LiquidAI models on Tokenator

Every LiquidAI model available through Tokenator: API ID, context window, usage multiplier and current availability. The key and the base URL stay the same for every model in the catalog β€” switching models takes one request parameter.

LiquidAIonline
D1
liquid-d1
Γ—1.2

D1 is Liquid AI's structured decision model, served as a System One endpoint. Send a state along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a probability taken directly from the model rather than written out as text.

DecisionsContext 65.5K tokens
LiquidAIonline
D1 Ultra
liquid-d1-ultra
Γ—1.4

D1-ultra is Liquid AI's largest decision model, served as a System One endpoint. Send a state of text and images along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a probability taken directly from the model rather than written out as text.

DecisionsContext 32.8K tokens
LiquidAIonline
D1.1
liquid-d1.1
Γ—1.2

d1.1 is Liquid AI's structured decision model, served as a System One endpoint and the successor to d1. Send a state along with typed questions, and it returns a choice, a score, or a yes/no answer, each with a probability taken directly from the model rather than written out as text.

DecisionsContext 65.5K tokens
LiquidAIonline
D1.2
liquid-d1.2
Γ—1.2
NEW

d1.2 is Liquid AI's fast, cost-efficient omnimodal decision model. Built for classification, routing, information extraction, object detection, and automated decision-making at scale.

DecisionsContext 65.5K tokens
LiquidAIonline
D1.2 Ultra
liquid-d1.2-ultra
Γ—1.4
NEW

d1.2-ultra is Liquid AI's most capable omnimodal decision model. Designed for complex classification, multimodal understanding, information extraction, and high-stakes automated decision-making.

DecisionsContext 65.5K tokens
LiquidAIonline
LFM3-1.7B
lfm-3-1.7b
Γ—1.1

A compact 1.7B-parameter text model with a 256K-token context, post-trained for agents, tool calling, and structured outputs. It reasons before it answers. Prompts and outputs may be retained and used to train Liquid models.

Context 262.1K tokens

6 LiquidAI models in the catalog, 6 available right now, context up to 262.1K tokens, multiplier Γ—1.1–×1.4