Choosing this model
Selection advice by Y-API. The checks below are suggested evaluations, not published test results.
Where to start
Consider it for agent fan-out, where several instances run the same kind of step in parallel, or for coding assistance that has to read a whole repository context in one request.
What to watch for
Google deprecated this model on 2026-10-08: requests to it are automatically routed to 3.6 Flash, and its price has been withdrawn from the rate card. The wide modality list describes the model, not what the gateway will forward, and what answers a call is no longer this model — each media type needs its own check. Flash-tier naming is also not a latency measurement.
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
- $8.00
- Estimated cash equivalent
- $0.80
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 3.5 Flash | $8.00 | $0.80 |
| Gemini 3.7 Flash | $5.25 | $0.525 |
| Gemini 3.1 Pro Preview | $9.50 | $0.95 |
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
Split this feature request into independent workstreams that could be implemented in parallel, and name the shared files that would create conflicts.
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-3.5-flash",
"messages": [
{
"role": "user",
"content": "Split this feature request into independent workstreams that could be implemented in parallel, and name the shared files that would create conflicts."
}
],
"max_tokens": 4096
}
JSONHow to evaluate the result
The split should be genuinely independent — check whether any two workstreams touch the same file. Then run the streams in parallel and see how many merge conflicts actually appear.
Before you choose
Should I use 3.5 Flash or the newer 3.7 and 3.8 Flash?
Reach for 3.8 Flash. Google deprecated 3.5 Flash on 2026-10-08 and now routes its requests to 3.6 Flash, so the model string no longer selects what runs — only keep it if you have results pinned to that generation and are testing the routing.
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.