GLM-5.3-Flash

zai-org/glm-5.3-flash

Z.ai (Zhipu)· 1.0M ctx

API onlytool callreasoningstructured quant: unknown

spread (output, p90 ÷ p10)

2.5×

$0.416 – $4.47 · 20 providers · max÷min 11×

20 providers priced · 21 offerings

Including routers & resellers

Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.

Provider classes in the stats:

Blended $/M assumptionsInput : output: 1Cache-hit share of input%

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
TokenGo reseller	$0.0750	$0.0250	$0.0150	$0.0323
Merge Gateway router / aggregator	$0.0150	$0.0500	$0.00300	$0.0105
CrofAI unclassified	$0.0700	$0.220	$0.0100	$0.0455
EmpirioLabs AI unclassified	$0.0750	$0.250	$0.0750	$0.0909
302.AI reseller	$0.0750	$0.250	—	$0.0909no cache price published
NanoGPT router / aggregator	$0.0750	$0.250	$0.0150	$0.0527
OrcaRouter router / aggregator	$0.0750	$0.250	—	$0.0909no cache price published
LLM Gateway router / aggregator	$0.0880	$0.250	$0.0250	$0.0626
OpenRouter router / aggregator	$0.0900	$0.300	$0.0180	$0.0633
Cortecs router / aggregator	$0.100	$0.350	$0.0180	$0.0705
AIHubMix router / aggregator	$0.113	$0.394	$0.0282	$0.0845
RunInfra unclassified	$0.100	$0.400	$0.0100	$0.0700
Vancine reseller	$0.120	$0.400	$0.0240	$0.0844
Volcengine ArkCNoutlier hyperscaler	$0.119	$0.416	$0.0341	$0.0919
Bothub reseller	$0.120	$0.440	—	$0.149no cache price published
Melious unclassified	$0.116	$0.464	$0.0232	$0.0885
IteraCompute unclassified	$0.140	$0.490	$0.0300	$0.102
Vercel AI Gateway router / aggregator	$0.150	$0.500	$0.0300	$0.105
Baseten inference host	$0.150	$0.500	—	$0.182no cache price published
Cloudflare Workers AI inference host	$0.150	$0.500	$0.0300	$0.105
CoralBricksfp4 unclassified	$0.150	$0.500	—	$0.0864
CrossModel router / aggregator	$0.150	$0.500	$0.0300	$0.118
Deep Infra inference host	$0.150	$0.500	$0.0300	$0.105
DigitalOcean inference host	$0.150	$0.500	$0.0300	$0.105
Eden AI router / aggregator	$0.150	$0.500	$0.0300	$0.105
Fireworks AI inference host	$0.150	$0.500	$0.0300	$0.105
Friendli inference host	$0.150	$0.500	$0.0300	$0.105
Hugging Face inference host	$0.150	$0.500	—	$0.182no cache price published
Inco unclassified	$0.150	$0.500	—	$0.182no cache price published
Kilo Gateway router / aggregator	$0.150	$0.500	$0.0300	$0.105
Nebius Token Factory inference host	$0.150	$0.500	$0.150	$0.182
Neon router / aggregator	$0.150	$0.500	$0.0300	$0.105
Ofox reseller	$0.150	$0.500	$0.0300	$0.105
Ollama Cloud inference host	$0.150	$0.500	$0.0300	$0.105
OpenCode Zen router / aggregator	$0.150	$0.500	$0.0300	$0.105
OpenCode Go subscription plan	$0.150	$0.500	$0.0300	$0.105
Synthetic inference host	$0.150	$0.500	$0.0400	$0.112
Together AI inference host	$0.150	$0.500	$0.0300	$0.105
Umans AI unclassified	$0.150	$0.500	$0.0300	$0.105
Venice AI inference host	$0.150	$0.500	$0.0300	$0.105
Vivgrid unclassified	$0.150	$0.500	$0.0400	$0.112
CoreWeave inference host	$0.150	$0.500	$0.0500	$0.118
Z.AIfirst-party first-party lab	$0.150	$0.500	$0.0300	$0.105
ZenMux router / aggregator	$0.150	$0.500	$0.0300	$0.105
TensorX unclassified	$0.200	$0.500	$0.0500	$0.132
GreenPToutlier inference host	$0.128	$0.511	$0.0256	$0.0976
Charm Hyper unclassified	$0.163	$0.544	$0.0316	$0.114
above.dev unclassified	$0.165	$0.550	$0.0319	$0.115
Berget.AIoutlier inference host	$0.290	$0.580	—	$0.316no cache price published
Requesty router / aggregator	$0.200	$0.600	$0.0700	$0.154
Tinfoiloutlier inference host	$0.40	$1.25	$0.10	$0.29
Modaloutlier inference host	$0.45	$1.50	$0.09	$0.32
Privatemode AIoutlier inference host	$0.89	$4.47	$0.09	$0.71

Subscription plans (flat fee, not per-token) · 7

Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.

Umans AI Coding Plan umans-glm-5.3-flashsubscription plan
Zhipu AI Coding Plan glm-5.3-flashsubscription plan
SCNet Token Plan GLM-5.3-FlashMainland-China endpointsubscription plan
Volcengine Ark Coding Plan glm-5.3-flashMainland-China endpointsubscription plan
Z.AI Coding Plan glm-5.3-flashsubscription plan
DevPass (LLM Gateway) glm-5.3-flashsubscription plan
ClinePass cline-pass/glm-5.3-flashsubscription plan

Free tiers (rate-limited) · 1

No payment required; rate limits and quotas apply (not tracked yet). Excluded from cheapest, median and spread.

Nvidia z-ai/glm-5.3-flashNVIDIA developer account + API keyfree tier

Unpriced · 3

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.

OrcaRouter z-ai/glm-5.3-flash-freeunpriced
Kenari glm-5-3-flashunpriced
NaN glm5.3-flashunpriced

Connect

Provider (default: cheapest output among direct providers)

$0.416 /M · hyperscaler

opencode.json

{
  "provider": {
    "volcengine": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://ark.cn-beijing.volces.com/api/v3"
      },
      "models": {
        "glm-5-3-flash-260828": {}
      }
    }
  }
}

Set ARK_API_KEY in your environment. Generated — verify against the OpenCode docs.

Output $/M over time7-day preview

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.