TackleKey
Model reference
scaledown/summarize on TackleKey
Check this model ID and provider context, then confirm its current price and availability in the live marketplace before a larger test.
Model details
OpenAI-compatible request
Use the exact public model identifier scaledown/summarize. Keep the API key in a server-side environment variable and start with a small response limit.
curl https://api.tacklekey.com/v1/chat/completions \
-H "Authorization: Bearer $TACKLEKEY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "scaledown/summarize",
"messages": [
{
"role": "user",
"content": "Reply with a one-sentence API health check."
}
],
"max_tokens": 64
}'How to use it
TackleKey is OpenAI-compatible for common chat completion workflows. Replace the base URL with the TackleKey endpoint, use an API key, and verify the scaledown/summarize availability, endpoint support, request log, and balance record before scaling traffic.
This page is generated from a public model catalog snapshot. Live price, permissions, and route availability can change; check the model marketplace and a small request before scaling.
Related Unknown models
relace/relace-search
amazon/nova-2-lite-v1
google/gemma-3-27b-it
inference-net/schematron-v2-small
mancer/weaver
perplexity/sonar-pro
FAQ
What model ID should I send for scaledown/summarize?
Use scaledown/summarize exactly as shown in the current TackleKey pricing catalog, then confirm it is still available before a larger run.
Where can I find the scaledown/summarize price?
Open the live model marketplace. Static pages do not reproduce token, fixed, or expression-based billing rules.
Is scaledown/summarize the cheapest or best model?
This page does not make that claim. Compare live Unknown and cross-provider prices, endpoint support, request success, and output quality for your workload.
Try TackleKey with one OpenAI-compatible change
Create an account, generate an API key, then replace your client base URL with the TackleKey endpoint. Keep keys server-side and verify live pricing before scaling traffic.