NEWMEN
← back to all models

Z.ai: GLM 5.1

z-ai/glm-5.1

Z.AIopen-weight203K context19 providersIntelligence 73.5· est.

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.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
Baiduq8· fp8$0.9800$3.080094.78%
GMICloudq8· fp8$0.9800$3.080090.06%
DeepInfraq4· fp4$1.0500$3.500099.96%
StreamLakeundisclosed$1.1900$3.740099.83%
Chutesq8· fp8$1.2000$4.000040.17%
Phalaundisclosed$1.2100$4.200078.00%
AtlasCloudq8· fp8$1.2600$3.960099.44%
BaseTenq4· fp4$1.3000$4.3000100.00%
Io Netq8· fp8$1.3000$4.2000100.00%
Novitaq8· fp8$1.3800$4.400091.33%
Ambientq8· fp8$1.4000$4.400098.84%
Fireworksundisclosed$1.4000$4.400098.45%
Friendliundisclosed$1.4000$4.400099.79%
Inceptronq8· fp8$1.4000$4.400098.90%
Parasailq8· fp8$1.4000$4.400097.63%
SiliconFlowq8· fp8$1.4000$4.400098.68%
Togetherundisclosed$1.4000$4.400097.55%
Z.AIundisclosed$1.4000$4.400098.11%
Veniceq8· 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.

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.