Choosing this model
Selection advice by Y-API. The checks below are suggested evaluations, not published test results.
Where to start
Start with extraction, classification and short summarisation over mixed input — a PDF page, a screenshot, a short clip — where the answer is checkable against the source.
What to watch for
A Lite tier is a cost and latency choice, not a capability guarantee. Media input appearing in the specification does not prove the gateway forwards that media format; verify each one with a small request before building on it.
Model specifications
These are OpenRouter model-level specifications, not a Y-API compatibility test. A particular route may accept fewer input formats, parameters or tokens. Verify the features you need with a small request; a successful text response does not validate vision or tool calling.
- Context window
- 1,048,576 tokens
- Input
- Text · Image · Video · File · Audio
- Output
- Text
- Listed on OpenRouter
- Parameters listed by OpenRouter
include_reasoningmax_tokensreasoningreasoning_effortresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p
API pricing & cost estimate
- Estimated credit consumed
- $1.00
- Estimated cash equivalent
- $0.10
Illustrative token budget, not measured usage or a quote. Includes input and output; excludes separate media charges, cache discounts and retries. Include billed reasoning tokens in your output budget where applicable. Actual billing follows usage returned by the service.
$1 paid adds $10 of credit. Cash equivalent = credit consumed ÷ 10; this is not the model publisher’s list price.
| Model | Estimated credit consumed | Estimated cash equivalent |
|---|---|---|
| Gemini 3.1 Flash Lite | $1.00 | $0.10 |
| Gemini 3.8 Flash | $5.25 | $0.525 |
| GPT-6 Luna | $0.35 | $0.035 |
API integration examples
These minimal, text-only requests use the exact Y-API model ID. They do not demonstrate image, audio, video, file or tool support. The output limit also needs room for reasoning; an empty answer with finish_reason=length can mean the budget was exhausted.
A task to try
From this delivery note, extract the supplier, the amount and the due date. Return null for anything the note does not state, and do not infer a date from context.
Set the TOKEN environment variable to a key from your console. Run this on your server or locally; never expose a key in browser code or a public repository.
curl --fail-with-body --silent --show-error --max-time 120 \
'https://api.y-api.bestvirtualgoods.com/v1/chat/completions' \
-H "Authorization: Bearer ${TOKEN:?Set TOKEN first}" \
-H 'Content-Type: application/json' \
--data-binary @- <<'JSON'
{
"model": "google/gemini-3.1-flash-lite",
"messages": [
{
"role": "user",
"content": "From this delivery note, extract the supplier, the amount and the due date. Return null for anything the note does not state, and do not infer a date from context."
}
],
"max_tokens": 4096
}
JSONHow to evaluate the result
Score field accuracy separately from invented values. A run that fills a plausible date where the note was silent is worse than one that returns null, even though it looks more useful.
Before you choose
Can Flash Lite replace a larger Gemini entry?
Only where your own evaluation says so. Run the same task set through both and compare accepted outputs and retries; a cheaper call that needs a second attempt is not cheaper.
Sources & scope
Technical facts come from the cited model page and, where available, its linked publisher card. A card describes that checkpoint; it is not proof of the weights a gateway serves. Prices come only from the Y-API catalog. We do not claim measured latency, uptime or benchmark scores for this endpoint.