GLM-5 Turbo
zai-org/glm-5-turbo
spread (output, p90 ÷ p10)
1.5×
$1.92 – $3.20 · 11 providers · max÷min 1.7×
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 |
|---|---|---|---|---|
NanoGPT router / aggregator | $0.60 | $1.90 | $0.10 | $0.40 |
GMI Cloudfp8 inference host | $0.60 | $1.92 | $0.12 | $0.41 |
Deep Infra inference host | $0.60 | $2.08 | $0.12 | $0.43 |
FastRouter router / aggregator | $0.60 | $2.08 | $0.12 | $0.43 |
LLM Gateway router / aggregator | $0.72 | $2.30 | $0.14 | $0.50 |
DInference unclassified | $0.75 | $2.40 | — | $0.90no cache price published |
SiliconFlow inference host | $0.95 | $2.55 | $0.20 | $0.62 |
Meganova unclassified | $0.80 | $2.56 | $0.20 | $0.58 |
Alibaba (China)CNtiered first-party lab | $0.57 | $2.58 | — | $0.76no cache price published |
ZenMuxtiered router / aggregator | $0.58 | $2.60 | $0.14 | $0.48 |
302.AItiered reseller | $0.60 | $2.60 | — | $0.78no cache price published |
Qiniutiered hyperscaler | $0.58 | $2.61 | — | $0.76no cache price published |
Zhipu AIfirst-partytiered first-party lab | $0.60 | $2.69 | $0.15 | $0.50 |
CrossModeltiered router / aggregator | $0.60 | $3.00 | $0.16 | $0.59 |
Baseten inference host | $0.95 | $3.15 | $0.20 | $0.67 |
Hugging Face inference host | $1.00 | $3.20 | $0.20 | $0.69 |
Kilo Gateway router / aggregator | $1.00 | $3.20 | $0.20 | $0.69 |
Impossibl unclassified | $1.00 | $3.20 | $0.20 | $0.69 |
Merge Gateway router / aggregator | $1.00 | $3.20 | $0.20 | $0.69 |
Novita AI inference host | $1.00 | $3.20 | $0.20 | $0.69 |
Ofox reseller | $1.00 | $3.20 | $0.20 | $0.69 |
OpenCode router / aggregator | $1.00 | $3.20 | $0.20 | $0.69 |
Eden AI router / aggregator | $1.00 | $3.20 | $0.20 | $0.69 |
OpenRouter router / aggregator | $1.00 | $3.20 | $0.20 | $0.69 |
OrcaRouter router / aggregator | $1.00 | $3.20 | $0.26 | $0.73 |
Poe router / aggregator | $1.00 | $3.20 | $0.20 | $0.69 |
DigitalOcean inference host | $1.00 | $3.20 | $0.20 | $0.69 |
Tempr Gateway unclassified | $1.00 | $3.20 | $0.20 | $0.69 |
TensorX unclassified | $1.00 | $3.20 | $0.25 | $0.83 |
Together AI inference host | $1.00 | $3.20 | — | $1.20no cache price published |
Vercel AI Gateway router / aggregator | $1.00 | $3.20 | — | $1.20no cache price published |
Abacus router / aggregator | $1.00 | $3.20 | — | $1.20no cache price published |
TokenGo reseller | $0.89 | $3.26 | $0.22 | $0.68 |
Melious unclassified | $1.10 | $3.36 | $0.27 | $0.78 |
AI/ML API unclassified | $1.56 | $5.20 | $0.31 | $1.10 |
Subscription plans (flat fee, not per-token) · 9
Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.
- Z.AI Coding Plan glm-5-turbosubscription plan
- Alibaba Coding Plan glm-5subscription plan
- Alibaba Coding Plan (China) glm-5Mainland-China endpointsubscription plan
- Alibaba Token Plan glm-5subscription plan
- Alibaba Token Plan (China) glm-5Mainland-China endpointsubscription plan
- Tencent Coding Plan (China) glm-5Mainland-China endpointsubscription plan
- SCNet Token Plan GLM-5Mainland-China endpointsubscription plan
- DevPass (LLM Gateway) glm-5subscription plan
- DevPass (LLM Gateway) glm-5-turbosubscription plan
Unpriced · 1
Listed at $0 with no published pricing — we can't tell whether it's free, bundled or just missing. Excluded from cheapest, median and spread.
- OpenCode glm-5-freeunpriced
Data: models.dev (MIT), snapshot 2026-10-22. Prices are vendor-published; verify before purchase. Methodology.