Hugging Face Inference Endpoints vs Together GPU Clusters

Hugging Face Inference Endpoints 73

Better Stack status page at status.huggingface.co with separate Inference Endpoints UI and API components and 90 days of history (20). On 2 November 2026 both components show 100 per cent uptime, with one scheduled maintenance window for H200 on 7 October 2026. The page posts incidents for other services in the window (GPU Jobs and Spaces failing to start on 24 and 25 September), and none touches Inference Endpoints since the UI outage of 16 July left the 90 days, so a clean record (30). No rate limits were found for the management API. The Hub publishes limits per 5-minute window (1,000 API requests for a free user), without saying they cover api.endpoints.huggingface.cloud (5). The docs explain the 503 returned while a replica starts and the X-Scale-Up-Timeout header that holds the request, and advise 2 replicas for availability. No backoff guidance or idempotency keys for writes (8). No SLA found in the docs or on the pricing page (0). The service is generally available (10).

Together GPU Clusters 38

Read with the hosted lines. status.together.ai lists the website, the playground and serverless models with no component for GPU clusters, and a vendor page with no component for the product takes 15 in this run, as for Together's Code Sandbox and fine-tuning listings (15). No incident history for clusters can be read (5). No rate limits for the clusters API found (0). Together's docs give 429 and 503 backoff guidance for its APIs, per the inference listing's 1 November check, and the CLI has --non-interactive and --json for scripted retries, but creation has no idempotency key (8). No SLA for clusters found; the published 99% commitment covers provisioned inference throughput only (0). Generally available since 9 September 2025 and out of the CLI's beta paths since 22 October 2026, with preemptible nodes in preview (10). 15+5+0+8+0+10 = 38.

Hugging Face Inference Endpoints 73

Public OpenAPI 3.1 documents for the management API (42 paths, 48 operations on 2 November 2026) and the catalogue API (3 operations, per the 8 October check) (25). llms.txt with a Markdown twin of every docs page (10). Every operation has a summary tagged READ, WRITE, PUBLIC or PRO, but only 7 of 48 have a description. The MCP tool table states each tool's purpose and says to call get_recommended_config before create_endpoint (11). 131 typed schemas with required fields and enums for state, type and accelerator. List filters are comma-separated strings (12). Parameters carry examples. The management document lists only 200 responses on 45 of 48 operations, plus 501 on three log routes, while the catalogue document lists 400, 401, 404, 409 and 500 (7). Paths are versioned /v2 and /v3 and the document is version 2.0.0. Inference Endpoints has no changelog of its own. The Hub changelog and the docs repository history are the dated record (8).

Together GPU Clusters 92

Public OpenAPI 3.1 for /v1/compute/clusters and shared volumes, MIT, embedded in every reference page (25). llms.txt and a Markdown twin of every page (10). The docs say when to choose Kubernetes or Slurm and each capacity type, and the management page carries instructions for agents on reporting live availability and prices (18). Enums for cluster type, billing type, GPU type and status, required fields marked (13). CLI, Python, TypeScript and console steps on each task, with 402 and 403 cases documented, though no error catalogue for the clusters API (11). Versioned SDKs and a dated changelog with cluster entries (15). 25+10+18+13+11+15 = 92.

Hugging Face Inference Endpoints 83

OAuth through huggingface.co with read-endpoints and write-endpoints scopes, PKCE and dynamic client registration for the MCP server, and revocable fine-grained access tokens for the API. No documented option to send a token in a URL (30). Read and write scopes are separate, endpoints are private by default, organisations on Team and Enterprise plans can require approval of fine-grained tokens, and the MCP delete tool needs confirm: true. Other write calls have no confirmation step (17). The service returns the output and logs of the owner's own model, not third-party content (10). An audit log route and MCP tool on Pro, Team or Enterprise plans, plus logs and metrics for every endpoint (12). security.txt valid to 2030 with security@huggingface.co, SOC2 Type 2 stated for the Hub and Inference Endpoints, malware and pickle scanning of repositories. No bug bounty was found (14).

Together GPU Clusters 68

Project-scoped API keys, revocable with optional expiry, read as Together's other listings read the same key model (30). Admin and editor roles with no read-only role. Only admins get the admin kubeconfig, which has cluster-admin rights, and OIDC lets editors use kubectl under RBAC. Deletes run without confirmation when --non-interactive is passed (8). The API returns cluster state, not third-party content (10). Invoices itemise reserved, on-demand and storage charges, and no audit log for cluster operations was found (5). security.txt with a HackerOne route, per the 1 November check of the inference listing (15). 30+8+10+5+15 = 68.

Hugging Face Inference Endpoints 62

List endpoints takes limit (default 20) and cursor, logs take limit, tail and line_max_length, and the MCP server has 19 tools (18). Cursor pagination, filters by state, type, task and tags, sorting, and a time window on logs (18). Errors are documented for the catalogue API and in prose for pause, resume and scale to zero. The management document has no error schema (8). No idempotency keys. Endpoints are addressed by name, updates are a PUT, and the MCP delete tool previews before a confirmed second call. MCP annotations weren't read (8). One-call deploy from the catalogue with tuned defaults, a Python client and the hf endpoints CLI. A second-language SDK for endpoint management wasn't found (10).

Together GPU Clusters 55

Cluster objects are compact, and --json gives machine-readable output, but list calls take no field selection (15). No pagination or filters on the clusters list (8). 402 and 403 with readable messages such as "Insufficient credits for cluster creation", and troubleshooting for common failures (12). Status polling until Ready is documented and deletes run non-interactively, but there is no idempotency key on creation and a duplicate create bills a second cluster (8). Official Python and TypeScript SDKs and a CLI, though a create takes GPU type, region, driver and CUDA versions, cluster type and billing type (12). 15+8+12+8+12 = 55.

Hugging Face Inference Endpoints 80

huggingface_hub v2.4.0 was tagged on 29 October 2026, and the docs repository changed on 23 October (30). Tags v2.0.0 (24 September), v2.1.0, v2.1.1, v2.2.0, v2.3.0 (23 October) and v2.4.0 in the 90 days, and docs commits on 14 and 15 October adding the inferenceLoad scaling strategy and a daily autoscaling schedule (20). GitHub's pages refused our requests, so issue response times went unread. A public changelog for the Hub, a forum and a quota contact form exist (8 of 15). Current official Python client and CLI (15). The client supports Python 3.10 and later and ships weekly. Its CI wasn't read (7).

Together GPU Clusters 75

Closed service. The newest cluster change is CLI and SDK 3.0 on 22 October 2026, 15 days before this check (30). Dated cluster entries in the 90 days from 8 August include 12, 18, 19, 24, 27 and 28 August, 10 September and 22 October (20). Dated changelog, a support portal and Discord, with responsiveness not tested (8). Python SDK 3.1 and TypeScript SDK 1.0 are current and cover clusters (15). SDK CI and dependencies weren't audited (2). 30+20+8+15+2 = 75.

Hugging Face Inference Endpoints 70

Closed service under clear terms that name Inference Endpoints, with an Apache-2.0 client (20). The security page says payloads and tokens aren't stored and logs are kept 30 days. The privacy policy dates from 28 March 2023 and gives retention as long as necessary, and a data processing agreement requires an Enterprise subscription (20). Instance deprecations are dated to the month in the pricing table and flagged in the provider API, and the TGI maintenance notice is dated. No deprecation policy for the API was found (10). The privacy policy lists 11 subprocessors with countries and the docs and API list deployment regions (18).

Together GPU Clusters 65

Closed service under Together's terms, with Apache-2.0 SDKs, which don't raise the line for a closed API (15). The privacy policy's data table covers GPU clusters, per the 4 November Code Sandbox check, and the billing page states when volumes are deleted after credit runs out, with no retention period for data on deleted clusters (15). The 3.0 breaking change came with a migration guide on the day, and reservations carry dated end-of-term emails, with no notice period for API changes found (8). Regions are listed through the API and US regions appear in examples; subprocessors and data locations for clusters were not established (8). 15+15+8+8 = 46.