Choosing this model
Selection advice by Y-API. The checks below are suggested evaluations, not published test results.
Where to start
Start with the high-volume, low-ambiguity slice of a pipeline: field extraction, ticket triage, commit-message drafting, or a first pass that a larger model only reviews.
What to watch for
The window is less than half of the full 5.4 entry, which matters for whole-repository prompts. Mini tiers also tend to degrade earlier on long multi-step instructions — measure that before moving a workflow wholesale.
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
- 400,000 tokens
- Input
- File · Image · Text
- Output
- Text
- Listed on OpenRouter
- Parameters listed by OpenRouter
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsverbosity
API pricing & cost estimate
- Estimated credit consumed
- $3.05
- Estimated cash equivalent
- $0.305
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 |
|---|---|---|
| GPT-5.4 Mini | $3.05 | $0.305 |
| GPT-5.4 | $10.00 | $1.00 |
| GPT-5.6 Luna | $0.95 | $0.095 |
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
Classify each of these support messages into billing, access or bug, and give the one phrase that decided it. Return null when the message does not fit any of the three.
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": "openai/gpt-5.4-mini",
"messages": [
{
"role": "user",
"content": "Classify each of these support messages into billing, access or bug, and give the one phrase that decided it. Return null when the message does not fit any of the three."
}
],
"max_tokens": 4096
}
JSONHow to evaluate the result
Measure accuracy on a labelled sample and count the null returns separately. A model that never returns null is guessing on the ambiguous cases, and that failure is invisible in an accuracy number alone.
Before you choose
When should this be escalated to full GPT-5.4?
Set the trigger from your own results: repeated disagreement between two runs, an input near the window limit, or a task that needs several dependent steps. Do not escalate on token count alone.
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.