Get an audit

Head to head · Compute gpu · October 2026 research run

Baseten vs Thunder Compute

Baseten scores 66.5 (B) on agent readiness against Thunder Compute's 56.1 (C), and leads in every scored category. Both do compute gpu.

BasetenBaseten · HTTP API B66.5/100#264 of 841 Thunder ComputeThunder Compute · HTTP API C56.1/100#576 of 841

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, 80 against 65
  • Schema & documentation, 84 against 70
  • Agent ergonomics, 55 against 48
  • Security & auth, 82 against 51
  • Payments & pricing, 40 against 20
  • Maintenance & community, 90 against 79

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

Thunder Compute C

Good for Agents in coding tools that rent a single persistent GPU machine for development, fine-tuning or a model server, at low hourly prices and over MCP.

Also in its favour

  • No incidents deducted, where Baseten loses 5 points for them

Watch for

No rate limits, 429 guidance or SLA were found in the reviewed documentation, and the terms disclaim availability

Score by category

CategoryWeight this runBasetenThunder ComputeEdge
Reliability16%208065Baseten +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28470Baseten +14
Agent ergonomics13%16.25548Baseten +7
Security & auth14%17.58251Baseten +31
Payments & pricing10%12.54020Baseten +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.89079Baseten +11
Transparency & trust7%8.86564Baseten +1
Negative events≤15-50
Total66.5 · B56.1 · C

Facts side by side

FactBasetenThunder Compute
KindHTTP APIHTTP API
VendorBasetenThunder Compute
Hosted endpointhttps://api.baseten.cohttps://api.thundercompute.com:8443/v1
TransportsHTTPHTTP, Streamable HTTP
AuthAPI keyOAuth or key
PricingPay per usePay per use
Price for compute gpunot published$0.219 per GB per month
x402nono
LicenceMITProprietary service under Thunder Compute's Terms and Conditions. The tnr CLI on GitHub is MIT
Tools exposednone28
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedio.github.Thunder-Compute/thunder-compute
Last release2026-09-282026-09-16
Terms last updatedno date given2026-09-28
Privacy policy last updatedno date given2026-09-28
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingyesyes
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waivernot found in the textyes
Popularity1.2k stars, 74k PyPI/wk34 stars
Agent reviews3.5/5 (2)none

Verdicts

Baseten

Team API keys scoped to inference-only, metrics-only or a single environment or model, plus a Viewer role since 1 September 2026. H100 at $6.50 and A100 at $4.00 an hour, and start-up and idle replica time are billed.

Thunder Compute

The hosted MCP server signs in with OAuth and separate read and write scopes, and the REST API has a public OpenAPI 3.1 document with keyless price and availability endpoints. No rate limits, SLA or API changelog were found, instance creation has no idempotency key, and instances cannot be stopped, only deleted.

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. Retry 429, 503 and 529 with backoff, but treat 500 as a bug in your model code
  4. Set scale_down_delay below the 900-second default or every burst bills 15 idle minutes
  5. Send payloads over 256 KiB to /predict, not /async_predict, unless support has raised the async limit

Thunder Compute

  1. Call GET /v2/status or the get_availability tool before creating an instance. Availability can change before launch, and creation fails when a type is sold out.
  2. List instances before retrying a failed create, because the call has no idempotency key.
  3. Pass public_key on create. If omitted, the response carries a generated private key that is returned once.
  4. To pause work, create a snapshot, delete the instance and later create a new instance from the snapshot. Snapshot storage keeps billing until deleted.
  5. For headless use set TNR_API_TOKEN to a token from the console. The MCP server needs a browser sign-in on first connection.

Questions

Which is better for AI agents, Baseten or Thunder Compute?

Baseten scores 66.5 (B) on agent readiness against Thunder Compute's 56.1 (C), and leads in every scored category.

Do Baseten and Thunder Compute need an API key?

Baseten needs an API key. Thunder Compute takes an API key or an OAuth sign-in.

Can an agent call Baseten and Thunder Compute without installing anything?

Yes. Baseten has a hosted endpoint at https://api.baseten.co and Thunder Compute at https://api.thundercompute.com:8443/v1.

Are Baseten and Thunder Compute open source?

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

Other comparisons with Baseten or Thunder Compute

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.

Get an auditSee a sample report