doctl serverless-inference async-invoke create
Generated on 3 Jun 2026
from doctl version
v1.160.1
Usage
doctl serverless-inference async-invoke create [flags]Description
Starts an asynchronous job for a fal model and returns a request ID.
Use –model with: –prompt for image generation (e.g. fal-ai/flux/schnell) or audio generation (e.g. fal-ai/stable-audio-25/text-to-audio) –text for text-to-speech models (e.g. fal-ai/elevenlabs/tts/multilingual-v2)
Use –request to send a full JSON body for any model. Poll the result with the get subcommand once you have a request ID.
For full API reference see: https://docs.digitalocean.com/reference/api/reference/serverless-inference/#inference_create_async_invoke
Example
doctl inference async-invoke create --model fal-ai/flux/schnell --prompt "A futuristic city at sunset"Flags
| Option | Description |
|---|---|
--help, -h |
Help for this command |
--model, -m |
fal model ID (required unless –request is set) |
--prompt |
Text prompt for image generation (e.g. fal-ai/flux/schnell) or audio generation (e.g. fal-ai/stable-audio-25/text-to-audio) models |
--request |
Path to a full JSON request body. Use “-” for stdin. |
--seconds-total |
Desired audio duration in seconds, used with audio generation models (e.g. fal-ai/stable-audio-25/text-to-audio) Default: 0 |
--tag |
Tag in key=value form (repeatable, e.g. –tag env=prod) |
--text |
Text to convert to speech, used for text-to-speech models (e.g. fal-ai/elevenlabs/tts/multilingual-v2) |
Related Commands
| Command | Description |
|---|---|
| doctl serverless-inference async-invoke | Display commands for managing async model invocations |
Global Flags
| Option | Description |
|---|---|
--access-token, -t |
API V2 access token |
--api-url, -u |
Override default API endpoint |
--config, -c |
Specify a custom config file Default: |
--context |
Specify a custom authentication context name |
--http-retry-max |
Set maximum number of retries for requests that fail with a 429 or 500-level error
Default: 5 |
--http-retry-wait-max |
Set the minimum number of seconds to wait before retrying a failed request
Default: 30 |
--http-retry-wait-min |
Set the maximum number of seconds to wait before retrying a failed request
Default: 1 |
--interactive |
Enable interactive behavior. Defaults to true if the terminal supports it (default false)
Default: false |
--output, -o |
Desired output format [text|json] Default: text |
--trace |
Show a log of network activity while performing a command Default: false |
--verbose, -v |
Enable verbose output Default: false |