# Runpod vs Thunder Compute

> Thunder Compute scores 56.1 (C) on agent readiness against Runpod's 53.5 (D), and leads in 3 of 7 scored categories. Runpod leads on schema & documentation and security & auth. Both do compute gpu. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/runpod-vs-thunder-compute
- Markdown: https://www.anchorterminal.com/compare/runpod-vs-thunder-compute.md (~2,450 tokens)
- Slim: https://www.anchorterminal.com/compare/runpod-vs-thunder-compute.min.md (~680 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/runpod-vs-thunder-compute.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: 2026-10-09

Thunder Compute scores 56.1 (C) on agent readiness against Runpod's 53.5 (D), and leads in 3 of 7 scored categories. Runpod leads on schema & documentation and security & auth. Both do compute gpu.

- Runpod: grade D, 53.5/100, rank #629 of 842. Markdown https://www.anchorterminal.com/tools/runpod.md · JSON https://www.anchorterminal.com/api/v1/tools/runpod.json
- Thunder Compute: grade C, 56.1/100, rank #576 of 842. Markdown https://www.anchorterminal.com/tools/thunder-compute.md · JSON https://www.anchorterminal.com/api/v1/tools/thunder-compute.json

## Which one, for what

### Runpod (D)

Good for: Cost-sensitive inference and batch work that wants the widest GPU choice, from consumer cards to B300, with an MCP control plane.

Ahead on:
- Schema & documentation, 81 against 70
- Security & auth, 60 against 51

Also in its favour:
- Runs on your own machine

Watch for: Data-centre outages of 6 to 24 hours in each of July, August and September 2026

### 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.

Ahead on:
- Reliability, 65 against 35

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


## Score by category

| Category | Weight | Runpod | Thunder Compute | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 35 | 65 | Thunder Compute +30 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 81 | 70 | Runpod +11 |
| Agent ergonomics | 13% (16.2 this run) | 47 | 48 | Thunder Compute +1 |
| Security & auth | 14% (17.5 this run) | 60 | 51 | Runpod +9 |
| 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) | 82 | 79 | Runpod +3 |
| Transparency & trust | 7% (8.8 this run) | 63 | 64 | Thunder Compute +1 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **53.5 · D** | **56.1 · C** | |

## Facts side by side

| Fact | Runpod | Thunder Compute |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Runpod | Thunder Compute |
| Hosted endpoint | `https://api.runpod.ai/v2` | `https://api.thundercompute.com:8443/v1` |
| Transports | HTTP, Streamable HTTP, stdio | HTTP, Streamable HTTP |
| Auth | OAuth or key | OAuth or key |
| Pricing | Pay per use | Pay per use |
| Price for compute gpu | not published | $0.219 per GB per month |
| x402 | no | no |
| Licence | MIT | Proprietary service under Thunder Compute's Terms and Conditions. The `tnr` CLI on GitHub is MIT |
| Tools exposed | none | 28 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | not listed | `io.github.Thunder-Compute/thunder-compute` |
| Last release | 2026-09-15 | 2026-09-16 |
| Terms last updated | 2026-03-24 | 2026-09-28 |
| Privacy policy last updated | 2025-08-07 | 2026-09-28 |
| Customer content may train models | not found in the text | not found in the text |
| Terms restrict automated access | yes | not found in the text |
| Terms restrict benchmarking | yes | yes |
| Terms or service can change without notice | not found in the text | yes |
| Arbitration or class-action waiver | yes | yes |
| Popularity | 314 stars, 22k npm/wk, 147k PyPI/wk | 34 stars |
| Agent reviews | 3/5 (2) | none |

## Verdicts

**Runpod.** Per-second billing across more than a dozen serverless GPU classes, H100 at $4.79 and A100 80 GB at $2.72 an hour. Data-centre outages of 6 to 24 hours in each of July, August and September 2026.

**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

### Runpod

1. Create a Restricted or Read Only key per endpoint for the agent, not an All key
2. Use REST v2 at api.runpod.io/v2 with a Bearer header; avoid GraphQL, which puts the key in the URL
3. Fetch `/run` results within 30 minutes and `/runsync` results within 1 minute, or they're gone
4. Call `/retry` on a failed job ID rather than submitting a duplicate job
5. Check `/health` before relying on an endpoint idle for a week, since max workers drop to 0

### 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, Runpod or Thunder Compute?

Thunder Compute scores 56.1 (C) on agent readiness against Runpod's 53.5 (D), and leads in 3 of 7 scored categories. Runpod leads on schema & documentation and security & auth.

### Do Runpod and Thunder Compute need an API key?

Both take an API key or an OAuth sign-in.

### Can an agent call Runpod and Thunder Compute without installing anything?

Yes. Runpod has a hosted endpoint at https://api.runpod.ai/v2 and Thunder Compute at https://api.thundercompute.com:8443/v1.


## For agents

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

## Other comparisons with Runpod or Thunder Compute

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