LFM2.5-2.6B (free) Open vs INMercury 2 Paid
LFM2.5-2.6B (free) vs Mercury 2 compared — price per token, context window, multimodality, openness and which to choose. Can the open-source model replace the paid one? Full 2026 breakdown.
Prices & specs refreshed from live data · olud.ai
Open-model prices = cheapest provider via OpenRouter; official maker rates may be higher.
Free /M outputNo per-token fees if you self-host
$0.75 /M outputManaged API (no infra to run)
LFM2.5-2.6B (free) vs Mercury 2 specs
| Spec | LFM2.5-2.6B (free) | Mercury 2 | Winner |
|---|---|---|---|
| Maker | Liquid | Inception | – |
| Type | Open-weight | Proprietary | |
| Context window | 66K tokens | 128K tokens | INMercury 2 |
| Input price | Free/M · free self-host | $0.25/M | |
| Output price | Free/M · free self-host | $0.75/M | |
| Vision / multimodal | No | No | – |
| Tool / function calling | Yes | Yes | = Tie |
| Self-hostable | Yes | No (API only) | |
| License | Open weights | Proprietary |
Price gap & when to choose each
- You want to self-host or run on your cloud
- You prioritize data privacy & control
- You want the lowest operating costs
- You are building open or reproducible AI
- You want frontier performance through a managed API
- You need the longer 128K context window
- You value reliability & ecosystem
- You don't want to manage infrastructure
Feature comparison
| Capability | LFM2.5-2.6B (free) | Mercury 2 |
|---|---|---|
| Open weights (downloadable) | ✓ | ✗ |
| Self-hostable | ✓ | ✗ |
| Runs fully offline | ✓ | ✗ |
| Vision / multimodal | ✗ | ✗ |
| Tool / function calling | ✓ | ✓ |
| 1M+ context window | ✗ | ✗ |
Benchmarks: LFM2.5-2.6B (free) vs Mercury 2
Independent benchmark scores measured by Artificial Analysis. Higher is better (except latency).
Benchmark data by Artificial Analysis.
How LFM2.5-2.6B (free) and Mercury 2 score
| Criterion | LFM2.5-2.6B (free) | Mercury 2 |
|---|---|---|
| Cost-efficiency | 5.0 | 5.0 |
| Context window | 3.0 | 3.5 |
| Openness | 5.0 | 1.5 |
| Self-hosting | 5.0 | 1.0 |
| Multimodality | 3.5 | 3.5 |
Scores come from live data — output price (cost), context length, open vs closed weights (openness & self-hosting) and vision/tool support (multimodality). Raw task quality isn't scored here; it depends on your benchmark — see the verdict.
What each model is
LFM2.5-2.6B (free) Open
LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...
Mercury 2 Paid
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
Frequently asked questions
Is LFM2.5-2.6B (free) as good as Mercury 2?
LFM2.5-2.6B (free) is open-weight and competitive on many tasks, but Mercury 2 may still lead on the hardest reasoning and agentic work. The gap keeps narrowing — benchmark both on your actual use case before deciding.
Can I run LFM2.5-2.6B (free) locally?
Yes. LFM2.5-2.6B (free) has open weights, so you can self-host it on your own GPUs or run it via a low-cost API. Mercury 2 is API-only and cannot be self-hosted.
LFM2.5-2.6B (free) vs Mercury 2 — which should I pick in 2026?
Choose LFM2.5-2.6B (free) if you want to self-host, keep your data private and skip per-token fees — it's open-weight and runs on your own hardware. Choose Mercury 2 if you want frontier capability through a managed API with zero infrastructure to run.
People also compare
Explore more open-source AI
Browse the full open-source model leaderboard, thousands of tools and live benchmarks — all in one place.
Open the leaderboard →