NEWMEN
← back to all models

Z.ai: GLM 4.6

z-ai/glm-4.6

Z.AIopen-weight203K context5 providersIntelligence 85.4

Cheapest provider

$0.43 / 1M

DeepInfra

Fastest provider (p95)

69 tok/s

DeepInfra

Intelligence (composite)

85.4

MMLU-Pro · HumanEval · math · GPQA

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
DeepInfraq4· fp4$0.4300$1.7400530ms / 1882ms34 / 69 tok/s100.00%100.0%
Novitafull· bf16$0.5500$2.20002227ms / 13329ms28 / 43 tok/s94.78%94.8%
AtlasCloudq8· fp8$0.6000$2.20001680ms / 10957ms15 / 31.8 tok/s100.0%
Z.AIundisclosed$0.6000$2.20007387ms / 22333ms26 / 37 tok/s81.3%
Veniceq4· fp4$0.8500$2.75001159ms / 2000ms25 / 39.6 tok/s71.0%

“—” 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 breakdown

Composite score is a weighted average of public benchmarks (30% MMLU-Pro, 25% code pass@1, 25% math, 20% GPQA). Numbers come from model cards and the Artificial Analysis intelligence harness; missing components are renormalised over what’s present.

MMLU-Pro

84.6

broad reasoning

Code

82.8

pass@1 (HumanEval / LiveCodeBench)

AIME 2025

93.9

math accuracy

GPQA Diamond

79.1

hard reasoning

Source: Z.ai GLM-4.6 evaluations (MMLU-Pro 84.6, GPQA 79.1, LiveCodeBench v6 82.8, AIME25 93.9); docs.z.ai + github.com/zai-org/glm-simple-evals

How Atlas mode sources Z.ai: GLM 4.6

  • Strict mode — pin Z.ai: GLM 4.6 exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently DeepInfra at $0.43/1M.
  • 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.