GLM-5V-Turbo
zai-org/glm-5v-turbo
spread (output, p90 ÷ p10)
— too few providers
$4.00 – $5.00 · 3 providers · max÷min 1.3×
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 |
|---|---|---|---|---|
AIHubMix router / aggregator | $0.70 | $3.10 | $0.17 | $0.58 |
ZenMuxtiered router / aggregator | $0.73 | $3.19 | $0.17 | $0.60 |
302.AI reseller | $0.72 | $3.20 | — | $0.95no cache price published |
Cortecs router / aggregator | $1.19 | $3.96 | $0.30 | $1.00 |
LLM Gateway router / aggregator | $1.20 | $4.00 | $0.24 | $0.84 |
NanoGPT router / aggregator | $1.20 | $4.00 | $0.24 | $0.84 |
Ofox reseller | $1.20 | $4.00 | $0.24 | $0.84 |
OpenRouter router / aggregator | $1.20 | $4.00 | $0.24 | $0.84 |
SiliconFlow inference host | $1.20 | $4.00 | $0.24 | $0.84 |
Kilo Gateway router / aggregator | $1.20 | $4.00 | $0.24 | $0.84 |
Vercel AI Gateway router / aggregator | $1.20 | $4.00 | $0.24 | $0.84 |
Z.AIfirst-party first-party lab | $1.20 | $4.00 | $0.24 | $0.84 |
Eden AI router / aggregator | $1.20 | $4.00 | $0.24 | $0.84 |
TensorX unclassified | $1.20 | $4.00 | $0.30 | $1.00 |
Venice AI inference host | $1.50 | $5.00 | $0.30 | $1.05 |
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.
- Zhipu AI Coding Plan glm-5v-turbosubscription plan
- DevPass (LLM Gateway) glm-5v-turbosubscription plan
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.