Z.ai: GLM 4.6
z-ai/glm-4.6
Cheapest provider
$0.43 / 1M
DeepInfra
Fastest provider (p95)
49 tok/s
AtlasCloud
Intelligence (composite)
85.4
MMLU-Pro · HumanEval · math · GPQA
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 | $0.4300 | $1.7400 | 379ms / 2234ms | 24 / 37 tok/s | 100.00% | 99.8% |
| Novita | full· bf16 | $0.5500 | $2.2000 | 2232ms / 9486ms | 24 / 45 tok/s | 96.65% | 94.4% |
| AtlasCloud | q8· fp8 | $0.6000 | $2.2000 | 889ms / 13300ms | 41 / 49 tok/s | 100.00% | 100.0% |
| Z.AI | undisclosed | $0.6000 | $2.2000 | 11314ms / 28573ms | 24 / 38 tok/s | 59.33% | 60.2% |
| Venice | q4· fp4 | $0.8500 | $2.7500 | 1133ms / 3174ms | 25 / 45.2 tok/s | — | 58.6% |
“—” 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 routes Z.ai: GLM 4.6
- 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 4.6 that’s currently DeepInfra at $0.43/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.