Modal vs Together GPU Clusters

Modal 70

Status page at status.modal.com (Better Stack) with per-component history and RSS (20). The feed, re-read on 2 November 2026, lists eight incidents from 4 August and an announced control plane maintenance (26 October to 2 November). Slow .spawn() calls for some callers for about 15 minutes (19 August), function latency for 11 minutes (26 August), elevated errors on an endpoint that reads application and volume contents for about 2 hours (4 September), a 14-minute dashboard and sandbox outage (16 September), degraded worker networking for functions and sandboxes (5 October), two incidents on the Kimi K3 shared endpoint only (14 October), and a 2-minute period when 30 to 40 per cent of web function requests failed (19 October). Each hit one product or part of the traffic, or degraded it, and none took a core service down for an hour, so minor only, as modal-sandboxes reads the same feed (20). Web Functions and Function calls are rate limited to 200 a second with a 5-second burst, and plans cap containers at 100 and 5,000 and concurrent GPUs at 10 (Starter) and 50 (Team) (15). Excess requests get a 429, with no Retry-After or backoff guidance for callers; Functions take a documented retry policy with exponential backoff through modal.Retries (5). No SLA on the pricing page (0). Functions, web endpoints and Servers are GA (10). 20+20+15+5+0+10 = 70.

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.

Modal 70

No HTTP API for deploying, so no OpenAPI; the contract is the typed Python SDK with a generated reference (10 of 25). llms.txt at modal.com/llms.txt (10). Guides say when to pick a Function, a web endpoint, a Server or an Endpoint, and when to use memory snapshots (15). Python type hints throughout, but GPU names, regions and plan limits are plain strings (10). Large example gallery; errors are typed Python exceptions without a published HTTP error table (10). Dated SDK release notes (15). 10+10+15+10+10+15 = 70.

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.

Modal 85

Python SDK 1.6.3 on 27 October 2026 per the release notes (30). Six dated Python SDK releases from 4 August (1.5.4 on 12 August, 1.5.5 on 28 August, 1.6.0 on 28 September, 1.6.1 on 3 October, 1.6.2 on 15 October and 1.6.3 on 27 October) (20). The client is open source in modal-labs/modal-client, but its issues and replies can't be read from a clone and github.com answers 403, so responsiveness stays at the 1 October reading, dated release notes and community Slack (10). Python is current, and the JavaScript and Go SDKs (tagged 0.11.1, beta) are in the same repository (15). CodeQL and unit tests on main per the 1 October check, and the Python package supports current runtimes, Python 3.15 since 1.6.2 (10). 30+20+10+15+10 = 85.

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.

Modal 71

Closed service; the Python client is Apache-2.0 (20). Retention is spelled out per product on the security page. Function inputs and outputs up to 7 days, logs 1 day on Starter and 30 on Team, function memory snapshots 30 days, sandbox memory snapshots 7 days, metadata for the account's lifetime, zero retention on inference Endpoints, and volumes and images until you delete them. A DPA sits in the trust centre (25). The 1.1.0 release notes say breaking changes for outstanding deprecations come only in 1.Y.0 releases, and releases give deprecation warnings first (1.6.2 deprecates .update_autoscaler()), with no stated notice period (15). The data residency guide says where each product runs and stores data and which regions can be pinned. The security page says the subprocessor list is in the trust centre at trust.modal.com, which didn't render for us (10). 20+25+15+10 = 70.

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.