NEWMEN
← back to all models

Z.ai: GLM 4.7

z-ai/glm-4.7

Z.AIopen-weight203K context11 providersIntelligence 76.5· est.

Cheapest provider

$0.40 / 1M

DeepInfra

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

Intelligence (estimated)

76.5

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.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
DeepInfraq4· fp4$0.4000$1.750096.40%
StreamLakeundisclosed$0.4200$1.540095.23%
Parasailq8· fp8$0.4500$2.100099.78%
SiliconFlowq8· fp8$0.4500$2.2000
AtlasCloudq8· fp8$0.5200$1.850097.05%
Novitaq8· fp8$0.5400$1.980088.64%
Veniceq4· fp4$0.5500$2.6500100.00%
Googleundisclosed$0.6000$2.2000100.00%
Z.AIundisclosed$0.6000$2.200081.08%
Phalaundisclosed$0.8500$3.3000100.00%
Cerebrasfull· fp16$2.2500$2.7500100.00%

“—” 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 routes Z.ai: GLM 4.7

  • 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 4.7 that’s currently DeepInfra at $0.40/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.