Inference Logoinference shell
apps/liquid/d1-omni-600m

d1-omni-600M

Liquid AI's 587M decision model for text, images and speech. Send a state with images or an audio clip and typed questions (choice, score, yes/no); get a probability for every answer. Research release

run in browser →run via API
run with your agent
# install belt
$curl -fsSL https://cli.inference.sh | sh
# view schema & details
$belt app get liquid/d1-omni-600m
# run
$belt app run liquid/d1-omni-600m

api reference

about

liquid ai's 587m decision model for text, images and speech. send a state with images or an audio clip and typed questions (choice, score, yes/no); get a probability for every answer. research release

1. calling the api

install the client

the client provides a convenient way to interact with the api.

bash
1pip install inferencesh

setup your api key

set INFERENCE_API_KEY as an environment variable. get your key from settings → api keys.

bash
1export INFERENCE_API_KEY="inf_your_key"

run and get result

submit a request and wait for the final result. best for batch processing or when you don't need progress updates.

python
1from inferencesh import inference23client = inference()456result = client.run({7        "app": "liquid/d1-omni-600m",8        "input": {}9    })1011print(result["output"])

stream live updates

get real-time progress updates as the task runs. ideal for showing progress bars, partial results, or long-running tasks.

python
1from inferencesh import inference23client = inference()456# stream=True yields updates as they arrive7for update in client.run({8        "app": "liquid/d1-omni-600m",9        "input": {}10    }, stream=True):11    if update.get("progress"):12        print(f"progress: {update['progress']}%")13    if update.get("output"):14        print(f"output: {update['output']}")

2. authentication

the api uses api keys for authentication. see the authentication docs for detailed setup instructions.

3. files

file inputs are automatically handled by the sdk. you can pass local paths, urls, or base64 data.

automatic upload

the python sdk automatically detects local file paths and uploads them. urls are passed through as-is.

python
1# local file paths are automatically uploaded2result = client.run({3    "app": "liquid/d1-omni-600m",4    "input": {5        "image": "/path/to/local/image.png",  # detected & uploaded6        "audio": "https://example.com/audio.mp3",  # url passed through7    }8})

manual upload

you can also upload files manually and use the returned url.

python
1# upload and get a hosted URL2file = client.files.upload("/path/to/file.png")3print(file.uri)  # https://cloud.inference.sh/...

4. webhooks

get notified when a task completes by providing a webhook url. when the task reaches a terminal state (completed, failed, or cancelled), a POST request is sent to your url with the task result.

python
1result = client.run({2    "app": "liquid/d1-omni-600m",3    "input": {},4    "webhook": "https://your-server.com/webhook"5}, wait=False)

webhook payload

your endpoint receives a JSON POST with the task result:

json
1{2  "id": "task_abc123",3  "status": 9,4  "output": { ... },5  "error": "",6  "session_id": null,7  "created_at": "2024-01-15T10:30:00Z",8  "updated_at": "2024-01-15T10:30:05Z"9}
idstring— task id
statusnumber— terminal status (9=completed, 10=failed, 11=cancelled)
outputobject— task output (when completed)
errorstring— error message (when failed)
session_idstring— session id (if using sessions)
created_atstring— iso timestamp
updated_atstring— iso timestamp

5. schema

input

stateany

the text to evaluate: a string, or a json object / array of related context. every question sees the same state. may be empty when `images` or `audio` carries the content. a state over the model's limit is cut at the end and `state_truncated` is set: the state and one question share 16,384 tokens for text, 15,360 with audio, 896 with images.

default: ""example: "Seller title: wireless earbuds, barely used"
imagesarray

up to 4 images the questions are about. cannot be combined with `audio`.

audiostring(file)

one speech clip the questions are about, up to 30 seconds (wav, flac, ogg or mp3). trained on english requests to an assistant. cannot be combined with `images`.

choicesarray

choice questions: pick one option from a set.

scoresarray

score questions: place the state on ordered levels.

noulsarray

noul questions: probability that the answer is yes.

output

choicesobject

choice answers by question id.

input_tokensinteger

positions read, summed over the questions. image and audio positions are included.

modelstring*

the model that answered: `liquidai/d1-omni-600m`.

noulsobject

noul answers by question id.

scoresobject

score answers by question id.

state_truncatedboolean

true when the state did not fit and its end was cut for at least one question.

ready to run d1-omni-600M?

try in browserbrowse all tools

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.