ModelPriceWatch.com
Last scan 2026-09-24 Models tracked 270 Providers 35 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

LFM2.5 8B A1B

by Together · 8.5B (A1B) parameters

Current budget open weights cheap tier
Email me when LFM2.5 8B A1B gets cheaper
Availability: This is Together's price for hosting Liquid AI's model, not a price from Liquid AI. Liquid AI does not sell its models per token at all — liquid.ai/pricing offers the open weights free under the LFM Open License below $10M annual revenue, and a commercial licence above it — so Together's serverless rate is the only per-token price that exists for this model. The 32,768-token context is what Together serves on this endpoint; the model itself is built for 128K, which this endpoint does not offer.

Today's price · per 1M tokens

Input

$0.030

per 1M tokens

Output

$0.120

per 1M tokens

Blended

$0.052

blended $/1M — 3:1 weighted input:output

Source: official Together pricing · read MODELPRICEWATCH.COM · 2026-09-24

Price receipt

We read Together's own pricing page on and found LFM2.5-8B-A1B listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is b57861c9ad.

Overview

Liquid AI's LFM2.5 8B (A1B active) on Together serverless. $0.03/$0.12 per 1M tokens. Named replacement for the retired LFM2 24B A2B.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

RunPod →
Rent GPUs by the second and serve any open-weight model yourself.
Novita AI →
Serverless open-model inference billed per token — no GPU ops.
Vast.ai →
GPU marketplace — rent spot/on-demand GPUs cheaply and serve any open-weight model.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

struck through = not supported
Input 1/4
Text ✓ Image Audio Video
Output
Text ✓
Features 2/9
Prompt caching Reasoning Coding Fast inference ✓ Long context Open weights ✓ Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Percentile vs all tracked models 26.3th1 independent measurement
Percentile per $/Mtok 526

We hold no per-benchmark accuracy scores for this model yet, so it has no accuracy average. That is a gap in our coverage, not a sign the model is untested — independent evaluators often publish a composite index for a new model long before releasing its per-benchmark numbers. The percentile above is its standing across the independent composites below.

Independent composite scores
  • AA-Omniscience Index: -33.2 (−100–100)
How it stacks up
  • Ranks #132 of 187 comparably-measured models by percentile score, across 1 independent measurement
  • Ranks #2 of 187 comparably-tested models by normalized performance per dollar top value

Source: Artificial Analysis · updated · See full rankings →

Specifications

Provider
Together
Context window
33K tokens
Modality
text
Parameters
8.5B (A1B)
Open source
Yes — open weights available
Released
Status
Current
Last updated
Tags
fastopen-weightsbudget

Availability verified: — listed on Together's own page

Try on Together Official pricing page