Summary
- Not scored: 80 of 80 questions failed on the host's side during testing, too many for a fair score. Speed, latency and price below are measured.
LiquidAIOpen weightsReleased 11 Aug 2026
liquid/lfm-2.5-2.6bPeer group: 31 models with a blended list price $0.15 to $1 per 1M tokens (3 input : 1 output). Charts below compare LFM2.5-2.6B with all models; cost and speed charts focus on this peer group.
Verification score: the share of 80 questions from open datasets answered correctly. See the benchmark datasets.
LFM2.5-2.6B circled; dashed line joins models no cheaper model beats
LFM2.5-2.6B circled · accurate and quick sits top left
LFM2.5-2.6B circled · output tokens, reasoning included
All models tested on the current suite
Average cost of one question, split into input, reasoning and answer tokens at each model's list price. Reasoning tokens are billed as output.
Peer group: blended price $0.15 to $1
All models · lower is better
Median of 3 streamed runs of the same prompt, measured 26 Oct 2026.
Peer group ($0.15 to $1) · higher is better
Peer group ($0.15 to $1) · lower is better
Peer group ($0.15 to $1) · lower is better
LFM2.5-2.6B circled · quick to start and fast sits top left
Questions answered correctly in each category
Not scored: 80 of 80 questions failed on the host's side.
Every host serving this model through OpenRouter, from OpenRouter's catalogue
| Host | Input / 1M | Output / 1M | Context | Max output | Quantization |
|---|---|---|---|---|---|
| Liquid | $0.35 | $0.5 | 128k | 8k | fp8 |
Scores, speed and billed cost are our own measurements. Prices, context window and hosts come from OpenRouter's catalogue on the test date.