Liquid AIOpen weights: LiquidAI/LFM2.5-24B-A2BNewFirst seen 8 Nov 2026 on one source; awaiting a secondCompare with another modelLFM2.5-24B-A2B
No cheaper ranked model scores higher: it is on the price frontier.
As of 9 Nov 2026, LFM2.5-24B-A2B by Liquid AI is not yet ranked on the BenchLeader Index, which needs at least five independent results across two categories. API pricing: $0.050 per 1M input tokens and $0.700 per 1M output tokens ($0.213 blended at 3:1), list price on 9 Nov 2026. It streams about 390 tokens/s (OpenRouter).
Key facts (as of 9 Nov 2026)
- LFM2.5-24B-A2B API pricing: $0.050 per 1M input tokens and $0.700 per 1M output tokens ($0.213 blended at 3:1) (list price, 9 Nov 2026).
- LFM2.5-24B-A2B streams about 390 tokens/s (OpenRouter, 9 Nov 2026).
In detail. LFM2.5-24B-A2B is a Liquid AI open-weights model. It is not yet ranked: no independent benchmark results so far, only pricing and metadata. At $0.213 per million tokens blended it is among the cheapest fifth of ranked models. Output speed of 385 tokens per second puts it in the fastest quarter, with a first token in 0.2 s.
- Blended price
- $0.213/M
- $0.050 in · $0.700 out
- via OpenRouter
- Output speed
- 385 tok/s
- OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
- First answer
- 0.22 s
- Context
- 128k
- via OpenRouter
- Full answer
- –
- Cost per task
- –
- Tokens per task
- –
- Released
- –
- date not published by our sources
No independent quality benchmark results yet — only pricing and metadata.
API pricing: where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Liquid | 508 tok/s | 0.14 s | $0.050 | $0.700 | 128k | fp8 |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0002 | – | 1.0 s |
| Summarize a 30-page report | 12,000 / 600 | $0.0010 | – | 1.8 s |
| Code edit | 6,000 / 1,500 | $0.0014 | – | 4.1 s |
| Agentic coding session | 60,000 / 4,000 | $0.0058 | – | 10.6 s |
| Structured extraction | 2,000 / 200 | $0.0002 | – | 0.7 s |
See also
Questions people ask
- Why does LFM2.5-24B-A2B have no BenchLeader Index score?
- The index needs at least five independent results across at least two categories, and as of 9 Nov 2026 LFM2.5-24B-A2B does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
- How much does LFM2.5-24B-A2B cost per 1M tokens?
- As of 9 Nov 2026, LFM2.5-24B-A2B costs $0.050 per 1M input tokens and $0.700 per 1M output tokens, $0.213 blended (three input tokens per output token).
Data as of 9 Nov 2026. Compare with another model.
Cite as: BenchLeader, “LFM2.5-24B-A2B: benchmarks, pricing, speed and rank”, data as of 9 Nov 2026, https://www.benchleader.com/models/lfm2-5-24b-a2b.