# Cloud Run GPUs vs Nodus Compute (slim)

> Cloud Run GPUs scores 69.6 (B) to Nodus Compute's 60.6 (C) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nodus-compute.md (~5,200 tokens) · this version ~1,030 tokens · JSON https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nodus-compute.json · canonical https://www.anchorterminal.com/compare/cloud-run-gpus-vs-nodus-compute
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-18
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Cloud Run GPUs scores 69.6 (B) on agent readiness against Nodus Compute's 60.6 (C), and leads in 4 of 7 scored categories. Nodus Compute leads on schema & documentation and agent ergonomics. Both do gpu compute.

- Cloud Run GPUs: B 69.6, rank #330 of 1557 · https://www.anchorterminal.com/tools/cloud-run-gpus.min.md
- Nodus Compute: C 60.6, rank #763 of 1557 · https://www.anchorterminal.com/tools/nodus-compute.min.md
- Cloud Run GPUs, 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 25; Security & auth, 78 against 73; Maintenance & community, 80 against 70; Transparency & trust, 84 against 59.
- Nodus Compute, good for Teams that want to run GPU training, inference and agent sandboxes from a coding agent with cost estimates before each create, or to put their own idle GPUs to work. Ahead on Schema & documentation, 89 against 81; Agent ergonomics, 82 against 66. Also Runs on your own machine.

| Category | Cloud Run GPUs | Nodus Compute |
| --- | --- | --- |
| Reliability (16%) | 70 | 25 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 81 | 89 |
| Agent ergonomics (13%) | 66 | 82 |
| Security & auth (14%) | 78 | 73 |
| Payments & pricing (10%) | 30 | 30 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 80 | 70 |
| Transparency & trust (7%) | 84 | 59 |

| Fact (where they differ) | Cloud Run GPUs | Nodus Compute |
| --- | --- | --- |
| Kind | Platform | HTTP API |
| Vendor | Google Cloud | Nodus, Inc. |
| Hosted endpoint | `https://run.googleapis.com` | `https://api-next.nodus-compute.ai/mcp` |
| Transports |  | HTTP, Streamable HTTP, stdio |
| Auth | OAuth | OAuth or key |
| Licence | Proprietary service under the Google Cloud Platform terms. Client libraries are Apache-2.0 | Proprietary hosted service under the Nodus Terms of Service. The Python SDK repository is Apache-2.0 |
| Tools exposed | none | 17 |
| Read-only variant documented | no | yes |
| Last release | 2026-10-30 | 2026-11-16 |
| Terms last updated | 2026-09-02 | 2026-07-28 |
| Privacy policy last updated | 2026-09-28 | 2026-10-08 |
| Customer content may train models | not found in the text | yes, with an opt-out |
| Popularity | none | 2 stars |

Why the edge:
- Reliability, Cloud Run GPUs +45: Cloud Run GPUs 70 (Hosted reading.); Nodus Compute 25 (Hosted lines, for the hosted MCP server and the HTTP API.)
- Transparency & trust, Cloud Run GPUs +25: Cloud Run GPUs 84 (Closed service under the Google Cloud terms, with Apache-2.0 client libraries (15).); Nodus Compute 59 (Closed service under terms dated 28 July 2026. The SDK repository is Apache-2.0 but stale (20 of 30).)
- Agent ergonomics, Nodus Compute +16: Cloud Run GPUs 66 (Platform reading.); Nodus Compute 82 (17 hosted MCP tools that work on every resource kind, filtered by the scopes granted, with logs capped at 2,000 lines and waits at 60 seconds (15 for 11 to 30…)
- Maintenance & community, Cloud Run GPUs +10: Cloud Run GPUs 80 (Closed service with official SDKs.); Nodus Compute 70 (`nodus-compute` 1.0.92 on PyPI on 16 November 2026, per PyPI's release feed (30).)
- Schema & documentation, Nodus Compute +8: Cloud Run GPUs 81 (API reading.); Nodus Compute 89 (OpenAPI 3.0.3, shown in the v1 API reference and published as openapi/openapi.yaml in the Apache-2.0 SDK repository with 184 operation IDs (25).)
- Security & auth, Cloud Run GPUs +5: Cloud Run GPUs 78 (OAuth 2.0 tokens from service accounts under IAM.); Nodus Compute 73 (API keys with Standard, Inference only, Read only or custom scopes, project limits and an optional expiry, stored as a keyed hash and revocable.)
