# CoreWeave vs Vast.ai

> Vast.ai scores 62.6 (B) on agent readiness against CoreWeave's 61.5 (C), and leads in 2 of 7 scored categories. CoreWeave leads on transparency & trust. Both do compute gpu. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/coreweave-vs-vast-ai
- Markdown: https://www.anchorterminal.com/compare/coreweave-vs-vast-ai.md (~2,250 tokens)
- Slim: https://www.anchorterminal.com/compare/coreweave-vs-vast-ai.min.md (~630 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/coreweave-vs-vast-ai.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-08

Vast.ai scores 62.6 (B) on agent readiness against CoreWeave's 61.5 (C), and leads in 2 of 7 scored categories. CoreWeave leads on transparency & trust. Both do compute gpu.

- CoreWeave: grade C, 61.5/100, rank #363 of 722. Markdown https://www.anchorterminal.com/tools/coreweave.md · JSON https://www.anchorterminal.com/api/v1/tools/coreweave.json
- Vast.ai: grade B, 62.6/100, rank #331 of 722. Markdown https://www.anchorterminal.com/tools/vast-ai.md · JSON https://www.anchorterminal.com/api/v1/tools/vast-ai.json

## Which one, for what

### CoreWeave (C)

Good for: Teams that already run Kubernetes and need whole multi-GPU nodes or clusters for training and dedicated inference, with a contract and IAM.

Ahead on:
- Transparency & trust, 77 against 62

Watch for: No self-serve route. CoreWeave's sales team approves an organisation and emails the activation link before a token can be created

### Vast.ai (B)

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, 65 against 50

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


## Score by category

| Category | Weight | CoreWeave | Vast.ai | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 50 | 65 | Vast.ai +15 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 79 | 78 | CoreWeave +1 |
| Agent ergonomics | 13% (16.2 this run) | 58 | 57 | CoreWeave +1 |
| Security & auth | 14% (17.5 this run) | 74 | 72 | CoreWeave +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) | 80 | 81 | Vast.ai +1 |
| Transparency & trust | 7% (8.8 this run) | 77 | 62 | CoreWeave +15 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **61.5 · C** | **62.6 · B** | |

## Facts side by side

| Fact | CoreWeave | Vast.ai |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | CoreWeave, Inc. | Vast.ai Inc. |
| Hosted endpoint | `https://api.coreweave.com` | `https://console.vast.ai/api/v0` |
| Transports | HTTP | HTTP |
| Auth | Token | API key |
| Pricing | Pay per use | Pay per use |
| x402 | no | no |
| Licence | Proprietary service under CoreWeave's Terms of Service. The Terraform provider on GitHub is MIT | Proprietary service under Vast.ai's Terms of Use Agreement. The `vastai` CLI and Python SDK on GitHub are MIT |
| Tools exposed | 38 | none |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| Last release | 2026-10-02 | 2026-10-02 |
| Terms last updated | 2022-06-30 | 2026-09-01 |
| Privacy policy last updated | 2026-02-24 | 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 | not found in the text | yes |
| Terms or service can change without notice | yes | yes |
| Arbitration or class-action waiver | not found in the text | yes |
| Popularity | none | 223 stars, 33k PyPI/wk |

## Verdicts

**CoreWeave.** Per-hour prices for 8-GPU H100, H200 and B200 nodes are public, the docs ship as Markdown with llms.txt and embedded OpenAPI specs, and IAM has read-only roles per service. An organisation must be approved by CoreWeave's sales team before any token exists, and no request rate limits were found in the reviewed documentation.

**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 weekly with a skill file 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

### CoreWeave

1. Create an API access token at console.coreweave.com/tokens with an expiry and send it as `Authorization: Bearer` to https://api.coreweave.com
2. Add GPUs by applying a NodePool resource (`compute.coreweave.com/v1alpha1`) to a CKS cluster with `instanceType` and `targetNodes`. `instanceType` can't be changed afterwards
3. Set `targetNodes` to 0 or delete the Node Pool when a job ends. Nodes are whole 8-GPU machines billed by the hour
4. Never pass `dry_run` to the MCP tool `coreweave_kubectl_apply` expecting a preview. The reference says the parameter is ignored and the manifest is applied
5. Use a separate Forge API key and https://api.inference.wandb.ai/v1 for Serverless Inference. A CoreWeave API access token doesn't work there

### 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 three times from 0.15 seconds
6. Filter searches with `verified=true` or the Secure Cloud option for sensitive data, and set a `dph_total` price cap

## Questions

### Which is better for AI agents, CoreWeave or Vast.ai?

Vast.ai scores 62.6 (B) on agent readiness against CoreWeave's 61.5 (C), and leads in 2 of 7 scored categories. CoreWeave leads on transparency & trust.

### Do CoreWeave and Vast.ai need an API key?

CoreWeave needs an access token. Vast.ai needs an API key.

### Can an agent call CoreWeave and Vast.ai without installing anything?

Yes. CoreWeave has a hosted endpoint at https://api.coreweave.com and Vast.ai at https://console.vast.ai/api/v0.


## For agents

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

## Other comparisons with CoreWeave or Vast.ai

- [Baseten vs CoreWeave](https://www.anchorterminal.com/compare/baseten-vs-coreweave.md)
- [Baseten vs Vast.ai](https://www.anchorterminal.com/compare/baseten-vs-vast-ai.md)
- [Beam vs CoreWeave](https://www.anchorterminal.com/compare/beam-vs-coreweave.md)
- [Beam vs Vast.ai](https://www.anchorterminal.com/compare/beam-vs-vast-ai.md)
- [Cerebrium vs CoreWeave](https://www.anchorterminal.com/compare/cerebrium-vs-coreweave.md)
- [Cerebrium vs Vast.ai](https://www.anchorterminal.com/compare/cerebrium-vs-vast-ai.md)
- [CoreWeave vs Koyeb](https://www.anchorterminal.com/compare/coreweave-vs-koyeb.md)
- [CoreWeave vs Lambda Cloud](https://www.anchorterminal.com/compare/coreweave-vs-lambda.md)
- [CoreWeave vs Modal](https://www.anchorterminal.com/compare/coreweave-vs-modal.md)
- [CoreWeave vs Northflank](https://www.anchorterminal.com/compare/coreweave-vs-northflank.md)
- [CoreWeave vs Replicate Deployments](https://www.anchorterminal.com/compare/coreweave-vs-replicate-deploy.md)
- [CoreWeave vs Runpod](https://www.anchorterminal.com/compare/coreweave-vs-runpod.md)
- [Koyeb vs Vast.ai](https://www.anchorterminal.com/compare/koyeb-vs-vast-ai.md)
- [Lambda Cloud vs Vast.ai](https://www.anchorterminal.com/compare/lambda-vs-vast-ai.md)
- [Modal vs Vast.ai](https://www.anchorterminal.com/compare/modal-vs-vast-ai.md)
- [Northflank vs Vast.ai](https://www.anchorterminal.com/compare/northflank-vs-vast-ai.md)
- [Replicate Deployments vs Vast.ai](https://www.anchorterminal.com/compare/replicate-deploy-vs-vast-ai.md)
- [Runpod vs Vast.ai](https://www.anchorterminal.com/compare/runpod-vs-vast-ai.md)