AI for Less
50 sources reporting · latest verification 1 min ago

GLM 5.3 Flash (Z.AI)

View on Z.AIView on Hugging FaceView on OpenRouter

Identity and capabilities

Status
Current
Local execution
Available weights · transformers · mit Hardware requirements and licence restrictions apply.
Context window
1,000,000
Maximum output
128,000
Image input
Yes
Reasoning
Yes
Tool calling
Yes
Release date
First seen
2026-08-29 19:40:01Z UTC
Last verified

Current offers - prices in USD · per 1M tokens

CloudflareHugging Face Inference Providers⊕ 4 routes ▾Novita AIOpenRouterTogether AIZ.AI
StandardNovita
Cached input
$0.03
—
$0.03
$0.0232
$0.03
$0.03
Input
$0.15
$0.15
$0.15
$0.0232
$0.15
$0.15
Output
$0.5
$0.5
$0.5
$1.2
$0.5
$0.5
Batch
Cached input———
$0.012
——
Input———
$0.06
——
Output———
$0.2
——
Hugging Face Inference Providers · 4 routes — show all prices

The main table shows Novita: the lowest available starting token price for 2 input tokens per output token. Other input lengths, service tiers and usage ratios may favour another route.

Novita
Together AI
Baseten
DeepInfraunconfirmed
Input
$0.15
$0.15
$0.15
$0.15
Output
$0.5
$0.5
$0.5
$0.5

Active promotions

  • 50% off z-ai/glm-5.3-flash:batch

    OpenRouter · officially stated 50%

    Official source

Recent price changes

  • Prices moved both ways · cause unverified
    • Input: $0.15 → $0.0232
    • Output: $0.5 → $1.2
    OpenRouterz-ai/glm-5.3-flash