Nemotron 3.5 Lightning vs text-embedding-3-large.
model vs model · prices as of
Nemotron 3.5 Lightning takes 3 of 5 rounds against text-embedding-3-large. It is also the cheaper of the two to run, at $0.16 per million tokens against $0.39.
NVIDIAwins 3 roundsNemotron 3.5 Lightning
$0.16/M tokens
cheapest we can explain, at NanoGPT · $0.0306 per 1,000 pages
262k context · tool calling · open weights
OpenAItext-embedding-3-large
$0.39/M tokens
OpenAI list price, nothing below it is accounted for · $0.078 per 1,000 pages
8k context
List price in (lower wins)
$0.07/M
$0.13/M
List price out (lower wins)
$0.20/M
$0/M
Cheapest we can explain (lower wins)
$0.16/M at NanoGPT
none below list
Standard price (lower wins)
$0.41/M
$0.39/M
Cost per 1,000 pages (lower wins)
$0.0306
$0.078
Context
262k tokens
8k tokens
Open weights
yes
no
Tool calling
yes
no
Structured output
yes
not stated
Reads images
no
no
Reasoning
yes
no
Released
11 Aug 2026
25 Jan 2024
Providers selling it
12
9
Price we measure against
OpenRouter
the maker's own
Trains on your prompts (no is better)
not stated
no provider to check
Providers selling both · 2
Nous Portal$0.30 / $0.39
TrustedRouter$0.37 / $0.41
Nemotron 3.5 Lightning then text-embedding-3-large, 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
- Nemotron 3.5 LightningDarkbloom$0.07 / $0.18 $0.04 / $0.1820% cheaper ·
- Nemotron 3.5 Lightning
Kilo Gateway$0.07 / $0.18 $0.04 / $0.1820% cheaper · - Nemotron 3.5 Lightning
OpenRouterOpenRouter's list price, in and out per million tokens$0.08 / $0.20 $0.07 / $0.207% cheaper · - Nemotron 3.5 LightningNous Portal$0.07 / $0.18 $0.04 / $0.1820% cheaper ·
- Nemotron 3.5 LightningOpenRouter$0.08 / $0.20 $0.07 / $0.207% cheaper ·
- Nemotron 3.5 Lightning
Phala (RedPill)$0.08 / $0.20 $0.07 / $0.207% cheaper · - Nemotron 3.5 Lightning
CoreWeave$0.10 / $0.25 $0.07 / $0.2025% cheaper · - text-embedding-3-largeNous Portal$0.10 / $0 $0.13 / $025% dearer ·
Frequently asked
- Which is cheaper, Nemotron 3.5 Lightning or text-embedding-3-large?
- Nemotron 3.5 Lightning, at $0.16 per million tokens against $0.39 for text-embedding-3-large, three parts input to one part output, read on 19 Sept 2026.
- Where is each one cheapest?
- Nemotron 3.5 Lightning: $0.16 at NanoGPT. text-embedding-3-large: nobody goes below the maker's own price with a reason we can point at, so $0.39 is the number to beat.
- Can I buy both from one provider?
- Yes. 2 providers sell both: Nous Portal, TrustedRouter. The cheapest of them for the two together is Nous Portal.
- Which holds more context?
- Nemotron 3.5 Lightning, at 262k tokens against 8k.
Prices exclude tax and are per million tokens, read 19 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.