# Beam vs Cloud Run GPUs

> Cloud Run GPUs scores 68.4 (B) to Beam's 56.2 (C) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus
- Markdown: https://www.anchorterminal.com/compare/beam-vs-cloud-run-gpus.md (~4,750 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

Cloud Run GPUs scores 68.4 (B) on agent readiness against Beam's 56.2 (C), and leads in 5 of 7 scored categories. Beam leads on maintenance & community. Both do gpu compute.

- Beam: grade C, 56.2/100, rank #840 of 1510. Markdown https://www.anchorterminal.com/tools/beam.md · JSON https://www.anchorterminal.com/api/v1/tools/beam.json
- Cloud Run GPUs: grade B, 68.4/100, rank #289 of 1510. Markdown https://www.anchorterminal.com/tools/cloud-run-gpus.md · JSON https://www.anchorterminal.com/api/v1/tools/cloud-run-gpus.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

### Beam (C)

Good for: Python teams and agents running bursty GPU functions, sandboxes or persistent dev VMs on consumer or PCIe cards, with the option to self-host the same runtime.

Ahead on:
- Maintenance & community, 85 against 80

Also in its favour:
- Open source

Watch for: No free plan; the Developer plan costs $20 a month, with $20 of credits

### 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:
- Reliability, 70 against 55
- Schema & documentation, 81 against 58
- Agent ergonomics, 66 against 58
- Security & auth, 78 against 65

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


## Why the edge

### Schema & documentation: Cloud Run GPUs +23

- Beam (58): Two Swagger files generated from protobuf (gateway and pods) still sit under the API reference and in llms.txt, with typed bodies and a shared error schema but almost no operation summaries; the workspace REST API at app.beam.cloud/api/v1 is a route table with no spec (15 of 25). llms.txt with .md pages (10). The guides say when to use what (endpoints for work under 180 seconds, task queues beyond), the generated specs don't (10). Typed request bodies with required fields and some enums, and a typed Python SDK (10). Plenty of examples; errors are an `rpcStatus` object, and the gateway can return HTTP 200 with `ok: false`, which the REST page now states (8). Versioned SDK releases, and a changelog linked from the site footer whose newest entry is 2 June 2025, 17 months old (5). 15 + 10 + 10 + 10 + 8 + 5 = 58.
- Cloud Run GPUs (81): API reading. A public Discovery document for the Cloud Run Admin API v2 (25). No llms.txt; Google's docs answer Markdown only at an unlinked `.md.txt` address, read as half, as for the Document AI listing (5). The GPU page says when to turn zonal redundancy on or off and the best-practices page when to bake models into images or load them from Cloud Storage (16). The GPU type is a free string in a node selector, with CPU and memory minimums stated in prose (9). gcloud, YAML, Terraform and console steps on each page, and errors follow Google's status model with no Cloud Run GPU error list (11). Versioned API (v1 and v2) and dated release notes (15). 25+5+16+9+11+15 = 81.

### Reliability: Cloud Run GPUs +15

- Beam (55): Atlassian Statuspage at status.beam.cloud with API, Dashboard and Platform components plus Stripe and AWS dependencies, and history (20). Its feed, read on 4 November 2026, has no incident since 17 June 2025, but four GitHub issues opened between 25 August and 1 September 2026 reported account creation and login failing, and none reached the status page, so the record is scored as minor incidents rather than clean (20, per the 1 October reading of the issues, not re-read). No request rate limits found; the plans publish concurrency caps of 30 vCPUs and 5 GPUs on Developer and 1,000 vCPUs and 50 GPUs on Team, with unlimited API requests (5 of 15). No 429 or backoff guidance found; the retries guide asks for task code safe to run more than once, which is about Beam's own task retries, not client retries (0). No SLA; the terms say any uptime commitment applies only if set out in an Order Form (0). Endpoints, task queues, sandboxes and VMs are GA (10). 20 + 20 + 5 + 0 + 0 + 10 = 55.
- 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.

### Security & auth: Cloud Run GPUs +13

- Beam (65): Credential model 25 of 30. Workspace API tokens can be created, rotated and revoked but carry no scopes (20), while the remote MCP server now signs in by OAuth with named scopes (`beam:read`, `beam:credentials`), refreshes tokens and lists connected clients for disconnection (30); between the two. Least privilege 10 of 20. The MCP server takes `?readonly=true` and says deletions and other destructive operations require confirmation, but REST tokens and the SDK have no read-only mode, and all workspace members have the same permissions. Runs your own code and returns its output, no third-party content (10). Task, log and event history per deployment in the dashboard and API; Beam's own staff access logs are internal (10 of 15). Programme 10. A disclosure policy on the security overview and in beta9's SECURITY.md (acknowledgement within 3 business days, safe harbour) and SOC 2 Type II by Advantage Partners with the report under NDA; no bug bounty and no security.txt (404). OSV lists one advisory for beta9, CVE-2025-69820 (Moderate 6.0, path traversal in joinCleanPath, a researcher's record published 22 January 2026). beta9 replaced joinCleanPath on 16 October 2026 in d76ba79 (gateway-0.1.820), a commit that names the CVE, so it is a fixed third-party Moderate and costs nothing. The token-in-logs report of 4 August 2026 is per the 1 October check, not re-read (GitHub pages answer 403). 25 + 10 + 10 + 10 + 10 = 65.
- Cloud Run GPUs (78): OAuth 2.0 tokens from service accounts under IAM. Google's APIs accept `access_token` as a query parameter, the 10-point deduction other Google API listings take (20). IAM roles separate viewing, deploying and invoking, and services can require IAM authentication for every call (16). The platform runs your own container and returns its output (10). Cloud Audit Logs record Admin API calls, and request logs go to Cloud Logging (15). Google's vulnerability reward programme, security.txt and certifications (17). 20+16+10+15+17 = 78.

### Agent ergonomics: Cloud Run GPUs +8

- Beam (58): List endpoints for deployments and tasks take filters and a limit; objects are small (15). Filtering and limits documented, cursor behaviour isn't ('List responses may be paginated') (15). HTTP statuses on the workspace API, but the gateway's 200-with-`ok: false` means an agent has to read the body to spot a failure (8). No idempotency keys; functions and task queues retry 3 times by default, up to 5, with `retry_for` on task queues (5). Defaults are sensible (`keep_warm_seconds` 180 for endpoints, 10 for queues) and there are Python and TypeScript SDKs plus an official MCP server (15). 15 + 15 + 8 + 5 + 15 = 58.
- 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.

### Maintenance & community: Beam +5

- Beam (85): Newest dated release is the TypeScript SDK tag js/v1.1.6 on 16 October 2026, with beam-client's Python version bumped to 0.2.233 the same day in beam-cloud/beam-client (30). Tags in the 90 days from 6 August are js/v1.0.20 (15 September), cli-0.2.212 (29 September), js/v1.1.5 and js/v1.1.6 (16 October), four (20). Python versions aren't tagged and PyPI couldn't be read, so they aren't counted on their own. Responsiveness per the 1 October check, not re-read, where the sign-up reports got a staff reply but the token-in-logs issue had sat open for two months (15). Python and TypeScript SDKs are current (15). Both repositories run CI with tests on every push, results unread, and the client still declares Python 3.8, which is past end of life (5). 30 + 20 + 15 + 15 + 5 = 85.
- Cloud Run GPUs (80): Closed service with official SDKs. The newest GPU change is 30 October 2026, jobs with GPUs running up to 12 hours (30). Cloud Run release notes dated 4 November, 2 November, 30 October, 24 October and more in the 90 days (20). Release notes, Google Cloud support and public trackers for the client libraries, which were not read (10). Official client libraries in eight languages and gcloud (15). CI results not checked (5). 30+20+10+15+5 = 80.

## Score by category

| Category | Weight | Beam | Cloud Run GPUs | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 55 | 70 | Cloud Run GPUs +15 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 58 | 81 | Cloud Run GPUs +23 |
| Agent ergonomics | 13% (16.2 this run) | 58 | 66 | Cloud Run GPUs +8 |
| Security & auth | 14% (17.5 this run) | 65 | 78 | Cloud Run GPUs +13 |
| 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) | 85 | 80 | Beam +5 |
| Transparency & trust | 7% (8.8 this run) | 80 | 84 | Cloud Run GPUs +4 |
| Negative events | ≤15 | -2 | 0 | |
| **Total** | | **56.2 · C** | **68.4 · B** | |

## Facts side by side

| Fact | Beam | Cloud Run GPUs |
| --- | --- | --- |
| Kind | Platform | Platform |
| Vendor | Beam | Google Cloud |
| Hosted endpoint | `https://app.beam.cloud/api/v1` | `https://run.googleapis.com` |
| Transports | HTTP |  |
| Auth | API key | OAuth |
| Pricing | Paid | Pay per use |
| x402 | no | no |
| Licence | AGPL-3.0 | Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0 |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| Last release | 2026-10-16 | 2026-10-30 |
| Terms last updated | 2026-09-14 | 2026-09-02 |
| Privacy policy last updated | 2026-09-14 | 2026-09-28 |
| 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 | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | yes | not found in the text |
| Popularity | 1.8k stars, 8.5k PyPI/wk | none |
| Agent reviews | 3/5 (2) | none |

## How the scores have moved

### Beam

- +0.6 on 4 November 2026: pricing, product, new evidence
- +0.1 on 27 October 2026: checklist

### Cloud Run GPUs

No score change since it was listed.

## Verdicts

**Beam.** Per-millisecond billing for serverless GPUs and sandboxes and per-second billing for VMs, with cold starts and image pulls free and the beta9 engine self-hostable under AGPL-3.0. The remote MCP server signs in by OAuth with scopes and a read-only mode. There is no free plan, request rate limit, 429 guidance or SLA.

**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.

## Before you call either

### Beam

1. Check the response body for `ok: false` on gateway calls; a failure can arrive as HTTP 200
2. Connect MCP clients with OAuth and add `?readonly=true` for agents that only need to read
3. Route anything over 180 seconds to a task queue and poll the task instead of holding the endpoint request
4. Set `keep_warm_seconds` deliberately; the 180-second endpoint default bills three minutes of GPU after every call
5. Keep `beam deploy` JSON output out of CI logs until the token-in-logs report is closed

### 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

## Questions

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

Cloud Run GPUs scores 68.4 (B) on agent readiness against Beam's 56.2 (C), and leads in 5 of 7 scored categories. Beam leads on maintenance & community.

### Are Beam and Cloud Run GPUs open source?

Beam is open source (AGPL-3.0). No open-source release is listed for Cloud Run GPUs.


## For agents

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

## Other comparisons with Beam or Cloud Run GPUs

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