API ManyНовые модели: Qwen 3.8 Max, Claude Haiku 5.5, Claude Opus 5.5, Claude Sonnet 5.5
Liquid AILLMComparison

LFM3-1.7B vs LFM2.5-2.6B: smaller, longer context, stronger on agents

LFM3-1.7B has 35% fewer parameters than LFM2.5-2.6B, twice the context (256K vs 128K) and averages 49.4 vs 31.6 on Liquid AI’s benchmark suite. Specs, scores and API prices compared.

30 окт. 2026 г. · API Many

LFM2.5-2.6B was Liquid AI’s strongest small text model before LFM3. Liquid says the new LFM3-1.7B outperforms it while using 35% fewer parameters, thanks to a new tri-hybrid architecture and training recipe.

Source:Liquid AI: Introducing LFM3 (Oct 27, 2026)

Specs and prices

LFM3-1.7BLFM2.5-2.6B
Parameters1.73B2.69B
Layers24: 13 gated short convolutions, 5 sliding-window attention, 6 global attention30: 22 double-gated short convolutions, 8 grouped-query attention
Pre-training tokens22T34T
Context window256K tokens131,072 tokens
Vocabulary128K128K
LanguagesSame 16 languagesSame 16 languages
LicenseLFM Open License v1.0LFM Open License v1.0
API input / output per 1M tokens$0.08 / $0.20 (Liquid API)$0.35 / $0.50 (OpenRouter, Liquid provider)
Cached input per 1M tokens$0.02$0.04
On API ManyNoNo
OpenRouter serves LFM2.5-2.6B in FP8 with a 128K context and up to 8,192 output tokens, and also lists a free variant with a 65,536-token context. As of October 30, 2026 OpenRouter does not list LFM3-1.7B.

Sources:Hugging Face: LiquidAI/LFM3-1.7B model card · Hugging Face: LiquidAI/LFM2.5-2.6B model card · Liquid AI: Pricing · OpenRouter: LiquidAI LFM2.5-2.6B

Benchmarks

Benchmark (Liquid AI’s evaluation)LFM3-1.7BLFM2.5-2.6B
LiveClaw (agents)45.6014.70
Claw-Eval General (EN), average68.6462.63
WebArena-Verified38.423.02
AutomationBench (public)41.290.94
BFCL V4 (function calling)71.3955.89
ToolSandbox80.3678.04
SWE-bench Verified (OpenCode)43.4018.00
Terminal-Bench 2.1 (OpenCode)12.920.00
LiveCodeBench v673.4660.57
IFEval96.6695.39
IFBench73.0360.48
GPQA Diamond63.3757.78
AA-Omniscience accuracy (public)7.078.75
AA-Omniscience non-hallucination (public)92.9353.69
AA-LCR (long context)52.836.00
RULER 128K65.561.15
Average of all 29 scores49.3731.55
Numbers are from Liquid AI’s LFM3-1.7B model card; both models were run by Liquid with vLLM in BF16 at full context. LFM2.5-2.6B answers slightly more AA-Omniscience questions correctly, but LFM3-1.7B hallucinates far less.

Source:Hugging Face: LiquidAI/LFM3-1.7B model card

What changed

  • Architecture: LFM3 keeps short convolutions for over half the layers but adds sliding-window attention next to global attention, uses head-wise gated attention and partial RoPE, and widens the convolution kernel from 3 to 7.
  • Long context: the context window doubles to 256K, and the long-context scores move from near zero (RULER 128K 1.15) to usable (65.56).
  • Agents: the largest gains are in browser and business-app agents (WebArena-Verified, AutomationBench) and agentic coding, after a new agentic RL stage run inside real agent harnesses.
  • Size: 35% fewer parameters; Liquid says the 4-bit text model fits in about 1 GB.

Sources:Liquid AI: Introducing LFM3 (Oct 27, 2026) · Hugging Face: LiquidAI/LFM3-1.7B model card

Which one should you use?

  • New projects: LFM3-1.7B scores higher on almost every benchmark Liquid published, is smaller, and is cheaper on Liquid’s API than LFM2.5-2.6B is on OpenRouter.
  • If you already call LFM2.5-2.6B through OpenRouter: LFM3-1.7B is not on OpenRouter yet, so switching today means Liquid’s own API or self-hosting.
  • If you have LFM2.5 fine-tunes: LFM3 is a new architecture, so adapters do not carry over; plan a new fine-tuning run on the LFM3-1.7B base.
  • Both models: Liquid does not recommend them for complex multi-step reasoning or knowledge-heavy work without retrieval.

Sources:Hugging Face: LiquidAI/LFM3-1.7B model card · Hugging Face: LiquidAI/LFM2.5-2.6B model card · OpenRouter: Liquid models

Need a small hosted model on API Many today? GPT-6 Luna starts at $0.10 вход · $0.50 выход and Gemini 3.5 Flash Lite at $0.30 вход · $2.499 выход, both through one OpenAI-compatible endpoint.

Related

FAQ

Is LFM3-1.7B better than LFM2.5-2.6B?

On Liquid AI’s published benchmarks, yes: it averages 49.37 versus 31.55 across 29 scores and leads on agents, tool use, coding, instruction following and long context, despite having 35% fewer parameters.

Which has the longer context window?

LFM3-1.7B: 256K tokens versus 131,072 for LFM2.5-2.6B.

Which is cheaper to call?

LFM3-1.7B costs $0.08 / $0.20 per 1M input / output tokens on Liquid’s API. LFM2.5-2.6B costs $0.35 / $0.50 on OpenRouter, which also lists a free variant with a 65,536-token context.

Can I use either model on API Many?

Not currently. Neither LFM3-1.7B nor LFM2.5-2.6B is offered on API Many.

Sources

  1. Hugging Face: LiquidAI/LFM3-1.7B model card — LFM3-1.7B specs and the benchmark table with LFM2.5-2.6B.
  2. Liquid AI: Introducing LFM3 (Oct 27, 2026) — Architecture changes, the 35% parameter claim and training stages.
  3. Hugging Face: LiquidAI/LFM2.5-2.6B model card — LFM2.5-2.6B specs.
  4. Liquid AI: Pricing — LFM3-1.7B API price.
  5. OpenRouter: LiquidAI LFM2.5-2.6B — LFM2.5-2.6B price, context and output limit on OpenRouter.
  6. OpenRouter: Liquid models — Liquid models listed on OpenRouter (no LFM3 as of Oct 30, 2026).
Попробуйте с одним API-ключом

Все модели из статьи доступны в API Many. Оплата по факту от $10.

Смотреть модели →

Ещё в блоге