batchwatch
Live dashboard Use the API

batchwatch › Questions › How long does the Google (Gemini) batch API take?

How long does the Google (Gemini) batch API take?

Between 2 min and 2 min, depending on the model.

The answer

We have measured this. Across the 3 Google models we have enough completions for, the median wait ranges from 2 min (gemini-2.5-flash-lite) to 2 min (gemini-3.7-flash). Nine in ten gemini-2.5-flash-lite jobs finished within 4 min. Every figure carries n and a confidence grade on its own page.

Google promises only "within 24 hours" - a ceiling, not a typical wait. The measured medians above are what jobs actually get, and they are why batching is worth the wait for most workloads.

Questions this answers

How long does the Google batch API actually take?
It depends on the model. The median ranges from 2 min (gemini-2.5-flash-lite) to 2 min (gemini-3.7-flash) across the 3 models we have measured, over the last 30 days.
Is that faster than Google's 24-hour window?
Far faster for the typical job. Google guarantees completion within 24 hours; the measured medians above are minutes, not hours. The 24-hour window is the contract, not the experience.

See it live

Every number here is measured, and it is all public.

The live dashboard shows every model with its distribution, n and confidence grade. /v1/coverage is the same data as JSON, no key required. Contributing five measurements in seven days cuts the public delay to five minutes and unlocks the decision endpoints (/v1/should-i-batch, /v1/estimate-batchtime).

More questions we have measured the answer to

How long does the OpenAI batch API take? How long does the Anthropic Message Batches API take? Is the OpenAI Batch API worth it? Is the Anthropic Message Batches API worth it? How much cheaper is the OpenAI Batch API? How much cheaper is the LLM batch API? LLM batch API vs synchronous: which should I use?