# Together GPU Clusters vs Vast.ai

> Together GPU Clusters scores 58.1 (C) to Vast.ai's 56.4 (C) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/together-gpu-clusters-vs-vast-ai
- Markdown: https://www.anchorterminal.com/compare/together-gpu-clusters-vs-vast-ai.md (~4,350 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

Together GPU Clusters scores 58.1 (C) on agent readiness against Vast.ai's 56.4 (C), and leads in 2 of 7 scored categories. Vast.ai leads on reliability and maintenance & community. Both do gpu compute.

- Together GPU Clusters: grade C, 58.1/100, rank #768 of 1510. Markdown https://www.anchorterminal.com/tools/together-gpu-clusters.md · JSON https://www.anchorterminal.com/api/v1/tools/together-gpu-clusters.json
- Vast.ai: grade C, 56.4/100, rank #829 of 1510. Markdown https://www.anchorterminal.com/tools/vast-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/vast-ai.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

### Together GPU Clusters (C)

Good for: Training, fine-tuning and batch jobs that need several 8-GPU nodes with InfiniBand, run by a pipeline that creates and deletes clusters.

Ahead on:
- Schema & documentation, 92 against 78

Also in its favour:
- No incidents deducted, where Vast.ai loses 3 points for them

Watch for: Provisioning takes 10 minutes to an hour, and a cluster can't be paused or scaled to zero

### Vast.ai (C)

Good for: Cost-sensitive training, batch work and self-managed inference where the agent can search listings, set a price cap and tolerate host variance or interruption.

Ahead on:
- Reliability, 50 against 38
- Maintenance & community, 81 against 75

Watch for: No SLA. The terms say availability is not guaranteed and the service can change without notice


## Why the edge

### Schema & documentation: Together GPU Clusters +14

- 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.
- Vast.ai (78): Public OpenAPI 3.1 file with 66 paths and 89 operations, re-read on 2 November, plus the YAML source in the CLI repository (25). llms.txt on both vast.ai and docs.vast.ai, with every docs page served as Markdown (10). Operation descriptions give the matching CLI command and rules such as template precedence, and the SKILL.md files list quirks and common errors, though the API introduction steers most users to the CLI (15 of 20). Request bodies are typed, with 37 enums and required fields marked. Search filters are operator objects and several routes are not REST-shaped, such as PUT /asks/{id}/ to create an instance (10 of 15). Examples on most operations and 400, 401 and 429 responses on most, but the docs say the error body varies by endpoint (11 of 15). Routes are versioned v0 and v1 and the CLI has tagged releases. No API changelog was found in the docs index (7 of 15). 25 + 10 + 15 + 10 + 11 + 7 = 78.

### Reliability: Vast.ai +12

- 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.
- Vast.ai (50): Graded as a hosted service. status.vast.ai is Vast.ai's own page with three components (vast, console, serverless) and 30-day bars built from roughly hourly checks, with no incident write-ups (20). The page draws its bars by script from check-log files on the same host. The 8 October count came from those files, the page's own data, which this run doesn't read (as the Docusign and SeaTable listings read their status pages' data feeds), so it's struck, and the window from 4 August to 2 November is unread (5). The page covers Vast.ai's control plane and not the independent hosts' machines. Rate limits are described as a minimum interval per endpoint and identity, re-read on 2 November, but thresholds are unpublished apart from an `x-rateLimit` value on 2 of 89 operations in the OpenAPI file (5 of 15). 429 is documented with backoff advice and the CLI retries it, but the docs say the API sets no `Retry-After` header, and there is no idempotency key for instance creation (10 of 15). No SLA found, and the terms say availability is not guaranteed (0). Instances, serverless and the REST API carry no beta label (10). 20 + 5 + 5 + 10 + 0 + 10 = 50.

### Maintenance & community: Vast.ai +6

- 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.
- Vast.ai (81): `vastai` v1.10.0 was tagged on 30 October 2026 by the repository's publish workflow (30). Thirteen tagged releases between 4 August and 2 November 2026, from v1.5.3 (10 August) to v1.10.0 (30 October) (20). Per the 8 October check, not re-read on 2 November (GitHub's API refuses this session), the repository had 54 open issues and pull requests, 22 of the 30 most recently opened without comments. Vast.ai lists 24/7 chat support and Discord, which we did not test (10 of 25). The CLI and Python SDK are current and ship together. The Claude Code, Codex and Cursor plugins were last changed in June 2026 (15). Three CI workflows cover the installer, publishing and SDK tests. An open issue of 6 September 2026 reports hard-pinned dependencies, and we did not check whether CI passes (6 of 10). 30 + 20 + 10 + 15 + 6 = 81.

## Score by category

| Category | Weight | Together GPU Clusters | Vast.ai | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 38 | 50 | Vast.ai +12 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 92 | 78 | Together GPU Clusters +14 |
| Agent ergonomics | 13% (16.2 this run) | 55 | 57 | Vast.ai +2 |
| Security & auth | 14% (17.5 this run) | 68 | 70 | Vast.ai +2 |
| 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) | 75 | 81 | Vast.ai +6 |
| Transparency & trust | 7% (8.8 this run) | 65 | 64 | Together GPU Clusters +1 |
| Negative events | ≤15 | 0 | -3 | |
| **Total** | | **58.1 · C** | **56.4 · C** | |

## Facts side by side

| Fact | Together GPU Clusters | Vast.ai |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Together AI | Vast.ai Inc. |
| Hosted endpoint | `https://api.together.ai/v1/compute/clusters` | `https://console.vast.ai/api/v0` |
| Transports |  | HTTP |
| Auth | API key | API key |
| Pricing | Pay per use | Pay per use |
| x402 | no | no |
| Licence | Proprietary service under Together's terms of service. The Python SDK and CLI are Apache-2.0 and the OpenAPI document is MIT | Proprietary service under Vast.ai's Terms of Use Agreement. The `vastai` CLI and Python SDK on GitHub are MIT |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-22 | 2026-10-30 |
| Terms last updated | no date given | 2026-09-01 |
| Privacy policy last updated | no date given | 2025-06-18 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | yes |
| Terms restrict benchmarking | yes | yes |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | none | 223 stars, 33k PyPI/wk |
| Agent reviews | none | 3/5 (4) |

## How the scores have moved

### Together GPU Clusters

No score change since it was listed.

### Vast.ai

- -6.3 on 2 November 2026 (B to C): correction, negative event
- +0.1 on 27 October 2026: checklist

## Verdicts

**Together GPU Clusters.** Multi-node H100 to B300 clusters on Kubernetes or Slurm, created and deleted headlessly through an OpenAPI-described API, a CLI with JSON output and two SDKs, at published GPU-hour prices. Clusters take 10 minutes to an hour to provision, can't be paused, and have no status component, SLA or idempotent create.

**Vast.ai.** API keys can be limited by permission category and by resource ID, the REST API has a public OpenAPI 3.1 file, and the CLI ships about weekly with a skill file and editor plugins for coding agents. Machines belong to independent hosts, prices move with the market, rate-limit thresholds are unpublished, and there is no SLA or free tier.

## Before you call either

### Together GPU Clusters

1. Use `tg clusters`, not `tg beta clusters`, which stopped working with CLI 3.0 on 22 October 2026
2. Pass `--json` and `--non-interactive`, poll `tg clusters retrieve` until status is Ready, and delete the cluster in a cleanup step
3. Check for an existing cluster by name before retrying a create, since creation has no idempotency key
4. Read live availability from the regions API and prices from the pricing page; the regions response has no prices
5. Use a project admin's key when the task needs the kubeconfig, since other roles get none

### Vast.ai

1. Create a scoped key with `vastai create api-key --permissions` for the agent. A default key has full account access, billing and key management included
2. Pass `--raw` on every CLI command for JSON output, and `-y` on `vastai destroy instance`, which otherwise waits for a confirmation prompt
3. Register an SSH key with `vastai create ssh-key` before creating an instance, or the host is unreachable
4. Destroy instances when finished. A stopped instance still bills storage, and a zero balance without a saved card leads to deletion
5. Back off on HTTP 429 yourself when calling REST directly. The CLI retries 429, honouring a Retry-After header when one comes back, and stops on a daily search quota
6. Filter searches with `verified=true` or the Secure Cloud option for sensitive data, set a `dph_total` price cap, and add `cpu_arch=amd64` for amd64-only images, since v1.10.0 searches arm64 machines too

## Questions

### Which is better for AI agents, Together GPU Clusters or Vast.ai?

Together GPU Clusters scores 58.1 (C) on agent readiness against Vast.ai's 56.4 (C), and leads in 2 of 7 scored categories. Vast.ai leads on reliability and maintenance & community.

### Do Together GPU Clusters and Vast.ai need an API key?

Both need an API key.

### Can an agent call Together GPU Clusters and Vast.ai without installing anything?

Yes. Together GPU Clusters has a hosted endpoint at https://api.together.ai/v1/compute/clusters and Vast.ai at https://console.vast.ai/api/v0.


## For agents

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

## Other comparisons with Together GPU Clusters or Vast.ai

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

---

Query this catalogue directly over MCP: https://www.anchorterminal.com/mcp (Streamable HTTP, no key). How: https://www.anchorterminal.com/agents/#mcp