falImage to textComing soon
falfal-ai/moondream/batched
fal-ai/moondream/batched is an image to text tool from fal that runs in the background and returns text. Coming soon: listed with its price, not yet open to runs.
This tool is listed but not yet available to run.
Price pendingPricing
Price pending.
Limits
- Runs
- In the background
- Returns
- text
- Longest queue wait
- 3600s
- Run deadline
- 1800s
- Largest inline input
- 1024 KB
- Largest input file
- 500 MB
- Largest output
- 4768 MB
- Outputs per run
- 16
Input
| Field | Kind | Default | Description |
|---|---|---|---|
model_id | one of vikhyatk/moondream2, fal-ai/moondream2-docci | vikhyatk/moondream2 | Model ID to use for inference |
inputs required | JSON | — | List of input prompts and image URLs |
max_tokens | number (whole) 32 to 1024 | 64 | Maximum number of new tokens to generate |
temperature | number … to 1 | 0.2 | Temperature for sampling |
top_p | number 0 to 1 | 1 | Top P for sampling |
repetition_penalty | number 1 to 2 | 1 | Repetition penalty for sampling |
Same request in code
curl https://api.spiral.ai/v1/runs \
-H "Authorization: Bearer $SPIRAL_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"provider": "fal",
"model": "fal-ai/moondream/batched",
"input": {
"inputs": {}
}
}'