Deepinfra
100.00%Context202.8K
Max output202.8K
p50 latency354 ms
Throughput48.0 t/s
Input price$0.5
Output price$2
Zero retentionNo trainingCaching
Model directory
Baseer model profileLanguage model
zai/glm-4.6
GLM 4.6
As the latest iteration in the GLM series, GLM-4.6 achieves comprehensive enhancements across multiple domains, including real-world coding, long-context processing, reasoning, searching, writing, and agentic applications.
Input / 1M tokens$0.5
Output / 1M tokens$2
Maximum context204.8K
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.
Novita
100.00%Context204.8K
Max output131.1K
p50 latency1,179 ms
Throughput82.0 t/s
Input price$0.6
Output price$2.2
No trainingCaching
Zai
99.36%Context200K
Max output96K
p50 latency4,836 ms
Throughput102.5 t/s
Input price$0.6
Output price$2.2
Caching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Deepinfra | 202.8K | 202.8K | 354 ms | 48.0 t/s | 100.000% | $0.5 | $2 | |
Novita | 204.8K | 131.1K | 1,179 ms | 82.0 t/s | 100.000% | $0.6 | $2.2 | |
Zai | 200K | 96K | 4,836 ms | 102.5 t/s | 99.358% | $0.6 | $2.2 |
What can this model do?
Available modalities and capabilities across inference providers.
TextAdvanced reasoningAutomatic cachingTool useTools
Technical profile
- Model type
- Language model
- Release date
- Sep 30, 2025
- Knowledge cutoff
- 2025-04
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
zai/glm-4.6Model profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.