Cloud Run GPUs vs Hyperbolic

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.

Hyperbolic 25

Graded on the hosted lines for the REST API. Hyperbolic's Terms of Service (24 March 2025) bar spiders, robots and scrapers from downloading data from any web page in the Services, which cover the website, so hyperbolic.ai pages and the status page keep their 8 October readings, not re-read on 4 November 2026. Status page at status.hyperbolic.ai on UptimeRobot. The page draws its monitors and history by script from /api/, a path its robots.txt closes, so no component was ever read, and a status-page line with no readable component scores 0, as for fonoa, n8n and windmill (was 20). The incident record was never read either (5, unreadable history). Rate limits appear as numbers only on the plan cards in the docs, 60 requests a minute on the free tier and 600 on the pro tier, and the terms let Hyperbolic change limits without notice (10 of 15). No 429 response, Retry-After or backoff guidance in the docs, and no idempotency key on rental creation (0). SLA 7 to 0. The docs state a 99.5 per cent uptime figure for On-Demand and Reserved with credits reviewed case by case, and the Terms of Service disclaim uptime and any duty to give credits. A figure with discretionary credits and no SLA document isn't an SLA (manatal). The v2 API is not marked beta (10). 0 + 5 + 10 + 0 + 0 + 10 = 25.

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.

Hyperbolic 39

Readings are per the 8 October check, not re-read on 4 November 2026. The newest changelog entry is for the week of 5 October 2026, 30 days before today (30); it drops to 20 after 4 November unless a newer entry appears. It was the only dated entry on the changelog and its RSS feed, so the three-entry test is not met (0 of 20). A public changelog with RSS, in-app chat and email support with stated hours of Monday to Friday, 06:00 to 17:00 Pacific Time (9 of 15). No current official SDK for the v2 API. The vendor's MCP repository still ends at its 21 May 2025 commit (clone, 4 November) and targets legacy v1 paths (0 of 15). Package health 3 to 0. The partial rested on the spec served by the API, a struck reading, and there is no client package to assess. 30 + 0 + 9 + 0 + 0 = 39.

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.

Hyperbolic 48

Readings are per the 8 October check, not re-read on 4 November 2026. Plain API keys sent as a Bearer header, shown once, revocable, any number per account, and attributed to their creator inside an Organisation. No scopes or expiry found, and no secret in a URL (20 of 30). No read-only key and no confirmation step. A key can rent and terminate machines and can call DELETE /v2/users/me. Organisation members cannot deposit funds or see billing history (4 of 20). Responses are infrastructure metadata (10). Key lists show each key's creator and revocation time, and rental and transaction histories exist. No audit log was found for self-serve accounts (4 of 15). Programme 9 to 10. The docs ask for vulnerability reports by email with a 48-hour acknowledgement and claim a completed SOC 2 Type I audit with Type II under way, reports under NDA. A disclosure route with a stated acknowledgement time is 10; no security.txt or bug bounty, and the trust centre is drawn by script. 20 + 4 + 10 + 4 + 10 = 48.

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.

Hyperbolic 52

Readings are per the 8 October check, not re-read on 4 November 2026. Contract line 25 to 0. The OpenAPI document was read from the API host (api.hyperbolic.ai/v2/openapi.json, the product's own endpoint) and from a copy under /docs/api-reference/ with no recorded docs page that shows or links it. The first reading is struck, and a contract on a now-paused host with no recorded visible link is struck too (jambonz, stable-audio). llms.txt, every docs page as Markdown and a 188 KB llms-full.txt (10). Of the 34 current operations, 17 have a description that only repeats the summary. The rest state behaviour, limits and named error cases, and every deprecated operation names its replacement (10 of 20). Required fields, 89 enums, numeric bounds and a oneOf for new or existing storage volumes, but rental IDs accept an integer or a string (12 of 15). Five error schemas with examples and 400, 401, 403 and 500 on every operation. No request body has an example and no 429 is listed (8 of 15). Versioned in the path with a dated changelog and RSS feed, which held one entry (12 of 15). 0 + 10 + 10 + 12 + 8 + 12 = 52.

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.

Hyperbolic 64

Readings are per the 8 October check, not re-read on 4 November 2026, apart from the Terms of Service, re-read and unchanged (24 March 2025). Closed service under California law. The terms describe a marketplace in which the contract for compute is between buyer and supplier, which does not match the docs' description of a GPU cloud with an SLA (13 of 30). The Privacy Policy is effective 3 June 2024, gives no retention periods and names Babylon three times in one clause. The terms say user content is not used to train generative models. The docs promise data wiping on termination, a 30-day grace period for volumes and a DPA on request, and no published DPA was found (12 of 30). No written deprecation policy, but legacy paths carry a Sunset header with an end date of 1 March 2027 and each deprecated operation names its replacement (14 of 20). Stripe is named as payment processor. The suppliers that host the machines are not named, and the trust centre's sub-processor list, if any, was unreadable (6 of 20). 13 + 12 + 14 + 6 = 45.

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.

Hyperbolic 55

Readings are per the 8 October check, not re-read on 4 November 2026. No field selection. Lists page at 25 by default and 100 at most, and GET /v2/on-demand/active-rental-summary returns counts and hourly cost without the rental bodies (13 of 25). page and pageSize on active rentals, a cursor on history, and filters for GPU type, region and term type. Storage volumes and SSH keys return whole arrays (15 of 20). Errors carry code, message and issues, with named cases such as INVALID_INPUT_FOR_RENTAL_TYPE and REBOOT_ALREADY_IN_PROGRESS (14 of 20). No idempotency key on create calls. A duplicate SSH key is rejected and terminating an ended rental returns RENTAL_NOT_FOUND (5 of 20). A rental needs only rentalType and gpuCount, with defaults for region, GPU type and SSH key. No official SDK or CLI for the v2 API was found (8 of 15). 13 + 15 + 14 + 5 + 8 = 55.