Batch Mode in the Gemini API: Process More for Less

https://developers.googleblog.com/en/scale-your-ai-workloads-batch-mode-gemini-api/

by xnx • 1 year ago

168 54 1 year ago

developers.googleblog.com

For those who aren't aware, OpenAI has a very similar batch mode (50% discount if you wait up to 24 hours): https://platform.openai.com/docs/api-reference/batch

It's nice to see competition in this space. AI is getting cheaper and cheaper!

fantispug• 1 year ago

Yes, this seems to be a common capability - Anthropic and Mistral have something very similar as do resellers like AWS Bedrock.

I guess it lets them better utilise their hardware in quiet times throughout the day. It's interesting they all picked 50% discount.

qrian• 1 year ago

Bedrock has a batch mode but only for claude 3.5 which is like one year old, which isn't very useful.

calaphos• 1 year ago

Inference throughout scales really well with larger batch sizes (at the cost of latency) due to rising arithmetic intensity and the fact that it's almost always memory BW limited.

briangriffinfan• 1 year ago

50% is my personal threshold for a discount going from not worth it to worth it.

bayesianbot• 1 year ago

DeepSeek has gone a bit different route - they give automatic 75% discount between UTC 16:30-00:30

https://api-docs.deepseek.com/quick_start/pricing

dlvhdr• 1 year ago

The latest price increases beg to differ

dmos622• 1 year ago

What price increases?

dist-epoch3• 1 year ago

Only because Flash was mispriced to start with. It was set too cheap compared with its capabilities. They didn't raise the price of Pro.

laborcontract• 1 year ago

One open secret is that batch mode generations often take much less than 24 hours. I've done a lot of generations where I get my results within 5ish minutes.

ridgewell• 1 year ago

It can depend a lot on the shape of your batch to my understanding. A small batch job can be tasked out a lot quicker than a large batch job waiting for just the right moment where capacity fits.

dsjoerg• 1 year ago

We used the previous version of this batch mode, which went through BigQuery. It didn't work well for us at the time because we were in development mode and we needed faster cycle time to iterate and learn. Sometimes the response would come back much faster than 24 hours, but sometimes not. There was no visibility offered into what response time you would get; just submit and wait.

You have to be pretty darn sure that your job is going to do exactly what you want to be able to wait 24 hours for a response. It's like going back to the punched-card era. If I could get even 1% of the batch in a quicker response and then the rest more slowly, that would have made a big difference.

cpard5• 1 year ago

It seems that the 24h SLA is standard for batch inference among the vendors and I wonder how useful it can be when you have no visibility on when the job will be delivered.

I wonder why they do that and who is actually getting value out of these batch APIs.

Thanks for sharing your experience!

vineyardmike• 1 year ago

It’s like most batch processes, it’s not useful if you don’t know what the response will be and you’re iterating interactively. It for data pipelines, analytics workloads, etc, you can handle that delay because no one is waiting on the response.

I’m a developer working on a product that lets users upload content. This upload is not time sensitive. We pass the content through a review pipeline, where we did moderation and analysis, and some business-specific checks that the user uploaded relevant content. We’re migrating some of that to an LLM based approach because (in testing) the results are just as good, and tweaking a prompt is easier than updating code. We’ll probably use a batch API for this and accept that content can take 24 hours to be audited.

3eb7988a1663• 1 year ago

Think of it like you have a large queue of work to be done (eg summarize N decades of historical documents). There is little urgency to the outcome because the bolus is so large. You just want to maintain steady progress on the backlog where cost optimization is more important than timing.

YetAnotherNick• 1 year ago

Contrary to other comments it's likely not because of queue or general batch reasons. I think it is because that LLMs are unique in the sense that it requires lot of fixed nodes because of vRAM requirements and hence it is harder to autoscale. So likely the batch jobs are executed when they have free resources from interactive servers.

jampa• 1 year ago

who is actually getting value out of these batch APIs

I used the batch API extensively for my side project, where I wanted to ingest a large amount of images, extract descriptions, and create tags for searching. After you get the right prompt, and the output is good, you can just use the Batch API for your pipeline. For any non-time-sensitive operations, it is excellent.

dist-epoch3• 1 year ago

you have no visibility on when the job will be delivered

You do have - within 24 hours. So don't submit requests you need in 10 hours.

serjester• 1 year ago

We've submitted tens of millions of requests at a time and never had it take longer than a couple hours - I think the zone you submit to plays a role.

Jensson• 1 year ago

If I could get even 1% of the batch in a quicker response and then the rest more slowly, that would have made a big difference.

You can do this, just send 1% using the regular API.

Implicated• 1 year ago

I was also rather puzzled at this comment - why not dev against real time endpoints and batch when you've got things where you need them?

lazharichir• 1 year ago

You can also do gemini flash lite for a subset and then batch the rest with flash or pro

nnx• 1 year ago

It would be nice if OpenRouter supported batch mode too, sending a batch and letting OpenRouter find the best provider for the batch within given price and response time.

pugio• 1 year ago

Hah, I've been wrestling with this ALL DAY. Another example of Phenomenal Cosmic Powers (AI) combined with itty bitty docs (typical of Google). The main endpoint ("https://generativelanguage.googleapis.com/v1beta/models/gemi...") doesn't even have actual REST documentation in the API. The Python API has 3 different versions of the same types. One of the main ones (`GenerateContentRequest`) isn't available in the newest path (`google.genai.types`) so you need to find it in an older version, but then you start getting version mismatch errors, and then pydantic errors, until you finally decide to just cross your fingers and submit raw JSON, only to get opaque API errors.

So, if anybody else is frustrated and not finding anything online about this, here are a few things I learned, specifically for structured output generation (which is a main use case for batching) - the individual request JSON should resolve to this:

```json { "request": { "contents": [ { "parts": [ { "text": "Give me the main output please" } ] } ], "system_instruction": { "parts": [ { "text": "You are a main output maker." } ] }, "generation_config": { "response_mime_type": "application/json", "response_json_schema": { "type": "object", "properties": { "output1": { "type": "string" }, "output2": { "type": "string" } }, "required": [ "output1", "output2" ] } } }, "metadata": { "key": "my_id" } } ```

To get actual structured output, don't just do `generation_config.response_schema`, you need to include the mime-type, and the key should be `response_json_schema`. Any other combination will either throw opaque errors or won't trigger Structured Output (and will contain the usual LLM intros "I'm happy to do this for you...").

So you upload a .jsonl file with the above JSON, and then you try to submit it for a batch job. If something is wrong with your file, you'll get a "400" and no other info. If something is wrong with the request submission you'll get a 400 with "Invalid JSON payload received. Unknown name \"file_name\" at 'batch.input_config.requests': Cannot find field."

I got the above error endless times when trying their exact sample code: ``` BATCH_INPUT_FILE='files/123456' # File ID curl https://generativelanguage.googleapis.com/v1beta/models/gemi... \ -X POST \ -H "x-goog-api-key: $GEMINI_API_KEY" \ -H "Content-Type:application/json" \ -d "{ 'batch': { 'display_name': 'my-batch-requests', 'input_config': { 'requests': { 'file_name': ${BATCH_INPUT_FILE} } } } }" ```

Finally got the job submission working via the python api (`file_batch_job = client.batches.create()`), but remember, if something is wrong with the file you're submitting, they won't tell you what, or how.

TheTaytay• 1 year ago

Thank you for posting this! (When I run into errors with posted sample code, I spend WAY too long assuming it’s my fault.)

nacholibrev• 1 year ago

So you upload a .jsonl file with the above JSON, and then you try to submit it for a batch job. If something is wrong with your file, you'll get a "400" and no other info. If something is wrong with the request submission you'll get a 400 with "Invalid JSON payload received. Unknown name \"file_name\" at 'batch.input_config.requests': Cannot find field."

Thanks for your post, I've stumbled upon the same issue as you.

So I should interpret the "Unknown name \"file_name\" at 'batch.input_config.requests'" as an error with the jsonl file and not the payload itself?

I'm trying to submit a batch with a .jsonl file, but I'm always getting the "Unknown name \"file_name\" at 'batch.input_config.requests'" error.

great_psy• 1 year ago

Is this an indication of the peak of the AI bubble ?

In a way this is saying that there are some GPUs just sitting around so they would rather get 50% than nothing for their use.

graeme• 1 year ago

Seems more like electricity pricing, which has peak and offpeak pricing for most business customers.

To handle peak daily load you need capacity that goes unused in offpeak hours.

reasonableklout• 1 year ago

Why do you think that this means "idle GPU" rather than a company recognizing a growing need and allocating resources toward it?

It's cheaper because it's a different market with different needs which can be served by systems optimizing for throughput instead latency. Feels like you're looking for something that's not there.

dmitry-vsl• 1 year ago

Is it possible to use batch mode with fine-tuned models?

segalord• 1 year ago

Man googles offerings are so inconsistent, batch processing has been available on vertex for a while now, I dont really get why they have two different offering in vertex and gemini, both are equally inaccessible

nikolayasdf123• 1 year ago

omg I realized this is not Vertex AI face-palm

rockwotj• 1 year ago

It’s because vertex is the “entrrprise” offering that is hippa compliant, etc. That is why vertex only has explicit prompt caching and not implicit, etc. Vertex usage is never used for training or model feedback, but the gemini API does. Basically the Gemini API is Google’s way of being able to move faster like openai and the other foundational model providers, but still having an enterprise offering. Go check Anthropic’s documentation, they even say if you have enterprise or regulatory needs go use bedrock or vertex.

Deathmax• 1 year ago

Vertex's offering of Gemini very much does implicit caching, and has always been the case [1]. The recent addition of applying implicit cache hit discounts also works on Vertex, as long as you don't use the `global` endpoint and hit one of the regional endpoints.

[1] http://web.archive.org/web/20240517173258/https://cloud.goog..., "By default Google caches a customer's inputs and outputs for Gemini models to accelerate responses to subsequent prompts from the customer. Cached contents are stored for up to 24 hours."

druskacik• 1 year ago

I've been using OpenAI's batch API for some time, then replaced it with Mistral's batch API because it was cheaper (Mistral Small with $0.10 / $0.20 per million tokens was perfect for my use case). This makes me rethink my choice, e.g. Gemini 2.5 Flash-Lite seems to be a better model[0] with only a slight price increase.

[0] https://artificialanalysis.ai/leaderboards/models

tucnak• 1 year ago

I really hope it means that 2.5 models will be available for batching in Vertex, too. We had spent quite a bit of effort making it work with BigQuery, and it's really cool when it works. There's edge-case, though, where it doesn't work: in case the batch is also referring to cached prompt. We did report this a few months ago.

anupj• 1 year ago

Batch Mode for the Gemini API feels like Google’s way of asking, “What if we made AI more affordable and slower, but at massive scale?” Now you can process 10,000 prompts like “Summarize each customer review in one line” for half the cost, provided you’re willing to wait until tomorrow for the results.

dist-epoch3• 1 year ago

Most LLM providers have batch mode. Not sure why you are calling them out.

okdood642• 1 year ago

I'll take it further. Regular cloud compute have batch workload capabilities at cheaper rates, as well since forever.

diggan• 1 year ago

Now you can process 10,000 prompts like “Summarize each customer review in one line” for half the cost, provided you’re willing to wait until tomorrow for the results.

Sounds like a great option to have available? Not every task I use LLMs for need immediate responses, and if I wasn't using local models for those things, getting a 50% discount and having to wait a day sounds like a fine tradeoff.

XTXinverseXTY• 1 year ago

This is an extremely common use case.

Reading your comment history: are you an LLM?

https://news.ycombinator.com/item?id=44531907

https://news.ycombinator.com/item?id=44531868

okdood642• 1 year ago

I don't understand the point you're making. This has been a commonly used offering since cloud blew up.

https://aws.amazon.com/ec2/spot/

kerisi• 1 year ago

I've been using this with nothing notable to mention besides there seems to be a common bug where you receive an empty text response.

https://discuss.ai.google.dev/t/gemini-2-5-pro-with-empty-re...

lopuhin• 1 year ago

I find OpenAI's new flex processing more attractive, as it has the same 50% discount, but allows to use the same API as regular chat mode, so you can still do stuff where Batch API won't work (e.g. evaluating agents), and in practice I found it to work well enough when paired with client-side request caching: https://platform.openai.com/docs/guides/flex-processing?api-...

irthomasthomas• 1 year ago

It's nice that they stack the batch pricing and caching discount. I asked the Google guy if they did the same but got no reply, so probably not.

Edit: anthropic also stack batching and caching discounts

Batch Mode in the Gemini API: Process More for Less

Related Stories