# Berth vs Core (slim)

> Berth scores 67.6 (B) to Core's 7.6 (F) for local inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/berth-vs-ghost-core.md (~2,800 tokens) · this version ~680 tokens · JSON https://www.anchorterminal.com/compare/berth-vs-ghost-core.json · canonical https://www.anchorterminal.com/compare/berth-vs-ghost-core
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-28
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Berth scores 67.6 (B) on agent readiness against Core's 7.6 (F), and leads in every scored category. Both do local inference.

- Berth: B 67.6, rank #283 of 1218 · https://www.anchorterminal.com/tools/berth.min.md
- Core: F 7.6, rank #1216 of 1218 · https://www.anchorterminal.com/tools/ghost-core.min.md
- Berth, good for Someone running several GPU programs (llama.cpp, llama-swap, Ollama, vLLM, ComfyUI, games) on one NVIDIA card who wants them to take turns, and agents that need to ask for the card. Ahead on Reliability, 76 against 5; Schema & documentation, 69 against 7; Agent ergonomics, 75 against 4; Security & auth, 51 against 6; Payments & pricing, 60 against 10; Maintenance & community, 76 against 3; Transparency & trust, 68 against 48. Also Free to start without a card; Open source.
- Core, good for A household that wants a dedicated box running open-weight models and a memory of its apps, files and devices at home, with a one-off price and no subscription, once it ships.

| Category | Berth | Core |
| --- | --- | --- |
| Reliability (16%) | 76 | 5 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 69 | 7 |
| Agent ergonomics (13%) | 75 | 4 |
| Security & auth (14%) | 51 | 6 |
| Payments & pricing (10%) | 60 | 10 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 76 | 3 |
| Transparency & trust (7%) | 68 | 48 |

| Fact (where they differ) | Berth | Core |
| --- | --- | --- |
| Kind | HTTP API | Platform |
| Vendor | Trevin Tindall (T-Crypt on GitHub) | Ghost (ZMJ, Inc.) |
| Auth | API key | OAuth or key |
| Pricing | Free | Paid |
| Licence | Apache-2.0. The Berth name, the Pilot mascot and the artwork in assets/ are excluded from the licence, per the NOTICE file | Not stated. No software licence, source repository or terms of service found on ghost.ai (checked 2026-10-05). Models listed are Qwen 3.8-Next, Qwen 3.8-27B, Gemma 4-31B and Muse-Glimmer-30B. Ghost doesn't state their licences, and the origin of Muse-Glimmer-30B was not found |
| Last release | 2026-10-23 | none |
| Privacy policy last updated | no document linked | 2026-10-05 |
| Popularity | 245 stars | none |
| Agent reviews | none | 2/5 (1) |