Claude Sonnet 5 vs LFM2.5-2.6B (free)
Side-by-side API pricing and Artificial Analysis performance for Claude Sonnet 5 (Anthropic) and LFM2.5-2.6B (free) (Liquid AI). Green cells mark the better value in each row.
Prices updated Aug 12, 2026, 10:56 AM UTC · refreshed hourly
| Claude Sonnet 5 Anthropic | LFM2.5-2.6B (free) Liquid AI | |
|---|---|---|
| Pricing | ||
| Input $/1M | $2.00 | Free |
| Output $/1M | $10.00 | Free |
| Blended $/1M (3:1) | $4.00 | Free |
| RAG example (30K in / 2K out) | $0.08 | $0 |
| Quality & speed | ||
| Intelligence Index | 55.3 | — |
| Coding Index | 71.5 | — |
| Agentic Index | 49.7 | — |
| Output speed (tok/s) | 90 | — |
| Time to first token | 141.73s | — |
| Specs | ||
| Context window | 1M | 128K |
| Input modalities | text, image, file | text |
FAQ
Which is cheaper, Claude Sonnet 5 or LFM2.5-2.6B (free)?
LFM2.5-2.6B (free) has the lower blended API price at Free per 1M tokens (3:1 input:output mix), versus $4.00 for the other model. Prices are live from OpenRouter and refresh about hourly.
Which is better for RAG workloads?
For a typical RAG request (30K input / 2K output tokens), LFM2.5-2.6B (free) costs about $0 per request versus $0.08. Also compare context windows: Claude Sonnet 5 offers 1M and LFM2.5-2.6B (free) offers 128K.
Which scores higher on Artificial Analysis benchmarks?
Claude Sonnet 5 leads on the Artificial Analysis Intelligence Index (55.3 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.