Liquid AI: LFM2.5 2.6B
LFM2.5 2.6B is a reasoning model from Liquid AI released on Aug 11, 2026. It reads text and writes text, with a 128K token context window and up to 33K tokens per reply.
Show moreShow less
It costs $0.10 per million input tokens and $0.20 per million output tokens. Cached input bills at $0.05, 50% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
2 providers serve it, including NanoGPT and Kilo Gateway.
- Modalities
- In / out price
- $0.10 / $0.20 per 1M
- Context
- 128K
- Max output
- 33K
- Released
- Aug 11, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
LFM2.5 2.6B pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.10 / 1M tokens | |
|---|---|---|
| Output | $0.20 / 1M tokens | |
| Cached input (read) | $0.05 / 1M tokens | 50% off input |
LFM2.5 2.6B providers
2 providers serve it, including NanoGPT and Kilo Gateway. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| NanoGPT | $0.10 | $0.20 | $0.05 | 128K | 33K |
| Kilo Gateway | n/a | n/a | – | 66K | 8K |
What LFM2.5 2.6B costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call LFM2.5 2.6B through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning
Alternatives to LFM2.5 2.6B
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 6 providers.
by metaSep 2, 2026$0.10/M input tokens$0.20/M output tokens6 providers
- 1.05M context
Reads text, images, files, audio and video. Tool calling, structured output, reasoning. Served by 6 providers.
by metaAug 5, 2026$0.10/M input tokens$0.20/M output tokens6 providers
- 1.05M context
Reads text. Tool calling, reasoning. Served by 6 providers.
by poolsideJul 21, 2026$0.10/M input tokens$0.20/M output tokens6 providers
- 262K context
Reads text. Tool calling, reasoning. Served by 4 providers.
by poolsideJul 2, 2026$0.10/M input tokens$0.20/M output tokens4 providers
- 262K context
Reads text and images. Tool calling, structured output, reasoning.
by nex-agiSep 8, 2026$0.075/M input tokens$0.25/M output tokens
- 1M context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 11 providers.
by qwenFeb 23, 2026$0.065/M input tokens$0.26/M output tokens11 providers
More from Liquid AI
- 128K context
Reads text. Tool calling, structured output, reasoning. Served by 3 providers.
by liquidOct 13, 2026$0.05/M input tokens$0.70/M output tokens3 providers
LFM2.5 2.6B questions
How much does the LFM2.5 2.6B API cost?
$0.10 per million input tokens and $0.20 per million output tokens, with cached input at $0.05. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of LFM2.5 2.6B?
128,000 tokens of input, and it can write up to 32,768 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve LFM2.5 2.6B?
2 providers serve it, including NanoGPT and Kilo Gateway. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does LFM2.5 2.6B support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is LFM2.5 2.6B open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was LFM2.5 2.6B released?
Aug 11, 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on LFM2.5 2.6B?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting