Skip to main content
POST
/
responses
LFM2.5-1.2B-Thinking: Responses
curl --request POST \
  --url https://api.zerogpu.ai/v1/responses \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --header 'x-project-id: <api-key>' \
  --data '
{
  "input": "What is the capital of Japan",
  "model": "LFM2.5-1.2B-Thinking"
}
'
{}

Documentation Index

Fetch the complete documentation index at: https://docs.zerogpu.ai/llms.txt

Use this file to discover all available pages before exploring further.

Liquid AI’s LFM2.5-1.2B-Thinking is a hybrid architecture reasoning model built for deep, step-by-step problem solving at the 1B scale. It generates explicit reasoning traces before producing a final answer working through math, logic, and multi-step tasks the way a human would on paper delivering thinking-model performance without the compute overhead that typically comes with it. Its hybrid SSM-attention design keeps inference fast and memory usage low, making it one of the most capable small reasoning models available for constrained environments.
References: Model docs • Terms • Privacy

​
Specifications

PropertyValue
Model IDLFM2.5-1.2B-Thinking
TaskText Generation
Typelfm2.5
Parameters1.2B
Version2.5
Max Tokens32768
ProviderLiquid AI
Input Price$0.20 / 1M
Output Price$0.40 / 1M
Total Price$0.60 / 1M

​
Try it

Send a live request with your x-api-key and x-project-id. Model is fixed to LFM2.5-1.2B-Thinking. Use request examples below to switch use cases (JSON extraction, NER, PII, and so on).

Authorizations

​
x-api-key
string
header
required
​
x-project-id
string
header
required

Body

application/json
​
input
string<textarea>
required

Multi-line text or document content to send to the model.

Required string length: 1 - 131072
​
instructions
string
​
metadata
object

Response

Success

The response is of type object.