Choosing this model
Selection advice by Y-API. The checks below are suggested evaluations, not published test results.
Where to start
Evaluate it on structured extraction followed by a consistency check: recover chart values or document fields, then verify the arithmetic with an external tool. Separate perception errors from reasoning errors.
What to watch for
The Flash name does not supply a latency guarantee, and the gateway’s accepted media formats may be narrower than the reference. Verify each reasoning setting rather than assuming the native provider’s configuration maps directly.
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
- 262,144 tokens
- Input
- Text · Image · Video
- Output
- Text
- Listed on OpenRouter
- Parameters listed by OpenRouter
frequency_penaltyinclude_reasoninglogprobsmax_tokenspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Estimate your cost
- Estimated credit consumed
- $0.80
- Estimated cash equivalent
- $0.08
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 |
|---|---|---|
| Step 3.7 Flash | $0.80 | $0.08 |
| Qwen3.8 Flash | $0.45 | $0.045 |
| GLM 5.3 Flash | $0.40 | $0.04 |
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
An invoice lists items at 30 and 45, tax of 15 and a total of 100. Check the arithmetic and identify exactly which value is inconsistent.
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": "stepfun/step-3.7-flash",
"messages": [
{
"role": "user",
"content": "An invoice lists items at 30 and 45, tax of 15 and a total of 100. Check the arithmetic and identify exactly which value is inconsistent."
}
],
"max_tokens": 4096
}
JSONHow to evaluate the result
The components sum to 90, but the evidence does not show which source field is wrong. A good answer flags the inconsistency without silently changing the invoice.
Before you choose
What should I compare with other Flash models?
Use extraction accuracy, schema validity, completed tool calls and total tokens on the same inputs. Measure endpoint latency yourself instead of interpreting Flash as a standardized speed class.
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.