Choosing this model
Selection advice by Y-API. The checks below are suggested evaluations, not published test results.
Where to start
Use it for classification, extraction and summarization at volume, or as the cheap first stage of a two-stage pipeline that escalates only hard cases to a larger model.
What to watch for
The 200,000-token window is a fifth of the newer Haiku entry at a much higher input price, so it is not the value pick in this family. Its documented parameter list is also narrower than the newer models.
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
- 200,000 tokens
- Input
- Text · Image · File
- Output
- Text
- Listed on OpenRouter
- Parameters listed by OpenRouter
include_reasoningmax_completion_tokensmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
API pricing & cost estimate
- Estimated credit consumed
- $3.75
- Estimated cash equivalent
- $0.375
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 |
|---|---|---|
| Claude Haiku 4.5 | $3.75 | $0.375 |
| Claude Haiku 5.5 | $0.45 | $0.045 |
| Claude Sonnet 5 | $7.00 | $0.70 |
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 support message as billing, login or outage, and return one line per message with the label and a short reason.
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": "anthropic/claude-haiku-4.5",
"messages": [
{
"role": "user",
"content": "Classify each support message as billing, login or outage, and return one line per message with the label and a short reason."
}
],
"max_tokens": 4096
}
JSONHow to evaluate the result
Score the labels against a hand-checked set and track the escalation rate if you route low-confidence cases onward. Compare both against the newer Haiku on the same messages.
Before you choose
Is Haiku 4.5 cheaper than Haiku 5.5?
No — in this catalog it is the opposite. Haiku 4.5 lists $1.00 per million input tokens against $0.15 for Haiku 5.5, with a shorter window as well. Check the models page for current numbers before choosing.
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.