0 providers50 models

Use-case preset

Sentiment analysis cost calculator

Classify reviews or messages by sentiment; batch, high-throughput workload.

High-throughput batch classifier: ingest a review, support ticket, or social post and emit a label (positive/negative/neutral, or a 1–5 star score). Runs offline over millions of records; cost-per-call and throughput are the only metrics that matter.

The 95/5 ratio is near-maximal — the full text of the item dominates the prompt while the output is a single token or short label. A 1k context window is sufficient for the vast majority of reviews and short messages. Latency is batch/best-effort; this workload runs on queues, not in real-time APIs. `cachedPromptPercent` is ~35: the classification schema, label definitions, and few-shot examples repeat across every call. The biggest cost lever is model size — a 1B–3B model fine-tuned on classification can match a 70B zero-shot model at 20–40× lower cost. If you're running >1M items/day, that difference is worth a fine-tuning investment.

Recommended models

Minimal cost per classification at scale; sufficient for binary and 3-class sentiment with a good prompt.
Slightly stronger on nuanced sentiment (e.g., aspect-level) while remaining extremely cost-efficient.
IBM's compact model is well-calibrated on classification tasks with reliable label adherence.
Google's 2B instruction model delivers solid classification quality for a fraction of large-model pricing.
Step up to 8B when fine-grained multilingual sentiment or 5-star scoring accuracy is required.