LFM3-1.7B Official Specifications, Pricing & Benchmarks
LFM3-1.7B (lfm-3-1.7b) by Liquid AI, released 2026-11-06, featuring 262,144 context window, 8,192 max output tokens, and Text input.
📋 LFM3-1.7B Official API & System Card Specifications
Verified against official Liquid AI developer documentation & pricing
1. Identity & Capabilities
API Spec- API Model ID
- lfm-3-1.7b
- Release Date
- 2026-11-06
- Weight License
- Open-Weight (API Spec)
- Native Reasoning
- ✅ Supported
- Function Calling & JSON Schema
- ✅ 原生支持
- Batch API 异步批处理
- ✅ Supported (50% off)
2. Context, Output & Modalities
Limits- Max Context Window
- 262,000 tokens (262K)
- Max Output Tokens
- 8,192 tokens
- Input Modalities
- Text
- Output Modalities
- Text
- Direct China Access
- 🌐 Global / OpenRouter
- Deployment Mode
- Open-Weight + Cloud API
3. Official Pricing & Cache
USD / 1M- Input / 1M Tokens
- $ 0.08
- Cached Input / 1M
- $ 0.02 -75%
- Output / 1M Tokens
- $ 0.2
🎛️ Official Sampling & Reasoning Parameters
Recommended generation settings & API parameter constraints
📊 LFM3-1.7B Full Benchmark Scorecard
19 public benchmarks · ranks among 154 models · synced 2026-11-20
💻 Coding 6 items
Claw-Eval tests real-world agentic task completion across complex multi-step scenarios, evaluating a model's ability to use tools, navigate environments, and complete end-to-end tasks autonomously.
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.
SciCode is a research coding benchmark curated by scientists that challenges language models to code solutions for scientific problems.
A multilingual benchmark for issue resolving in software engineering that covers Java, TypeScript, JavaScript, Go, Rust, C, and C++.
Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal.
🤖 Agents & Tools 3 items
Berkeley Function Calling Leaderboard V4 (BFCL-V4) evaluates LLMs on their ability to accurately call functions and APIs, including simple, multiple, parallel, and nested function calls across diverse programming scenarios.
TAU3-Bench is a benchmark for evaluating general-purpose agent capabilities, testing models on multi-turn interactions with simulated user models, retrieval, and complex decision-making scenarios.
AutomationBench is a tool-use benchmark that evaluates AI agents on automating real-world workflows, testing their ability to orchestrate tools and complete multi-step automation tasks.
📐 Math 2 items
Text-only Humanity's Last Exam variant evaluated with tool use enabled.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions.
📜 Long Context 2 items
🧠 Reasoning & Science 4 items
Multi-IF benchmarks LLMs on multi-turn and multilingual instruction following. It expands upon IFEval by incorporating multi-turn sequences and translating English prompts into 7 other languages, resulting in 4,501 multilingual conversations with three turns each.
LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code.
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
AA-Omniscience Index is Artificial Analysis's knowledge-reliability metric. It rewards correct answers, penalizes hallucinations, and does not penalize abstention. Scores range from -100 to 100, where 0 means as many correct as incorrect answers.
📚 Knowledge & General 2 items
Instruction-Following Evaluation (IFEval) benchmark for large language models, focusing on verifiable instructions with 25 types of instructions and around 500 prompts containing one or more verifiable constraints.
Instruction Following Benchmark evaluating model's ability to follow complex instructions.
Source: ZeroEval / llm-stats.com (✓ = third-party verified, others vendor-reported).
Closest Self-Hostable Open-Weight Alternatives to LFM3-1.7B
Open-weight models with full HuggingFace weights for private GPU / Mac deployment
Frequently Asked Questions
Is LFM3-1.7B open-source or proprietary?
LFM3-1.7B (lfm-3-1.7b) is a proprietary commercial model by Liquid AI. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.
What are the context limit and API pricing of LFM3-1.7B?
LFM3-1.7B supports 262K input context and 8,192 max output tokens, priced at $0.08/1M input ($0.02/1M cached) and $0.2/1M output.