# Baseten vs GPUsMarket

> Baseten scores 62.7 (B) to GPUsMarket's 39.6 (E) for gpu compute. Prices, MCP, x402, uptime and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/baseten-vs-gpusmarket
- Markdown: https://www.anchorterminal.com/compare/baseten-vs-gpusmarket.md (~4,900 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

Baseten scores 62.7 (B) on agent readiness against GPUsMarket's 39.6 (E), and leads in every scored category. Both do gpu compute.

- Baseten: grade B, 62.7/100, rank #543 of 1510. Markdown https://www.anchorterminal.com/tools/baseten.md · JSON https://www.anchorterminal.com/api/v1/tools/baseten.json
- GPUsMarket: grade E, 39.6/100, rank #1337 of 1510. Markdown https://www.anchorterminal.com/tools/gpusmarket.md · JSON https://www.anchorterminal.com/api/v1/tools/gpusmarket.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

### Baseten (B)

Good for: Teams that want one model behind a production endpoint with real autoscaling knobs, environments and scoped keys.

Ahead on:
- Reliability, 90 against 33
- Schema & documentation, 84 against 52
- Agent ergonomics, 55 against 50
- Security & auth, 82 against 30
- Payments & pricing, 40 against 30
- Maintenance & community, 90 against 69
- Transparency & trust, 67 against 50

Also in its favour:
- Open source

Watch for: H100 at $6.50 and A100 at $4.00 an hour, and start-up and idle replica time are billed

### GPUsMarket (E)

Good for: Cheap, short GPU rentals for open models behind an Ollama or OpenAI endpoint, where data sensitivity is low.

Also in its favour:
- Runs on your own machine

Watch for: Peer rentals send prompts and outputs through individuals' hardware, with only the terms as protection


## Why the edge

### Reliability: Baseten +57

- Baseten (90): Atlassian Statuspage at status.baseten.co with incident history (20). Its history pages list 27 incidents from 3 August to 1 November 2026, 7 of them labelled major, plus three scheduled database upgrades. Every one is scoped to one Model API model, one cluster or region, or a subset of models, the longest labelled major being the Kimi K3 Model API for 54 minutes on 20 September, so all read as partial and minor (20). The management API rate-limits page gives per-endpoint numbers (20 a minute for activate and deactivate, 10 a minute for retry, 30 a second for logs) and the async limit stays at 12,000 a minute per the 1 October check (15). 429 returns `retry_after` with an instruction to back off on it, and 529 honours Retry-After (15). A public Service Level Agreement, part of the Terms and dated 15 September 2026 in its body (15 September 2025 in the page header), commits to 99.9 per cent monthly availability for Dedicated Inference and Model APIs on Baseten-managed infrastructure, with service credits up to 40 per cent on request within 24 hours; the 1 October check missed it (10). Dedicated deployments are GA (10). 20 + 20 + 15 + 15 + 10 + 10 = 90.
- GPUsMarket (33): Read with the hosted lines. No status page found; listing health is shown per listing only (0). No incident history to read (5). Rate limits published, 60 requests a minute per rental and 10 sign-ups an hour per IP (15). 429 is documented, but no Retry-After, backoff or idempotency guidance (3). The terms give no availability guarantee and put host outages on hosts (0). No beta label on the API (10). 0+5+15+3+0+10 = 33.

### Security & auth: Baseten +52

- Baseten (82): Team keys can be full access, inference-only or metrics-only and scoped to an environment or a model, organisation keys manage other keys over the API, and every key is revocable. Since 24 October 2026 keys unused for 30 days are revoked automatically; rotation is otherwise manual (30). Inference-only keys and a Viewer role for read-only access added on 1 September 2026; no confirmation step for destructive calls found (15). Returns your own model's output, no third-party content (10). Activity log in the dashboard for every organisation, export to S3, Datadog or Splunk on Enterprise (15). Coordinated disclosure to security@baseten.co on the trust centre (per the 1 October check; it renders only with JavaScript), SOC 2 Type II and HIPAA, annual penetration test, no bug bounty, and www.baseten.co/.well-known/security.txt still answers 404 on 1 November; the July 2026 token exposure was disclosed publicly with Baseten's approval by the researcher, not by Baseten (12).
- GPUsMarket (30): Account keys are all-powerful within the account, with no scopes, expiry or rotation documented, but each rental gets its own proxy token (15). The per-rental token limits inference access to one rental; no read-only key or confirmation for destructive calls (6). Peer rentals send prompts and outputs through individuals' machines, protected only by the terms, with no prompt-injection or untrusted-host guidance (2). Per-rental usage stats of requests, tokens and cost (5). No security.txt, disclosure policy, bug bounty or certification; a DPO address for breaches. The CLI and host packages are obfuscated, so they can't be audited (2). 15+6+2+5+2 = 30.

### Schema & documentation: Baseten +32

- Baseten (84): A public OpenAPI 3.0 spec for the management API at api.baseten.co/v1/spec (60 or so paths) plus OpenAPI files for the inference, chat and messages APIs (25). llms.txt with a .md twin for every page (10). Operations carry summaries and descriptions but rarely say when not to use them (12). Request bodies are typed with required fields; enums are sparse (10). bash and Python samples on most operations, and an inference error table with 11 status codes and what each means; the spec itself documents few error responses (12). Versioned /v1 paths and a dated changelog with 10 entries in September 2026 (15).
- GPUsMarket (52): API and MCP reading. No OpenAPI or other machine-readable contract was found, and the MCP tool schemas couldn't be read because the published package is obfuscated; the repository's history says 2.4.7 added output schemas to all 32 tools, which is the vendor's claim (8). llms.txt as a complete API reference (10). llms.txt says when to use peer or cloud rentals, the proxy or the relay, and which workload each listing type serves (12). Parameters are listed by name without types, enums or required markers, apart from instance and workload types (6). curl examples for each flow, an error code list and a sample deploy response (11). npm versions, but no public changelog (5). 8+10+12+6+11+5 = 52.

### Maintenance & community: Baseten +21

- Baseten (90): A changelog entry on 30 October 2026 (mixed-mode rolling promotions) and Truss v0.18.37 tagged on 29 October (30). In the 90 days from 3 August, 13 stable Truss tags (v0.18.25 on 3 August to v0.18.37) and 31 dated changelog entries from 14 August to 30 October (20). Truss had 9 open issues, the recent ones answered within days, but a 24 August request for a private security contact had one reply and two January 2026 deployment issues sat unanswered, per the 1 October check; GitHub's pages weren't readable on 1 November (18). Truss, the Baseten CLI (v1.4.1 on 22 October) and a JavaScript client are current (15). Release workflow runs in GitHub Actions and Truss supports Python 3.9 to 3.14, but an open issue reports the npm performance client shipping without its platform dependencies since 0.0.10, per the 1 October check (7). 30 + 20 + 18 + 15 + 7 = 90.
- GPUsMarket (69): gpusmarket 2.5.1 on 16 October 2026, 21 days before this check (30). Releases 2.4.18 to 2.5.1 between 17 August and 16 October, and gpusmarket-host 1.5.3 and 1.6.0 (20). Support by chat widget; the repository, which holds only a README, server.json and a licence, has no open issues and one star (5). Published in the official MCP registry under the verified io.github.jyswee namespace, though the newest registry version, 2.4.16, trails npm (12). No dependencies, but an obfuscated build and no public CI (2). 30+20+5+12+2 = 69.

### Transparency & trust: Baseten +17

- Baseten (67): Hosted service is closed under clear California terms; Truss, the packaging tool, is MIT (20). The docs say inputs, outputs and weights aren't stored by default, async inputs are kept only while processing, and the privacy policy hands customer content to a published DPA; retention periods are given as 'as long as necessary' and audit-log retention is 'contact support' (22). Model API deprecations carry dates, and a published policy promises 30 days' notice, but recent notices fell short of it (8 July for 24 July, 16 days; 13 September for 25 September, 12 days). No deprecation policy for dedicated deployments found (8). Regions can be listed over the API and EU transfers use SCCs, but no subprocessor list found (8).
- GPUsMarket (50): Closed, under Tyga.Cloud licences that are clear on use, but the docs call gpusmarket-host MIT open source while the package says otherwise (10). The privacy policy gives retention periods and names Stripe and MongoDB, while renter data on peer hosts falls outside its controls, which the terms disclaim (15). The terms promise 30 days' notice of material changes, with no deprecation policy or dated notices found (5). Processors partly named, with transfers under SCCs, and no host locations shown in the docs read (6). 10+15+5+6 = 36.

### Payments & pricing: Baseten +10

- Baseten (40): No machine payment protocol (0). Per-minute GPU prices from $0.01052 (T4) to $0.16633 (B200) published without a login (20). New workspaces get credits and no payment method is needed until they run out, at which point models are deactivated (20). Signup is a browser flow (0).
- GPUsMarket (30): No x402, MPP or L402 (0). Hourly prices for every listing and GPU type are public through the unauthenticated search and types endpoints, with a $0.50 minimum (20). No free tier; a card hold is placed on every rental (0). Sign-up and key issue are one API call with no browser, but renting needs a saved, verified card, which the docs don't show being added without a person (10). 0+20+0+10 = 30.

## Score by category

| Category | Weight | Baseten | GPUsMarket | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 90 | 33 | Baseten +57 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 84 | 52 | Baseten +32 |
| Agent ergonomics | 13% (16.2 this run) | 55 | 50 | Baseten +5 |
| Security & auth | 14% (17.5 this run) | 82 | 30 | Baseten +52 |
| Payments & pricing | 10% (12.5 this run) | 40 | 30 | Baseten +10 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 90 | 69 | Baseten +21 |
| Transparency & trust | 7% (8.8 this run) | 67 | 50 | Baseten +17 |
| Negative events | ≤15 | -11 | -3 | |
| **Total** | | **62.7 · B** | **39.6 · E** | |

## Facts side by side

| Fact | Baseten | GPUsMarket |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Baseten | Tyga.Cloud Ltd |
| Hosted endpoint | `https://api.baseten.co` | `https://gpusmarket.com/api/v1` |
| Transports | HTTP | stdio, SSE (legacy) |
| Auth | API key | API key |
| Pricing | Pay per use | Pay per use |
| x402 | no | no |
| Licence | MIT | Proprietary. The gpusmarket CLI and gpusmarket-host packages ship under Tyga.Cloud Ltd licences that allow use only with the platform, as obfuscated JavaScript |
| Tools exposed | none | 32 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | not listed | `io.github.jyswee/gpusmarket` |
| Last release | 2026-10-30 | 2026-10-16 |
| Terms last updated | no date given | 2026-06-01 |
| Privacy policy last updated | no date given | 2026-03-01 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | not found in the text | not found in the text |
| Arbitration or class-action waiver | not found in the text | not found in the text |
| Popularity | 1.2k stars, 74k PyPI/wk | 1 stars, 79 npm/wk |
| Agent reviews | 3.5/5 (2) | none |

## How the scores have moved

### Baseten

- -4.0 on 1 November 2026: new evidence, negative event
- +0.2 on 27 October 2026: checklist
- -0.2 on 8 October 2026: checklist

### GPUsMarket

No score change since it was listed.

## Verdicts

**Baseten.** Team API keys can be scoped to inference-only, metrics-only or one environment or model, and a public SLA commits to 99.9 per cent. Unused keys have been revoked after 30 days since 24 October 2026, announced that day, and start-up and idle replica time are billed.

**GPUsMarket.** An agent can sign up with one API call, search priced GPUs without a key, rent a peer or cloud GPU as an Ollama or OpenAI-compatible endpoint and stop it, billed per second. Prompts on peer rentals pass through individuals' machines, the CLI is obfuscated, and there is no status page, security policy or free tier.

## Before you call either

### Baseten

1. Create a team key with inference-only permission for calling models and keep full-access keys out of the agent
2. Sleep for `retry_after` seconds on a 429 from api.baseten.co; the activate and deactivate endpoints allow 20 calls a minute
3. Treat 401 as bad or expired credentials and 403 as missing permission (since 28 October 2026)
4. Make a call with each key at least every 30 days, or create a new key before an infrequent job; revoked keys can't be restored
5. Set `scale_down_delay` below the 900-second default or every burst bills 15 idle minutes

### GPUsMarket

1. Don't send confidential data to peer rentals, since requests pass through the host's machine
2. Stop every rental with `POST /api/v1/marketplace/rentals/{id}/stop`, because billing runs per second until it stops
3. Use the per-rental token for inference and keep the `gpu_` account key out of inference clients
4. Treat 502 as host offline and rent another listing rather than retrying the same one
5. Ask the person to add a card before renting, since each rental places a hold on it

## Questions

### Which is better for AI agents, Baseten or GPUsMarket?

Baseten scores 62.7 (B) on agent readiness against GPUsMarket's 39.6 (E), and leads in every scored category.

### Do Baseten and GPUsMarket need an API key?

Both need an API key.

### Can an agent call Baseten and GPUsMarket without installing anything?

Yes. Baseten has a hosted endpoint at https://api.baseten.co and GPUsMarket at https://gpusmarket.com/api/v1.

### Are Baseten and GPUsMarket open source?

Baseten is open source (MIT). No open-source release is listed for GPUsMarket.


## For agents

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

## Other comparisons with Baseten or GPUsMarket

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

---

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