GLM-4.6V
zai-org/glm-4.6v
spread (output, p90 ÷ p10)
— too few providers
$0.900 – $0.900 · 2 providers · max÷min 1.0×
Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.
blended = 90.9% input × [(1 − 70% cache) × input + 70% cache × cache-read] + 9.1% × output + cache writes (30% of uncached input) where a write price is published
A provider that publishes no cache price is blended with cache share 0 (all input at the input price) and labelled “no cache price published” — never penalised against identical in/out prices.
| Provider | Input | Output | Cache rd | Blended |
|---|---|---|---|---|
302.AI reseller | $0.145 | $0.430 | — | $0.171no cache price published |
ZenMuxtiered router / aggregator | $0.146 | $0.437 | $0.0291 | $0.0979 |
Kilo Gateway router / aggregator | $0.300 | $0.900 | $0.0550 | $0.199 |
LLM Gateway router / aggregator | $0.300 | $0.900 | $0.0550 | $0.199 |
NanoGPT router / aggregator | $0.300 | $0.900 | $0.150 | $0.259 |
NovitaAI inference host | $0.300 | $0.900 | $0.0550 | $0.199 |
OpenRouter router / aggregator | $0.300 | $0.900 | $0.0550 | $0.199 |
Z.AIfirst-party first-party lab | $0.300 | $0.900 | — | $0.355no cache price published |
Eden AI router / aggregator | $0.300 | $0.900 | $0.0500 | $0.195 |
Subscription plans (flat fee, not per-token) · 2
Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.
- DevPass (LLM Gateway) glm-4.6vsubscription plan
- Zhipu AI Coding Plan glm-4.6vsubscription plan
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.