Z.ai: GLM 5.1
z-ai/glm-5.1
Cheapest provider
$0.98 / 1M
Baidu
Fastest provider (p95)
—
No throughput data yet — populated as traffic accumulates
Intelligence (estimated)
73.5
Family + generation + popularity + price tier
Per-provider performance
Latency / throughput / uptime / price measured across providers over the last 30 minutes of live traffic. This is what proves “sourced cheapest” — Atlas mode draws on these per call to serve the cheapest path that holds quality.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| Baidu | q8· fp8 | $0.9800 | $3.0800 | — | — | 94.78% | — |
| GMICloud | q8· fp8 | $0.9800 | $3.0800 | — | — | 90.06% | — |
| DeepInfra | q4· fp4 | $1.0500 | $3.5000 | — | — | 99.96% | — |
| StreamLake | undisclosed | $1.1900 | $3.7400 | — | — | 99.83% | — |
| Chutes | q8· fp8 | $1.2000 | $4.0000 | — | — | 40.17% | — |
| Phala | undisclosed | $1.2100 | $4.2000 | — | — | 78.00% | — |
| AtlasCloud | q8· fp8 | $1.2600 | $3.9600 | — | — | 99.44% | — |
| BaseTen | q4· fp4 | $1.3000 | $4.3000 | — | — | 100.00% | — |
| Io Net | q8· fp8 | $1.3000 | $4.2000 | — | — | 100.00% | — |
| Novita | q8· fp8 | $1.3800 | $4.4000 | — | — | 91.33% | — |
| Ambient | q8· fp8 | $1.4000 | $4.4000 | — | — | 98.84% | — |
| Fireworks | undisclosed | $1.4000 | $4.4000 | — | — | 98.45% | — |
| Friendli | undisclosed | $1.4000 | $4.4000 | — | — | 99.79% | — |
| Inceptron | q8· fp8 | $1.4000 | $4.4000 | — | — | 98.90% | — |
| Parasail | q8· fp8 | $1.4000 | $4.4000 | — | — | 97.63% | — |
| SiliconFlow | q8· fp8 | $1.4000 | $4.4000 | — | — | 98.68% | — |
| Together | undisclosed | $1.4000 | $4.4000 | — | — | 97.55% | — |
| Z.AI | undisclosed | $1.4000 | $4.4000 | — | — | 98.11% | — |
| Venice | q8· fp8 | $1.7500 | $5.5000 | — | — | — | — |
“—” 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
- ·v5.1 generation +1
Want a curated score? File a benchmark report and we’ll add it to the next sync.
How Atlas mode sources Z.ai: GLM 5.1
- Strict mode — pin Z.ai: GLM 5.1 exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently Baidu at $0.98/1M.
- Atlas mode — the default. Each call is auto-optimized for the cheapest path that holds quality, at least 5% off going direct from call one and climbing as it ramps. You always see which model served the call and exactly what you saved — thumbs-down anything you don’t like for a full refund.