Latenode LogoLatenode
AI Nodes

AI: Text Generation

AI: Text Generation is for open language models: Llama, Mixtral, Gemma, MythoMax, WizardLM, and more. Use it for chat, code, and creative text without your own provider API key.

Plug and Play (PnP) billing

This is a PnP (Plug and Play) node: Latenode meters usage and charges PnP tokens on top of execution credits (1 PnP token = $1). This node has custom pricing: check the node settings for the current rate.

Shared fields

Most models use the same field set. Fill in User Prompt or Dialogue History (at least one).

FieldDescription
User PromptCurrent request
Dialogue HistoryJSON array of messages [{ "role", "content" }]. Roles: user, assistant, tool (alternate)
Temperature0-2. Higher is more random. Default: 0.7. Usually change either Temperature or Top P
Max TokensToken limit for the answer. Often defaults to 512; Llama 3.3: 4096
Chat Completion ChoicesHow many completion variants to generate (not on every model)
StopUp to 16 stop sequences
Presence Penalty−2.0 to 2.0. Positive values encourage new topics. Default: 0
Frequency Penalty−2.0 to 2.0. Positive values reduce repetition. Default: 0
Top P0-1, nucleus sampling. Default: 0.9
Top KHow many top tokens to sample from; 0 disables. Range depends on the model
Response FormatText or JSON Object (Llama 3.3 also has Parsed JSON Object)
Repetition Penalty1 means no penalty; above 1 reduces repeats. Usually 0.01-2 or 0.01-5

Models

Need Help? Ask the community

If something on this page is missing or unclear, post on the Latenode community forum. Our team and other users usually reply quickly.

0/100
0/2000

On this page