Choosing this model
Selection advice by Y-API. The checks below are suggested evaluations, not published test results.
Where to start
Consider it for a controlled pilot of multi-step engineering tasks. Keep a known baseline, save the complete tool trace and score the final artifact against requirements that were written before the run.
What to watch for
The preview designation matters for rollout planning. Do not interpret catalog availability as a stable behavior contract; keep a fallback, regression set and a way to halt a run that stops making progress.
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
- Output
- Text
- Listed on OpenRouter
- Parameters listed by OpenRouter
frequency_penaltyinclude_reasoninglogit_biasmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Estimate your cost
- Estimated credit consumed
- $2.50
- Estimated cash equivalent
- $0.25
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.
Use the API
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
Plan a resumable import of one million rows. Include checkpoints, duplicate handling, progress reporting and recovery after a worker crash.
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": "tencent/hy4-preview",
"messages": [
{
"role": "user",
"content": "Plan a resumable import of one million rows. Include checkpoints, duplicate handling, progress reporting and recovery after a worker crash."
}
],
"max_tokens": 4096
}
JSONHow to evaluate the result
Check for durable checkpoints and idempotent writes. Replay a batch after a simulated crash; a convincing plan is not enough if duplicate records appear.
Before you choose
Should Hy4 preview immediately replace Hy3?
Not without a controlled comparison. A larger model and context do not guarantee a better result for your workload. Pilot it behind a switch and retain the tested Hy3 path until the evidence supports migration.
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.