GLM 5.3 pricing

Z.ai (GLM) · zai-glm-5.3 · 1M context · 37th cheapest of 68 current models

This row is flagged for review: new model discovered by pattern match — confirm name and rates. Check the vendor’s own page before relying on it.

What GLM 5.3 costs

USD, standard tier, global endpoint
RatePer 1M tokensPer 1K tokensWhat it covers
Input $1.4 $0.0014 Every token you send: prompt, history, documents.
Output $4.4 $0.0044 Every token the model generates, including hidden reasoning tokens.
Cached input $0.26 $0.00026 Input served from the provider’s prompt cache.

What that means in practice

The same three workloads are costed on every model page, so these numbers are directly comparable across the catalog. No prompt caching and no batch discount is assumed — the figures are what you pay before you optimise anything.

Support chatbot

2,500 six-turn conversations a day

$4,586 / month

$0.061 per conversation · $55,026 a year

An 800-token system prompt, 400-token questions and 900-token answers, over six turns — each turn re-sending everything before it.

Document summariser

1,000 single-shot summaries a day

$618 / month

$0.021 per conversation · $7,416 a year

One 12,000-token document in, an 800-token summary out, no conversation history. The case where input dominates the bill.

Coding agent

200 twelve-turn sessions a day

$3,463 / month

$0.577 per conversation · $41,558 a year

A 3,000-token system prompt, 1,500-token instructions and 2,500-token responses over twelve turns. Long sessions are where the quadratic cost of re-sent history stops being theoretical.

Change the assumptions in the calculator

Cheaper models in the catalog

Nothing cheaper is scored as highly as GLM 5.3, so these are simply the cheaper options, best-scored first. Trading down here is a real trade.

ModelInputOutputBlended saving
Kimi K2.6 $0.95 $4 20%
Grok 4.3 $1.25 $2.5 27%
DeepSeek V4 Pro $1.32 $3.96 8%
Kimi K2.5 $0.6 $3 44%
GLM-5 $1 $3.2 28%

Specification

Context window1M tokens
Maximum output128K tokens
ProviderZ.ai (GLM)
StatusCurrent
Reasoning modelYes
VisionNo
Token countingEstimated at ~3.5 characters per token (Estimate — GLM tokenizer, calibrated for mixed English/Chinese)

Where these numbers come from

Last checked against its source on 2026-08-28. Source of record: LiteLLM’s community-maintained price map.

Z.ai (GLM)’s own pricing page

Regional and data-residency premiums, priority tiers, server-side tool fees and negotiated discounts are not included. Prices change without notice; this page is rebuilt every time the catalog does.