Z.ai: GLM 5
z-ai/glm-5
Cheapest provider
$0.60 / 1M
DeepInfra
Fastest provider (p95)
—
No throughput data yet — populated as traffic accumulates
Intelligence (estimated)
73.0
Family + generation + popularity + price tier
Per-provider performance
Latency / throughput / uptime measured across providers over the last 30 minutes of live traffic. Atlas’s router weighs these per call (with the eval-gate signal) when picking a variant for Standard and Batch tiers.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| DeepInfra | q4· fp4 | $0.6000 | $2.0800 | — | — | 100.00% | — |
| GMICloud | q8· fp8 | $0.6000 | $1.9200 | — | — | 98.90% | — |
| StreamLake | undisclosed | $0.6500 | $2.0800 | — | — | 99.47% | — |
| Baidu | q8· fp8 | $0.7000 | $2.2400 | — | — | 99.88% | — |
| AtlasCloud | q8· fp8 | $0.9500 | $3.1500 | — | — | 99.54% | — |
| Chutes | q8· fp8 | $0.9500 | $2.5500 | — | — | 97.32% | — |
| SiliconFlow | q8· fp8 | $0.9500 | $2.5500 | — | — | 100.00% | — |
| Amazon Bedrock | undisclosed | $1.0000 | $3.2000 | — | — | 95.19% | — |
| Friendli | undisclosed | $1.0000 | $3.2000 | — | — | 99.94% | — |
| Novita | q8· fp8 | $1.0000 | $3.2000 | — | — | 99.91% | — |
| Parasail | q8· fp8 | $1.0000 | $3.2000 | — | — | 99.08% | — |
| Together | undisclosed | $1.0000 | $3.2000 | — | — | 98.77% | — |
| Venice | q8· fp8 | $1.0000 | $3.2000 | — | — | — | — |
| Z.AI | undisclosed | $1.0000 | $3.2000 | — | — | 99.79% | — |
| Phala | undisclosed | $1.2000 | $3.5000 | — | — | — | — |
“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).
Intelligence estimate
No public benchmark numbers indexed for this model yet, so the leaderboard score is derived from the catalogue data we sync: model family standing, generation, and live usage rank — applied identically to open- and closed-weight models. The heuristic ceiling sits below confirmed-benchmark frontier models so curated rankings stay clearly on top.
- ·glm family base
Want a curated score? File a benchmark report and we’ll add it to the next sync.
How Atlas routes Z.ai: GLM 5
- Realtime tier — direct passthrough at the upstream’s native precision. Best for hard latency / quality guarantees.
- Standard tier — Atlas picks the cheapest provider variant whose quantization has stayed green on your operation’s eval gates. For Z.ai: GLM 5 that’s currently DeepInfra at $0.60/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.