LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
li

LFM3-1.7B

liquid·liquid/lfm-3-1.7b·GA·Open weights·liquid series·NEW
Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·OpenRouterGateway
$0.08 / $0.20
Blended $0.11 · 1.3× spread
Context
262,144
Output limit
8,192
Knowledge cutoff
—
Released / updated
2026-11-06 / 2026-11-07
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text

LFM3-1.7B by liquid is offered by 3 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is OpenRouter at $0.08 / $0.20 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 1.3× across the providers that host it.

Artificial Analysis rates it 6 on the Intelligence Index, with 16.8 for Finance & Accounting, its strongest domain. Against its lowest blended price of $0.11 per 1M, that is roughly 55 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 146 tokens per second, with 0.47s to the first token. Running one task of the Artificial Analysis suite costs about $0.1732, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 262,144 tokens, with an output limit of 8,192 tokens. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence6
Value55
Engineering16.3
Finance & Accounting16.8
Legal16.1
Strategy & Ops8.7
Economics16
Output speed146 tok/s
TTFT0.47 s
Cost per task$0.17
Value formulaIQ 6 ÷ min blended $0.110 = 55

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 3 providers3 with public prices

  • ProviderInput / Output
  • OpenRouterGateway
    $0.08 / $0.20
    Cache read $0.02Context 262,144Output limit 8,192
  • Kilo GatewayGateway
    $0.08 / $0.20
    Cache read $0.02Context 262,144Output limit 8,192
  • NanoGPTGateway
    $0.10 / $0.25
    Cache read $0.025Context 262,144Output limit 8,192
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
OpenRouterGateway$0.08$0.20$0.02—262,1448,192
Kilo GatewayGateway$0.08$0.20$0.02—262,1448,192
NanoGPTGateway$0.10$0.25$0.025—262,1448,192

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = high

2 / 3 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1OpenRouter$18.80
2Kilo Gateway$18.80
3NanoGPT$23.50
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.11

Price history accumulates from each data sync; currently only 1 sample(s) (2026-11-07). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

lid1.2same series—lid1.2-ultrasame series—liLFM3-1.7B (free)same series—liLFM2.5-24B-A2Bsame lab—liLFM2.5 2.6Bsame lab—
Data partly from models.dev (MIT)