LiquidAI
LFM2.5-2.6B
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.
At a glance
- Input / 1M
- $0.35
- Output / 1M
- $0.50
- Context
- 128K
- Max output
- 8K
- Intelligence
- 8.4
- Released
- Aug 2026
Pricing
LFM2.5-2.6B API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $0.35 |
|---|---|
| Output tokensPer 1M tokens | $0.50 |
| Cached input (read)Per 1M tokens | $0.04 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$0.95
per 1,000 requests
Coding task
30K in, 4K out
$12.50
per 1,000 requests
Long document summary
150K in, 2K out
$53.50
per 1,000 requests
Benchmarks
LFM2.5-2.6B benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
8.4
Coding index
7.7
Agentic index
Not available
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 128K tokens
- Max output
- 8K tokens
- Input types
- Text
- Output types
- Text
- Reasoning effort
- Not available
- Release date
- August 11, 2026
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
LFM2.5-2.6B vs other models
See how LFM2.5-2.6B stacks up head to head on price, benchmarks, and features.
VS
LFM2.5-2.6B vs gpt-oss-120b
LiquidAI vs OpenAI
See comparisonVS
LFM2.5-2.6B vs Gemini 2.5 Flash Lite
LiquidAI vs Google
See comparisonVSLFM2.5-2.6B vs Llama 4 Maverick
LiquidAI vs Meta
See comparisonVS
LFM2.5-2.6B vs Qwen3 Coder Next
LiquidAI vs Qwen
See comparisonVSLFM2.5-2.6B vs Qwen3 VL 30B A3B Instruct
LiquidAI vs Qwen
See comparisonVSLFM2.5-2.6B vs GPT-4.1 Nano
LiquidAI vs OpenAI
See comparisonAlternatives
LFM2.5-2.6B alternatives
Similar models worth considering, and where each one has the edge.
OpenAI
gpt-oss-120b
Gemini 2.5 Flash Lite
Meta
Llama 4 Maverick
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does LFM2.5-2.6B cost?
LFM2.5-2.6B costs $0.35 per 1M input tokens and $0.50 per 1M output tokens through the API. A typical chat message costs about $0.95 per 1,000 messages.
What is the context window of LFM2.5-2.6B?
LFM2.5-2.6B accepts up to 128K tokens of input and can write up to 8K tokens in a single response.
What is the best alternative to LFM2.5-2.6B?
gpt-oss-120b from OpenAI is a strong alternative. It offers: higher intelligence score, larger 131k context.
Can I use LFM2.5-2.6B alongside other models?
Yes. Shortcut Chat sends one prompt to LFM2.5-2.6B and any other models you pick at the same time, so you can compare answers side by side.
Try LFM2.5-2.6B next to every other model.
Use LFM2.5-2.6B alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.