Savings
Batch API savings calculator
What moving a workload to the vendor's Batch API saves, for the share of requests that can wait.
Prices read from the vendor pages on 2026-10-20. Arithmetic on list prices, not advice or a quote.
Saving and exports need Norwell Tools Pro, $9 a month. See what is in it. Everything above is free.
How it works
OpenAI, Anthropic, Google and Mistral publish a 50 percent Batch discount for asynchronous jobs completed within about a day. DeepSeek and xAI list none. Classification, enrichment and nightly summaries are typical batchable work; chat is not.
The formula
with batch = standard * (1 - share) + standard * share * (1 - discount)Worked example
With the inputs the page opens on:
- model: gpt-5.4
- input tokens: 2000 tokens
- output tokens: 300 tokens
- requests per month: 200000
- batchable share pct: 70%
gives
- monthly standard: $1,900
- monthly with batch: $1,235
- monthly savings: $665
- batch discount pct: 50 %
Sources
- https://developers.openai.com/api/docs/pricing (read 2026-10-20)
- https://platform.claude.com/docs/en/about-claude/pricing (read 2026-10-20)
- https://ai.google.dev/gemini-api/docs/pricing (read 2026-10-20)
- https://docs.mistral.ai/inference/pricing (read 2026-10-20)
Prices read from each vendor's own pricing page on 2026-10-20; the page may have changed since. This is arithmetic on published list prices, not advice or a quote. Check the vendor's page before committing a budget.