Input / 1M tokens$2.1
Output / 1M tokens$6.6
Maximum context1M
Inference providers3
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
100.00%Context1M
Max output128K
p50 latency464 ms
Throughput—
Input price$2.1
Output price$6.6
Zero retentionNo trainingCaching
Fireworks
100.00%Context1M
Max output128K
p50 latency873 ms
Throughput242.0 t/s
Input price$2.1
Output price$6.6
Zero retentionNo trainingCaching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Alibaba | 1M | 128K | 487 ms | 169.0 t/s | 100.000% | $2.8 | $8.8 | |
Baseten | 1M | 128K | 464 ms | — | 100.000% | $2.1 | $6.6 | |
Fireworks | 1M | 128K | 873 ms | 242.0 t/s | 100.000% | $2.1 | $6.6 |
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 23, 2026
- Knowledge cutoff
- —
- Regions
- US
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
zai/glm-5.2-fastModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.