Cost = (input tokens ÷ 1M × input price) + (output tokens ÷ 1M × output price). Prices come from our daily-verified model data. Batch and cached-input discounts are not applied — they only ever make these numbers smaller.
“Needs chunking” means the model's context window can't hold this job in a single pass, so the real cost is higher than the figure shown and quality usually suffers.
Should you just pick the cheapest?
This is the volume shape where cheap models earn their keep: the per-item cost is fractions of a cent and the job is formulaic enough that a budget model rarely embarrasses you. Batch APIs typically halve these figures again for work with no deadline.
How much does it cost to write product descriptions with AI?
$0.0000 on Gemma 2 9B, the cheapest capable option, rising to $0.0027 on Claude Sonnet 5 at the top end. DeepSeek V4-Pro is the value pick at $0.0003 per run. The job is priced at 250 input and 220 output tokens — see the working below.
How did you work out the token count for this task?
Ten product attributes with values ≈ 250 input tokens. A 160-word description ≈ 220 output tokens.
What does this cost at a 1,000-product catalogue?
$0.027 a month on Gemma 2 9B, $0.300 on DeepSeek V4-Pro, and $2.70 on Claude Sonnet 5. Batch APIs typically halve these figures for work that can wait, and prompt caching cuts the input side further when the same context is reused.
Is the cheapest model the right choice for this task?
This is the volume shape where cheap models earn their keep: the per-item cost is fractions of a cent and the job is formulaic enough that a budget model rarely embarrasses you. Batch APIs typically halve these figures again for work with no deadline.
Are these prices current?
Yes. Every figure on this page is computed from our model pricing data, which is checked daily against each provider's official pricing page. When a provider changes a price, these numbers change with it.