Niches · GPU & serverless compute

Package the model and get a deploy to come up

Four or more companies' docs show a full fit.

5companies, full fit
6companies, fit with a limit
24companies carry the tag
8share of the category's work
6first-hand accounts

What counts as done

A build and deploy from the CLI or API completes, the worker reports ready with the engine loaded, logs of a failed start are readable, and no secret is printed in the deploy output.

Measured, for our own tests: the build and deploy complete within 20 minutes. No docs we read state these figures, so they don't count against a listing here.

How agents ask for it: deploy this repo as a GPU function, push my Cog model to Replicate, build a vLLM worker for this model and deploy it

Does the job 5

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Baseten B
Baseten Labs, Inc.
baseten model push builds and deploys from config.yaml; the Startup time card shows Failed and Stalled (30 minutes) outcomes with the phase reached and links to logs; team keys authenticate CI without a browser. source
Cerebrium C
Cerebrium Inc.
cerebrium deploy runs headless with CEREBRIUM_SERVICE_ACCOUNT_TOKEN, builds are cached and billed at $0.08 a minute, a GPU outside the plan is rejected at deploy time, and build logs are readable through the REST API. source
Cloud Run GPUs B
Google LLC
gcloud run deploy --source builds on an e2-highcpu-8 and deploys with --gpu 1 --gpu-type; a startup probe can be lengthened for slow model loads and logs are in Cloud Logging. A service account key or workload identity authenticates CI without a browser. source
Koyeb D
Koyeb SAS
Services build from git or a registry image and the CLI authenticates headless with a token; dry_run validates a definition before deploying and instance statuses (Starting, Unhealthy, Error) with messages are exposed for failed starts. source
Northflank C
Northflank Ltd
Services and jobs build from a linked git repository or deploy a registry image, API tokens come from roles and work headless, and build and job logs are API endpoints. source

Does the job, with a limit 6

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Beam C
Smartshare, Inc.
beam deploy --json with BEAM_TOKEN works headless from CI and the platform API streams logs. The founder-reported issue 1828 showed --format json printing the workspace token into CI logs until PR 1886 (8 September 2026), so older CLIs still leak. source
Hugging Face Inference Endpoints B
Hugging Face, Inc.
A custom container or an engine config is deployed through the UI, API or Python client with runtime logs available, but there is no build step: the image must already exist in a registry, and the FAQ covers endpoints stuck at initializing. source
Modal B
Modal Labs, Inc.
modal deploy builds the image and deploys from a token in the environment; crash-looping containers appear in the dashboard. A deployed Function that crashes on start is retried indefinitely with backoff rather than stopped, and there is no REST deploy API. source
Replicate Deployments B
Replicate, LLC
cog push r8.im/user/model builds and publishes with REPLICATE_API_TOKEN set headless, but a push of a granite-speech model failed with unknown blob for two months (acc-41) and Cog 0.23.1 flooded receivers with full-log webhooks that restarted the pod mid-prediction (acc-42). source
Runpod C
Runpod, Inc.
Templates and endpoints are created through REST v2 or the CLI, and rp login takes RUNPOD_API_KEY headless since 2.1.0. A startup OOM in the vLLM worker exits 1 and restarts on the same footprint with no response-level sign of the eager relaunch (acc-09). source
Verda C
DataCrunch Oy
Containers deploy from any registry through the REST API with Docker config.json or provider auth, but there is no build step: the image must exist first, and the ECR note warns pulls fail after 12 hours without the token permission. source

Doesn't do this job 10

Listings in the category that do something else, with the reason.

ListingWhy
CoreWeave C
CoreWeave, Inc.
No build or push step; customers bring container images to Kubernetes or point Dedicated Inference at weights in object storage. source
Crusoe Cloud B
Crusoe Technologies LLC
No image build or push; Crusoe Container Registry stores images for CMK and VMs take custom images, but nothing deploys a worker from a repo. source
GPUsMarket E
Tyga.Cloud Ltd
No custom image build or push; instance types are the host's Ollama, a docker container with SSH, or a shell. source
Hyperbolic E
Hyperbolic Labs, Inc.
No image build, push or deploy step; the product is a raw VM with Docker installed. source
Lambda Cloud C
Lambda, Inc.
No image build, push or deploy; the product is a VM with Lambda Stack preinstalled. source
Massed Compute E
Massed Compute, Inc.
No image build, push or deploy; images are a fixed list of VM images. source
Nebius AI Cloud BB
Nebius B.V.
Serverless AI takes a container image from a registry; there is no build or push step on the platform. source
Thunder Compute D
Thunder GPU, Inc.
Sandbox images can be prepared from a Dockerfile, but nothing deploys a worker or endpoint from them; instances are VMs with templates. source
Together GPU Clusters C
Together Computer, Inc.
No image build or push; workloads are Kubernetes manifests or Slurm scripts the user brings. source
Vast.ai C
Vast.ai Inc.
Templates reference an existing Docker image; there is no build or push step on the platform. source

What stops agents finishing

  • engine defaults tuned for one GPU list OOM on a card not in the list, and the worker restarts on the same footprint
  • image push fails with an opaque registry error and the only workaround is retrying
  • deploy output in JSON mode contains the bearer token, so CI logs leak it
  • CLI login opens a browser, so a headless agent needs a separate service token

Around it

Before: open-weights.fine-tune-base, agent-harnesses.fix-failing-ci. After: gpu-compute.serverless-model-endpoint.

Where this comes from

Weight 8 of 100 in GPU & serverless compute: 6 of 48 accounts are deploy-time failures: startup OOM with a default setting, a push that fails with unknown blob for two months, a client that ignores Retry-After, a deploy log that prints the workspace token.

The same as data: /api/v1/use-cases/gpu-compute.package-and-deploy.json, or the MCP tool get_use_case with id gpu-compute.package-and-deploy. Other jobs in this category: /api/v1/niches?category=gpu-compute.

Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.