Laguna S 2.1 vs LFM3-1.7B
Prices checked
Laguna S 2.1 and LFM3-1.7B split the 5 rounds this table counts: the maker's two prices, the cheapest price, the maker's blended price and context. The weighting you pick decides the rest.
PoolsideLaguna S 2.1
1M context · tool calling · open weights
$0.11/M tokensVultr Serverless Inference's own price · 6.5¢ per 1,000 pages
LFM3-1.7B
262k context · tool calling · open weights
$0.11/M tokensLiquid AI's own price · 6¢ per 1,000 pages
Maker's price in (lower wins)
$0.09/M
$0.08/M
Maker's price out (lower wins)
$0.18/M
$0.20/M
Cheapest price (lower wins)
none below the maker
none below the maker
Maker's price, blended (lower wins)
$0.11/M
$0.11/M
Cost per 1,000 pages (lower wins)
6.5¢
6¢
Context
1M tokens
262k tokens
Open weights
yes
yes
Tool calling
yes
yes
Structured output
no
yes
Reads images
no
no
Reasoning
yes
yes
Released
21 Jul 2026
6 Nov 2026
Providers selling it
4
6
Price we measure against
Vultr Serverless Inference
the maker's own
Trains on your prompts (no is better)
no provider to check
no provider to check
Providers selling both · 0
No provider we read sells both, so running the two means two accounts.
Go further
Add a third or fourth model, or change the weighting, in the tool.
Frequently asked
- Which is cheaper, Laguna S 2.1 or LFM3-1.7B?
- LFM3-1.7B, at $0.11 per million tokens against $0.11 for Laguna S 2.1, blended 3 in : 1 out, read on 7 Nov 2026.
- Where is each one cheapest?
- Laguna S 2.1: nobody sells it below Vultr Serverless Inference's own price with a stated reason, so $0.11 is the number to beat. LFM3-1.7B: nobody sells it below the maker's own price with a stated reason, so $0.11 is the number to beat.
- Can I buy both from one provider?
- No provider we read sells both, so running the two means two accounts and two bills.
- Which holds more context?
- Laguna S 2.1, at 1M tokens against 262k.
Prices exclude tax, read 7 Nov 2026 from each provider's own catalog. They are per M tokens, blended 3 in : 1 out, and a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.
Related comparisons