Flan-PaLM 540B achieves state-of-the-art performance on several benchmarks, such as 75.2% on five-shot MMLU. We also publicly release Flan-T5 checkpoints, which achieve strong few-shot performance even compared to much larger models, such as PaLM 62B. Overall, instruction finetuning is a general method for improving the performance and usability of pretrained language model.

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-t5-xxl'
```

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-t5-xxl'  \
    -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

google/flan-t5-xxl

HTTP/cURL API

Input fields

`input`string

`max_length`integer

`webhook`file

Input Schema

Output Schema