Choosing this model
Selection advice by Y-API. The checks below are suggested evaluations, not published test results.
Where to start
Start with bounded tasks such as intent classification and extracting a small set of fields. Route ambiguous or high-impact cases to review instead of making a cheap model responsible for every decision.
What to watch for
Model positioning is not a Y-API latency measurement. Structured-output support in the reference also does not remove the need for schema validation, unknown-value handling and an escalation path.
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
- 1,050,000 tokens
- Input
- File · Image · Text
- Output
- Text
- Listed on OpenRouter
- Parameters listed by OpenRouter
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsverbosity
Estimate your cost
- Estimated credit consumed
- $0.95
- Estimated cash equivalent
- $0.095
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-5.6 Luna | $0.95 | $0.095 |
| GPT-5.6 Sol | $20.00 | $2.00 |
| Qwen3.8 Flash | $0.45 | $0.045 |
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
Extract order_id and intent as JSON from: Please cancel order A-1042 before it ships. Use only information present in the sentence.
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-5.6-luna",
"messages": [
{
"role": "user",
"content": "Extract order_id and intent as JSON from: Please cancel order A-1042 before it ships. Use only information present in the sentence."
}
],
"max_tokens": 4096
}
JSONHow to evaluate the result
Validate the two fields and the order ID, then test missing IDs, multiple orders and ambiguous intent. Measure false confident extractions separately from parse failures.
Before you choose
When should a Luna workflow escalate to Sol?
Define thresholds from your own evaluations: conflicting evidence, repeated validation failure or a task with substantial reasoning depth. Do not use the model’s self-reported confidence as the sole trigger.
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.