DeepSeek V3.1 Terminus vs GLM-4.6V.
model vs model · prices as of
GLM-4.6V takes 3 of 5 rounds against DeepSeek V3.1 Terminus. It is also the cheaper of the two to run, at $0.84 per million tokens against $1.45.
DeepSeek V3.1 Terminus
$1.45/M tokens
cheapest we can explain, at NanoGPT · $0.192 per 1,000 pages
164k context · tool calling · open weights
List price in (lower wins)
$0.27/M
$0.30/M
List price out (lower wins)
$1/M
$0.90/M
Cheapest we can explain (lower wins)
$1.45/M at NanoGPT
$0.84/M at ZenMux
Standard price (lower wins)
$1.81/M
$1.80/M
Cost per 1,000 pages (lower wins)
$0.192
$0.109
Context
164k tokens
128k tokens
Open weights
yes
yes
Tool calling
yes
yes
Structured output
yes
not stated
Reads images
no
yes
Reasoning
yes
yes
Released
22 Sept 2025
8 Dec 2025
Providers selling it
18
14
Price we measure against
OpenRouter
the maker's own
Trains on your prompts (no is better)
not stated
not stated
Providers selling both · 7
NanoGPT$1.45 / $1.80
Eden AI$1.76 / $1.80
Kilo Gateway$1.81 / $1.80
Nous Portal$1.81 / $1.80
Novita$1.81 / $1.80
OpenRouter$1.81 / $1.80
TrustedRouter$1.86 / $1.90
DeepSeek V3.1 Terminus then GLM-4.6V, per million tokens
Go further
Add a third or fourth model, or switch the weighting, in the tool.
What moved in the last seven days
- DeepSeek V3.1 Terminus
Nous Portal$0.22 / $0.80 $0.27 / $125% dearer · - GLM-4.6V
Nous Portal$0.24 / $0.72 $0.30 / $0.9025% dearer ·
Frequently asked
- Which is cheaper, DeepSeek V3.1 Terminus or GLM-4.6V?
- GLM-4.6V, at $0.84 per million tokens against $1.45 for DeepSeek V3.1 Terminus, three parts input to one part output, read on 17 Sept 2026.
- Where is each one cheapest?
- DeepSeek V3.1 Terminus: $1.45 at NanoGPT. GLM-4.6V: $0.84 at ZenMux.
- Can I buy both from one provider?
- Yes. 7 providers sell both: NanoGPT, Eden AI, Kilo Gateway, Nous Portal, Novita, OpenRouter, and more. The cheapest of them for the two together is NanoGPT.
- Which holds more context?
- DeepSeek V3.1 Terminus, at 164k tokens against 128k.
Prices exclude tax and are per million tokens, read 17 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.