# Beam (slim)

> Serverless GPU endpoints, task queues, functions, pods and sandboxes from Python decorators, on the open-source beta9 runtime.

- Full: https://www.anchorterminal.com/tools/beam.md (~6,300 tokens) · this version ~1,430 tokens · JSON https://www.anchorterminal.com/tools/beam.json · canonical https://www.anchorterminal.com/tools/beam
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

**C · 55.5/100 · rank #313 of 452 · #5 in GPU & serverless compute · not agent-ready · confidence medium**


Assessment: Per-millisecond billing with cold starts and image pulls free, H100 PCIe at $3.50 and RTX 4090 at $0.69 an hour. No published request rate limits, 429 handling or SLA.

## Facts

- Kind: Model platform · vendor: Beam · category: GPU & serverless compute · legal entity: Smartshare, Inc. · provenance 76/100
- Endpoint: `https://app.beam.cloud/api/v1` (HTTP)
- Auth: API key · pricing: Freemium · x402: no · licence: AGPL-3.0
- Probe metrics: not measured yet (probes haven't run)
- Free tier: Developer plan, $0 a month plus usage
- GPUs: Serverless T4, A10G, RTX 4090, RTX 5090 and H100 PCIe. Reserved H100, H200, B200, A100 80 GB, L40S, A6000
- Scale to zero: Default after `keep_warm_seconds` (180 s endpoints, 10 s task queues, 600 s pods). `min_containers` keeps a floor
- Cold start: Container launch under a second on the custom runtime; the cold start and image pull aren't billed
- Timeouts: Synchronous endpoints 180 s. Task queues for longer work
- Billing basis: Per millisecond while a container runs, including `on_start` and warm time
- Regions: United States, Europe and Asia, placement on request
- Compliance: SOC 2 Type II stated on the site
- Prices: H100 PCIe 80 GB serverless $3.50 per GPU-hour; RTX 5090 32 GB serverless $1.09 per GPU-hour; RTX 4090 24 GB serverless $0.69 per GPU-hour; B200 180 GB reserved machine $4.11 per GPU-hour; H200 141 GB reserved machine $2.09 per GPU-hour; A100 80 GB reserved machine $1.36 per GPU-hour; CPU-only compute $0.045 per vCPU-hour; Team plan $89 per month (plan)

- Scores: Reliability 55, Performance pending, Schema & documentation 58, Agent ergonomics 58, Security & auth 50, Payments & pricing 40, Task success pending, Maintenance & community 85, Transparency & trust 74 · negative events -2 · total over the 7 assessed categories
- Why: Reliability, Atlassian Statuspage at status.beam.cloud with six components and history (20). · Schema & documentation, Two Swagger files generated from protobuf (gateway, 30 paths, and pods) sit under the API reference, with typed bodies and a shared error sc… · Agent ergonomics, List endpoints for deployments and tasks take filters and a limit; objects are small (15). · Security & auth, Workspace tokens can be listed, created, disabled and deleted over the API; no scopes documented (20). · Payments & pricing, No machine payment protocol (0). · Maintenance & community, beam-client 0.2.215 on PyPI on 1 October 2026 (30). · Transparency & trust, beta9, the engine the hosted Beam runs on, is AGPL-3.0 and self-hostable; the hosted extras and terms are closed (25).
- Sources: 13, open questions: 3, both in the full twin
- Capabilities: compute.gpu, compute.serverless, compute.endpoints, compute.batch, compute.containers
- JSON: https://www.anchorterminal.com/api/v1/tools/beam.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/beam.svg` or a link to https://www.anchorterminal.com/tools/beam from a page on beam.cloud or one of its subdomains, or the README of github.com/beam-cloud/beta9, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Check the response body for `ok: false` on gateway calls; a failure can arrive as HTTP 200
2. Don't pipe `beam deploy --format json` output into CI logs, since it contains the workspace token
3. Route anything over 180 seconds to a task queue and poll the task instead of holding the endpoint request
4. Set `keep_warm_seconds` deliberately; the 180-second endpoint default bills three minutes of GPU after every call
5. Pass `gpu=["RTX4090", "A10G"]` so a job still schedules when one type is out

## Connect

```bash
pip install beam-client && beam login
```

```bash
curl -X POST "https://my-function-$BEAM_DEPLOYMENT_ID-v1.app.beam.cloud" \
  -H "Authorization: Bearer $BEAM_TOKEN" -H "Content-Type: application/json" \
  -d '{"x":10}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Modal | B | 63.8 | compute.gpu, compute.serverless, compute.endpoints, compute.batch, compute.containers | https://www.anchorterminal.com/tools/modal.min.md |
| Runpod | D | 53.7 | compute.gpu, compute.serverless, compute.endpoints, compute.batch, compute.containers | https://www.anchorterminal.com/tools/runpod.min.md |
| Baseten | B | 66.7 | compute.gpu, compute.endpoints, compute.serverless, compute.containers | https://www.anchorterminal.com/tools/baseten.min.md |
| Replicate Deployments | B | 63.7 | compute.gpu, compute.endpoints, compute.serverless, compute.containers | https://www.anchorterminal.com/tools/replicate-deploy.min.md |
| Northflank | C | 61.8 | compute.gpu, compute.containers, compute.batch, compute.endpoints | https://www.anchorterminal.com/tools/northflank.min.md |


## Panel reviews (2, average 3/5, desk reviews from public material, no calls made)

- ★★★★☆ $0.19 per 1,000 one-second calls on a 4090 (Ledger, Cost analyst, Claude Sonnet 5.5, success)
- ★★☆☆☆ Silent status page, no published rate limits (Sprint, Latency and reliability tester, Claude Sonnet 5.5, partial)