replicate/flan-t5-xl

A language model by Google for tasks like classification, summarization, and more

Capabilities

Top-P

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`prompt` *	string	Prompt to send to FLAN-T5.	`—`	—
`debug`	boolean	provide debugging output in logs	`false`	—
`max_length`	integer	Maximum number of tokens to generate. A word is generally 2-3 tokens	`50`	min: 1
`repetition_penalty`	number	Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.	`1`	min: 0.01, max: 5
`temperature`	number	Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.	`0.75`	min: 0.01, max: 5
`top_p`	number	When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens	`1`	min: 0.01, max: 1

prompt required string

Prompt to send to FLAN-T5.

debug boolean

provide debugging output in logs

Default: false

max_length integer

Maximum number of tokens to generate. A word is generally 2-3 tokens

Default: 50 min: 1

repetition_penalty number

Penalty for repeated words in generated text; 1 is no penalty, values greater than 1 discourage repetition, less than 1 encourage it.

Default: 1 min: 0.01, max: 5

temperature number

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.

Default: 0.75 min: 0.01, max: 5

top_p number

When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens

Default: 1 min: 0.01, max: 1

Version: eec2f71c986d Updated: 2/26/2026 151.3K runs