Choosing this model
Selection advice by Y-API. The checks below are suggested evaluations, not published test results.
Where to start
Use it as the default for routine engineering work — implementing a scoped ticket, writing tests around existing behaviour, reviewing a pull request — where Sol is more than the task needs.
What to watch for
The tier structure is the publisher’s framing. Terra sitting between two other entries tells you about positioning, not about which model will pass your acceptance checks; measure that yourself.
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
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 |
|---|---|---|
| GPT-5.6 Terra | $8.00 | $0.80 |
| GPT-5.6 Sol | $20.00 | $2.00 |
| 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
Implement this ticket against the existing interfaces. List the assumptions you made where the ticket was silent, and add a test for each one.
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-terra",
"messages": [
{
"role": "user",
"content": "Implement this ticket against the existing interfaces. List the assumptions you made where the ticket was silent, and add a test for each one."
}
],
"max_tokens": 4096
}
JSONHow to evaluate the result
The stated assumptions should match the ones you would have flagged. A run that silently picks a behaviour for an unspecified edge case, with no test, has hidden a decision from you.
Before you choose
Terra or Sol for a long agent run?
Start with Terra and record where it fails. Escalating the whole run to Sol because of a few hard steps usually costs more than routing only those steps to it.
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.