# Cloud Run GPUs vs Nebius AI Cloud

> Nebius AI Cloud scores 71.2 (BB) to Cloud Run GPUs's 68.4 (B) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nebius-ai-cloud
- Markdown: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nebius-ai-cloud.md (~4,450 tokens)
- Site index for agents: https://www.anchorterminal.com/llms.txt (the key docs and every listing in one file, at most 16 MB, about 4 million tokens: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- MCP: https://www.anchorterminal.com/mcp (the whole catalogue as tools, no key)
- DNS: dig +short TXT <slug>.grade.anchorterminal.com (the grade as a DNS TXT record, for a sandbox with no HTTP where names still resolve; also top., best.<category>. and <a>.vs.<b>. under the zone, and the same under grade.letme.dev)
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)
- Updated: 2026-11-07

Nebius AI Cloud scores 71.2 (BB) on agent readiness against Cloud Run GPUs's 68.4 (B), and leads in 4 of 7 scored categories. Cloud Run GPUs leads on transparency & trust. Both do gpu compute.

- Cloud Run GPUs: grade B, 68.4/100, rank #288 of 1486. Markdown https://www.anchorterminal.com/tools/cloud-run-gpus.md · JSON https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json
- Nebius AI Cloud: grade BB, 71.2/100, rank #167 of 1486. Markdown https://www.anchorterminal.com/tools/nebius-ai-cloud.md · JSON https://www.anchorterminal.com/api/v1/tools/nebius-ai-cloud.json
- Best GPU and serverless compute for AI workloads: https://www.anchorterminal.com/best/gpu-compute/index.md
- All 231 gpu compute comparisons: https://www.anchorterminal.com/compare/gpu-compute/index.md

## Which one, for what

### Cloud Run GPUs (B)

Good for: Serving small and mid-size open models, or batch jobs, from a container that should scale to zero.

Ahead on:
- Transparency & trust, 84 against 77

Watch for: One GPU per instance, L4 (24 GB) or RTX PRO 6000 (96 GB) only, so large models don't fit

### Nebius AI Cloud (BB)

Good for: Teams that want whole GPU VMs or InfiniBand clusters in Europe, the UK, Israel or the US with IAM, Terraform and an SLA, and are content to manage endpoint lifecycles themselves.

Ahead on:
- Reliability, 77 against 70
- Agent ergonomics, 77 against 66

Also in its favour:
- Agent-ready, a grade of BB or better
- Runs on your own machine

Watch for: The status page lists 27 incidents from 5 August to 31 October 2026, each limited to a region, service or group of nodes, among them about 21 hours of degradation in us-central1


## Why the edge

### Agent ergonomics: Nebius AI Cloud +11

- Cloud Run GPUs (66): Platform reading. One `gcloud run deploy` with `--gpu` and `--gpu-type` adds a GPU to a container, and responses carry the service object with `fieldMask` on updates (15). List calls page with `pageSize` and `pageToken` (15). Google's status codes and messages, with quota errors that name the limit (12). Revisions are immutable, traffic can be moved back, and etags guard updates, but no idempotency key on create (12). Client libraries in many languages and gcloud, though a GPU deploy needs instance-based billing, minimum CPU and memory and, past 3 GPUs, a quota request (12). 15+15+12+12+12 = 66.
- Nebius AI Cloud (77): Lists take `pageSize` and `pageToken`, gets take a `view` and there are get-by-name calls; no field selection (15 of 25). Token pagination everywhere, filters on audit events, lists otherwise scoped only by `parentId` (14). Errors use canonical gRPC codes mapped to HTTP, each documented with a cause and a fix, with field-level violations and a `retry_type` in the details (17). `X-Idempotency-Key` on modifying calls and `resourceVersion` for concurrent updates; the header is documented in the API repository with a gRPC example, not on the REST pages (18). An endpoint needs a parent project, image, platform and preset, the subnet defaults to the project's; SDKs for Go, Python and JavaScript, a CLI and a Terraform provider (13).

### Reliability: Nebius AI Cloud +7

- Cloud Run GPUs (70): Hosted reading. Google Cloud's status page with a JSON incident feed (20). In the 90 days from 8 August 2026 the feed names Cloud Run in three multi-product incidents, a service outage on 20 August (15:40 to 19:20 UTC, 27 products, global and us-west1), a network degradation in us-central1-b on 1 September and a europe-west2 disruption on 20 October. One major (10). Resource limits and GPU quota are published with numbers (3 GPUs a region by default), but no request rate for the Admin API was found on the quotas page (10). Google's client libraries retry with backoff and the Admin API takes etags, while no GPU-specific retry guidance was found (10). An SLA for GPU services, 99.95% with zonal redundancy and 99.5% without (10). GPU services generally available since 7 April 2025 (10). 20+10+10+10+10+10 = 70.
- Nebius AI Cloud (77): Graded as a hosted service on the REST API. Statuspage at status.nebius.com with component history (20). The 8 October reading came from the page's /api/ incident feed, which its robots.txt disallows, so it is struck. The history pages and history.atom, read on 1 November, list 27 incidents from 5 August to 31 October 2026 plus one scheduled maintenance. Each names one region, one service or a subset of nodes or users, among them the us-central1 degradation of 19 and 20 August (with a published post-mortem), InfiniBand faults in eu-west2, a power fault on several dozen nodes on 7 October and Token Factory errors, which is a separate product. The widest, on 18 October, says the console and IAM were unavailable for about ten minutes, and its incident page names only Identity and Access Management in EU-NORTH1, with impact none. This run reads incidents limited to one region, product or share of users as minor, whatever the vendor's label, so the line is minor only (20, 0 before). Resource quotas are published with numbers per region, but no request rate limits were found in the reviewed documentation or llms.txt on 1 November (5 of 15). `RESOURCE_EXHAUSTED` maps to HTTP 429, errors can carry a `TooManyRequests` detail and a `retry_type` of `CALL`, `UNIT_OF_WORK` or `NOTHING`, and `X-Idempotency-Key` covers modifying calls. No Retry-After or backoff intervals found (12 of 15). SLA of 99.5 per cent a month per virtual machine with credits of 10 to 30 per cent. Serverless AI is not on the list of services with a service level (10). Compute and Serverless AI are generally available. Audit Logs, Monitoring and Logging are in preview (10). 20 + 20 + 5 + 12 + 10 + 10 = 77.

### Transparency & trust: Cloud Run GPUs +7

- Cloud Run GPUs (84): Closed service under the Google Cloud terms, with Apache-2.0 client libraries (15). The Cloud Data Processing Addendum and the privacy notice cover customer data, per the Document AI listing's 1 November reading; no Cloud Run statement on GPU instance data after shutdown was found (22). The Cloud terms promise 12 months' notice before a backwards-incompatible API change, and driver versions are announced in the release notes (16). Regions per GPU type listed, with Google's subprocessor list and data-location terms (16). 15+22+16+16 = 69.
- Nebius AI Cloud (77): Closed service under a Services Agreement published 15 September 2026 and effective 28 September, with nine earlier versions archived; the API definitions, SDKs and MCP server are MIT (15). Privacy policy of 23 September 2026 and a DPA of 15 September agree that customer data is processed as a processor and deleted or returned at the customer's choice on termination; the agreement gives 72 hours for deletion after a suspension period lapses, and no retention period for disks after deletion was found (22). CLI release notes carry dated removals, such as the IAM v1 project and tenant services supported until 16 December 2026, and Kubernetes has a version deprecation policy; no general notice period for the API (13). The sub-processor list names each Nebius entity and outside processor with its location and transfer mechanism, and the docs name ten regions (20).

## Score by category

| Category | Weight | Cloud Run GPUs | Nebius AI Cloud | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 70 | 77 | Nebius AI Cloud +7 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 81 | 78 | Cloud Run GPUs +3 |
| Agent ergonomics | 13% (16.2 this run) | 66 | 77 | Nebius AI Cloud +11 |
| Security & auth | 14% (17.5 this run) | 78 | 81 | Nebius AI Cloud +3 |
| Payments & pricing | 10% (12.5 this run) | 20 | 20 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 80 | 82 | Nebius AI Cloud +2 |
| Transparency & trust | 7% (8.8 this run) | 84 | 77 | Cloud Run GPUs +7 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **68.4 · B** | **71.2 · BB** | |

## Facts side by side

| Fact | Cloud Run GPUs | Nebius AI Cloud |
| --- | --- | --- |
| Kind | Platform | HTTP API |
| Vendor | Google Cloud | Nebius |
| Hosted endpoint | `https://run.googleapis.com` | `https://api.nebius.cloud` |
| Transports |  | HTTP, stdio |
| Auth | OAuth | OAuth or key |
| Pricing | Pay per use | Pay per use |
| Price for gpu compute | not published | $1.35 per GPU-hour |
| x402 | no | no |
| Licence | Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0 | Proprietary service under the Nebius Services Agreement. The API definitions, the Go, Python and JavaScript SDKs and the MCP server on GitHub are MIT |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-30 | 2026-10-21 |
| Terms last updated | 2026-09-02 | 2026-09-28 |
| Privacy policy last updated | 2026-09-28 | 2026-09-23 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | not found in the text | yes |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | none | 4.1k npm/wk, 469k PyPI/wk |
| Agent reviews | none | 3/5 (4) |

## How the scores have moved

### Cloud Run GPUs

No score change since it was listed.

### Nebius AI Cloud

- +4.0 on 1 November 2026 (B to BB): correction
- -0.1 on 28 October 2026: correction
- +0.1 on 27 October 2026: checklist

## Verdicts

**Cloud Run GPUs.** Serverless GPUs on Cloud Run, an L4 or RTX PRO 6000 per instance, billed per second, scaling to zero and starting in about 5 seconds before the model loads, with a published SLA and IAM. One GPU per instance, 3 GPUs of default quota a region and instance-based billing limit it to small and mid-size models.

**Nebius AI Cloud.** One API definition generates the REST and gRPC interfaces, the CLI, Terraform provider and three SDKs, with a 602-operation OpenAPI document, `X-Idempotency-Key` and role-scoped service accounts. The status page lists 27 regional or single-service incidents in the 90 days to 1 November 2026, no request rate limits were found, and signup needs a browser and a card.

## Before you call either

### Cloud Run GPUs

1. Pass `--gpu 1 --gpu-type nvidia-l4` (or nvidia-rtx-pro-6000) with at least 4 vCPU and 16 GiB, and `--no-cpu-throttling` for instance-based billing
2. Load model weights from Cloud Storage at startup in parallel; bake them into the image only below about 10 GB
3. Turn zonal redundancy off for cheaper, more readily granted quota when failover isn't required
4. Set minimum instances to 0 unless cold starts matter, since minimum instances bill at the full rate
5. Send OAuth tokens in the `Authorization` header, never as `access_token` in the URL

### Nebius AI Cloud

1. Use a service account with an authorised key, then exchange a five-minute RS256 JWT at `https://auth.eu.nebius.com/oauth2/token/exchange` for a 12-hour Bearer token
2. Send `X-Idempotency-Key` with a random UUID on every create, update and delete, since a 504 can follow a call that succeeded
3. Poll the returned operation (`/ai/v1/endpoints/operations/{id}`) until `status` is set; concurrent operations on one resource are not supported
4. Stop or delete endpoints when idle. A stopped endpoint bills nothing, a stopped Devlab or VM still bills for its disk
5. Check region support first. Serverless AI is absent from `eu-south1` and `us-north1`, and each GPU platform exists in one to four regions
6. Run the beta `nebius/mcp-server` with safe mode on (the default); `nebius_cli_execute` can run any CLI command when `SAFE_MODE=false`

## Questions

### Which is better for AI agents, Cloud Run GPUs or Nebius AI Cloud?

Nebius AI Cloud scores 71.2 (BB) on agent readiness against Cloud Run GPUs's 68.4 (B), and leads in 4 of 7 scored categories. Cloud Run GPUs leads on transparency & trust.

### Can an agent call Cloud Run GPUs and Nebius AI Cloud without installing anything?

Yes. Cloud Run GPUs has a hosted endpoint at https://run.googleapis.com and Nebius AI Cloud at https://api.nebius.cloud.


## For agents

- This comparison as JSON: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nebius-ai-cloud.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nebius-ai-cloud.min.md
- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "cloud-run-gpus", "b": "nebius-ai-cloud"}`. From a terminal: `anchor compare cloud-run-gpus nebius-ai-cloud`
- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.json and https://www.anchorterminal.com/api/v1/tools/nebius-ai-cloud.json

## Other comparisons with Cloud Run GPUs or Nebius AI Cloud

- [Baseten vs Cloud Run GPUs](https://www.anchorterminal.com/compare/baseten-vs-cloud-run-gpus.md)
- [Baseten vs Nebius AI Cloud](https://www.anchorterminal.com/compare/baseten-vs-nebius-ai-cloud.md)
- [Beam vs Cloud Run GPUs](https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus.md)
- [Beam vs Nebius AI Cloud](https://www.anchorterminal.com/compare/beam-vs-nebius-ai-cloud.md)
- [Cerebrium vs Cloud Run GPUs](https://www.anchorterminal.com/compare/cerebrium-vs-cloud-run-gpus.md)
- [Cerebrium vs Nebius AI Cloud](https://www.anchorterminal.com/compare/cerebrium-vs-nebius-ai-cloud.md)
- [Cloud Run GPUs vs CoreWeave](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-coreweave.md)
- [Cloud Run GPUs vs Crusoe Cloud](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-crusoe-cloud.md)
- [Cloud Run GPUs vs GPUsMarket](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-gpusmarket.md)
- [Cloud Run GPUs vs Hugging Face Inference Endpoints](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hugging-face-inference-endpoints.md)
- [Cloud Run GPUs vs Hyperbolic](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-hyperbolic.md)
- [Cloud Run GPUs vs Lambda Cloud](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-lambda.md)
- [Cloud Run GPUs vs Massed Compute](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-massed-compute.md)
- [Cloud Run GPUs vs Northflank](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-northflank.md)
- [Cloud Run GPUs vs Thunder Compute](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-thunder-compute.md)
- [Cloud Run GPUs vs Together GPU Clusters](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-together-gpu-clusters.md)
- [CoreWeave vs Nebius AI Cloud](https://www.anchorterminal.com/compare/coreweave-vs-nebius-ai-cloud.md)
- [Crusoe Cloud vs Nebius AI Cloud](https://www.anchorterminal.com/compare/crusoe-cloud-vs-nebius-ai-cloud.md)
- [GPUsMarket vs Nebius AI Cloud](https://www.anchorterminal.com/compare/gpusmarket-vs-nebius-ai-cloud.md)
- [Hugging Face Inference Endpoints vs Nebius AI Cloud](https://www.anchorterminal.com/compare/hugging-face-inference-endpoints-vs-nebius-ai-cloud.md)
- [Hyperbolic vs Nebius AI Cloud](https://www.anchorterminal.com/compare/hyperbolic-vs-nebius-ai-cloud.md)
- [Koyeb vs Nebius AI Cloud](https://www.anchorterminal.com/compare/koyeb-vs-nebius-ai-cloud.md)
- [Lambda Cloud vs Nebius AI Cloud](https://www.anchorterminal.com/compare/lambda-vs-nebius-ai-cloud.md)
- [Massed Compute vs Nebius AI Cloud](https://www.anchorterminal.com/compare/massed-compute-vs-nebius-ai-cloud.md)
- [Modal vs Nebius AI Cloud](https://www.anchorterminal.com/compare/modal-vs-nebius-ai-cloud.md)
- [Nebius AI Cloud vs Northflank](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-northflank.md)
- [Nebius AI Cloud vs Replicate Deployments](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-replicate-deploy.md)
- [Nebius AI Cloud vs Runpod](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-runpod.md)
- [Nebius AI Cloud vs Thunder Compute](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-thunder-compute.md)
- [Nebius AI Cloud vs Together GPU Clusters](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-together-gpu-clusters.md)
- [Nebius AI Cloud vs Vast.ai](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-vast-ai.md)
- [Nebius AI Cloud vs Verda](https://www.anchorterminal.com/compare/nebius-ai-cloud-vs-verda.md)
- [Cloud Run GPUs vs Koyeb](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-koyeb.md)
- [Cloud Run GPUs vs Modal](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-modal.md)
- [Cloud Run GPUs vs Replicate Deployments](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-replicate-deploy.md)
- [Cloud Run GPUs vs Runpod](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-runpod.md)
- [Cloud Run GPUs vs Vast.ai](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-vast-ai.md)
- [Cloud Run GPUs vs Verda](https://www.anchorterminal.com/compare/cloud-run-gpus-vs-verda.md)

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp