Which is cheaper, GLM-4.6 or GLM-4.7?

GLM-4.7, at $1.40 per million tokens against $2 for GLM-4.6, three parts input to one part output, read on 16 Sept 2026.

Where is each one cheapest?

GLM-4.6: $2 at 302.AI. GLM-4.7: $1.40 at NanoGPT.

Can I buy both from one provider?

Yes. 30 providers sell both: NanoGPT, 302.AI, ZenMux, FastRouter, Kilo Gateway, Nous Portal, and more. The cheapest of them for the two together is NanoGPT.

Which holds more context?

Both hold 205k tokens in one call.

GLM-4.6 vs GLM-4.7.

model vs model · prices as of 16 Sept 2026

GLM-4.7 takes 1 of 5 rounds against GLM-4.6. It is also the cheaper of the two to run, at $1.40 per million tokens against $2.

Z.ai

GLM-4.6

$2/M tokens

cheapest we can explain, at 302.AI · $0.24 per 1,000 pages

205k context · tool calling · open weights

Z.aiwins 1 rounds

GLM-4.7

$1.40/M tokens

cheapest we can explain, at NanoGPT · $0.168 per 1,000 pages

205k context · tool calling · open weights

NanoGPT ↗

List price in (lower wins)

$0.60/M

List price out (lower wins)

$2.20/M

Cheapest we can explain (lower wins)

$2/M at 302.AI

$1.40/M at NanoGPT

Standard price (lower wins)

$4/M

Cost per 1,000 pages (lower wins)

$0.24

$0.168

Context

205k tokens

Open weights

yes

Tool calling

yes

Structured output

not stated

Reads images

Reasoning

yes

Released

30 Sept 2025

22 Dec 2025

Providers selling it

Price we measure against

the maker's own

Trains on your prompts (no is better)

not stated

Providers selling both · 30

NanoGPT$2.45 / $1.40
302.AI$2 / $2
ZenMux$2.59 / $1.98
FastRouter$3.03 / $2.95
Kilo Gateway$3.04 / $2.95
Nous Portal$3.04 / $2.95
OpenRouter$3.04 / $2.95
Venice$3.04 / $3.13

GLM-4.6 then GLM-4.7, per million tokens · showing the 8 cheapest of 30

Go further

open in the compare tool →every price for GLM-4.6 every price for GLM-4.7

Add a third or fourth model, or switch the weighting, in the tool.

What moved in the last seven days

GLM-4.6io.net Intelligence$0.54 / $2.07 $0.52 / $2.042% cheaper · 16 Sept 2026
GLM-4.6Nous Portal$0.34 / $1.40 $0.43 / $1.7525% dearer · 16 Sept 2026
GLM-4.7Nous Portal$0.32 / $1.40 $0.40 / $1.7525% dearer · 16 Sept 2026
GLM-4.7Venice$0.55 / $2.65 $0.40 / $1.9327% cheaper · 16 Sept 2026
GLM-4.6Ofox$0.40 / $1.90 $0.60 / $2.2029% dearer · 11 Sept 2026
GLM-4.7Ofox$0.40 / $2 $0.40 / $2.206% dearer · 11 Sept 2026

Frequently asked

Which is cheaper, GLM-4.6 or GLM-4.7?: GLM-4.7, at $1.40 per million tokens against $2 for GLM-4.6, three parts input to one part output, read on 16 Sept 2026.
Where is each one cheapest?: GLM-4.6: $2 at 302.AI. GLM-4.7: $1.40 at NanoGPT.
Can I buy both from one provider?: Yes. 30 providers sell both: NanoGPT, 302.AI, ZenMux, FastRouter, Kilo Gateway, Nous Portal, and more. The cheapest of them for the two together is NanoGPT.
Which holds more context?: Both hold 205k tokens in one call.

Prices exclude tax and are per million tokens, read 16 Sept 2026 from each provider's own catalog. The standard price blends three parts input to one part output; a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.