Flan-UL2 is an encoder decoder model based on the T5 architecture. It uses the same configuration as the UL2 model released the previous year. It was fine tuned using the "Flan" prompt tuning and dataset collection. The original UL2 model was only trained with receptive field of 512, which made it non-ideal for N-shot prompting where N is large.

You can use cURL or any other http client to run inferences:

```bash
curl -X POST \
    -d '{"input": "Answer the following yes/no question by reasoning step-by-step. Can you write a whole Haiku in a single tweet?"}'  \
    -H "Authorization: bearer $(deepctl auth token)"  \
    -H 'Content-Type: application/json'  \
    'https://api.deepinfra.com/v1/inference/google/flan-ul2'
```

which will give you back something similar to:

```json
{
  "results": [
    {
      "generated_text": "Haiku is a Japanese poem that is around 108 characters long. A tweet is ..."
    }
  ],
  "request_id": null,
  "inference_status": {
    "status": "unknown",
    "runtime_ms": 0,
    "cost": 0.0,
    "tokens_generated": 0,
    "tokens_input": 0
  }
}

```


You can use our command-line tool [deepctl](/docs/getting-started) to run
inferences:

```bash
deepctl infer \
    -m 'google/flan-ul2'  \
    -i 'input=Answer the following yes/no question by reasoning step-by-step. Can you write a whole Haiku in a single tweet?'
```

which will give you back something similar to:

```json
{
  "results": [
    {
      "generated_text": "Haiku is a Japanese poem that is around 108 characters long. A tweet is ..."
    }
  ],
  "request_id": null,
  "inference_status": {
    "status": "unknown",
    "runtime_ms": 0,
    "cost": 0.0,
    "tokens_generated": 0,
    "tokens_input": 0
  }
}

```


input

max_length

The webhook to call when inference is done, by default you will get the output in the response of your inference request

webhook

Input

Max Length

Webhook

Text2TextGenerationIn

Haiku is a Japanese poem that is around 108 characters long. A tweet is ...

Generated Text

GeneratedText

estimated cost billed for the request in USD

Cost

Runtime Ms

Status

Tokens Generated

Tokens Input

Object containing the status of the inference request