Skip to content
CostPerPrompt

GLM 4.6 API Pricing

Z.ai (GLM) · context window 205K · prices updated 2026-09-15

Input per 1M tokens
$0.43
Output per 1M tokens
$1.75
Cached input per 1M
$0.08
81% cheaper than fresh input

Where GLM 4.6 sits on price

At $1.75 per million output tokens, GLM 4.6 is a mid tier model — 1.2× cheaper than the median output price of $2.08, which puts it cheaper than 57% and pricier than 43% of the models we track. It sits 6th cheapest of the 17 Z.ai (GLM) models we track. Output costs 4.1× input, the usual spread — trim both, starting with the answer length.

Output tokens per $1
571,429
One full context fill
$0.0881
Cheaper than
57% of tracked models

Cached input is 81% cheaper. On an input-heavy workload you need roughly a 31% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.

What real workloads cost on GLM 4.6

These three workloads are the ones teams actually run on a mid-priced model — a $1.75/1M model is not bought for the same job as one ten times the price.

Workload Per request Per month
Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. $0.0046 $69.00
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0022 $650
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0.0005 $14.32

Model your exact traffic in the API cost calculator — it preloads GLM 4.6 with caching and batch options.

GLM 4.6 price history

Z.ai (GLM) last cut GLM 4.6's output price on Sep 9, 2026 (-20% per output token), from $0.55/$2.20 to $0.43/$1.75 per 1M in/out. That is one of 9 repricings in the 44 days we have tracked it — worth knowing before you hard-code today's rate into a budget.

Date Input /1M Output /1M Output change
Aug 2, 2026 (tracking began) $0.5 $2.00
Aug 11, 2026 $0.55 $2.20 +10%
Aug 13, 2026 $0.5 $2.00 -9%
Aug 14, 2026 $0.55 $2.20 +10%
Aug 21, 2026 $0.5 $2.00 -9%
Aug 28, 2026 $0.43 $1.75 -12%
Sep 3, 2026 $0.55 $2.20 +26%
Sep 7, 2026 $0.43 $1.75 -20%
Sep 8, 2026 $0.55 $2.20 +26%
Sep 9, 2026 $0.43 $1.75 -20%

Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).

GLM 4.6 vs Qwen3.5 Plus 2026-04-20

The closest-priced alternative from another vendor is Qwen3.5 Plus 2026-04-20 (Alibaba (Qwen)) — 3% more expensive on output, with $0.13 less per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.

See Qwen3.5 Plus 2026-04-20 pricing →

Cheaper alternatives

More Z.ai (GLM) models

Frequently asked questions

How much does the GLM 4.6 API cost?

GLM 4.6 costs $0.43 per million input tokens and $1.75 per million output tokens, with cached input at $0.08 per million (81% cheaper). That works out to roughly 571,429 output tokens per dollar.

What does the support chatbot workload cost on GLM 4.6?

Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0046 per request and $69.00 per month on GLM 4.6. Conversation history re-sent each turn — the classic prompt-caching win.

What does it cost to fill GLM 4.6's 205K context window?

Sending 205K of input in a single request costs $0.0881 at $0.43 per million tokens — before any output. With prompt caching that same fill drops to about $0.0164 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.

Is GLM 4.6 worth the price?

GLM 4.6 sits in the middle of the market (6 of 17 by price within Z.ai (GLM)). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.