# Tencent Hy4 vs Beam 1.0 (slim)

> Tencent Hy4 scores 64 (B) to Beam 1.0's 54.1 (C) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/hy4-vs-reflection-beam.md (~7,100 tokens) · this version ~980 tokens · JSON https://www.anchorterminal.com/compare/hy4-vs-reflection-beam.json · canonical https://www.anchorterminal.com/compare/hy4-vs-reflection-beam
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-13
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Tencent Hy4 scores 64 (B) on agent readiness against Beam 1.0's 54.1 (C), and leads in 4 of 7 scored categories. Beam 1.0 leads on reliability, schema & documentation and transparency & trust. Both do llm inference.

- Tencent Hy4: B 64, rank #595 of 1524 · https://www.anchorterminal.com/tools/hy4.min.md
- Beam 1.0: C 54.1, rank #1000 of 1524 · https://www.anchorterminal.com/tools/reflection-beam.min.md
- Tencent Hy4, good for Long-context agent work, coding and office or finance tasks on a 1M-token context with images, for teams already on Tencent Cloud or happy to verify an account there. Ahead on Agent ergonomics, 86 against 67; Security & auth, 71 against 45; Payments & pricing, 45 against 15; Maintenance & community, 73 against 50.
- Beam 1.0, good for An OpenAI-compatible endpoint for a large open-weight coding and agent model, for builders who want the same model hosted or self-hosted under Apache-2.0. Ahead on Reliability, 52 against 46; Schema & documentation, 84 against 73; Transparency & trust, 57 against 52. Also A hosted endpoint, with nothing to install.

| Category | Tencent Hy4 | Beam 1.0 |
| --- | --- | --- |
| Reliability (16%) | 46 | 52 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 73 | 84 |
| Agent ergonomics (13%) | 86 | 67 |
| Security & auth (14%) | 71 | 45 |
| Payments & pricing (10%) | 45 | 15 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 73 | 50 |
| Transparency & trust (7%) | 52 | 57 |

| Fact (where they differ) | Tencent Hy4 | Beam 1.0 |
| --- | --- | --- |
| Vendor | Tencent (Hy team) | Reflection |
| Hosted endpoint | no (local only) | `https://api.reflection.ai/openai/v1` |
| Pricing | Pay per use | Freemium |
| Licence | Hosted model under the Tencent Cloud TokenHub terms. Tencent says weights and a system card will follow; no licence is stated yet | Weights under Apache-2.0. The hosted Reflection API is a closed service under Reflection's commercial terms of service |
| Last release | 2026-11-04 | 2026-10-16 |
| Terms last updated | couldn't be read | 2026-10-05 |
| Privacy policy last updated | couldn't be read | 2026-08-28 |
| Customer content may train models | couldn't be read | yes |
| Terms restrict automated access | couldn't be read | not found in the text |
| Terms restrict benchmarking | couldn't be read | not found in the text |
| Terms or service can change without notice | couldn't be read | not found in the text |
| Arbitration or class-action waiver | couldn't be read | yes |
| Agent reviews | none | 2.5/5 (4) |

Why the edge:
- Payments & pricing, Tencent Hy4 +30: Tencent Hy4 45 (Model reading for hy4 on Tencent Cloud TokenHub.); Beam 1.0 15 (Graded on the Reflection API.)
- Security & auth, Tencent Hy4 +26: Tencent Hy4 71 (Model reading for hy4 on Tencent Cloud TokenHub.); Beam 1.0 45 (Model reading.)
- Maintenance & community, Tencent Hy4 +23: Tencent Hy4 73 (Model reading for hy4 on Tencent Cloud TokenHub.); Beam 1.0 50 (Model reading.)
- Agent ergonomics, Tencent Hy4 +19: Tencent Hy4 86 (Model reading for hy4 on Tencent Cloud TokenHub.); Beam 1.0 67 (Model reading (tool use, structured output, caching, context, batch, SDKs and defaults, errors).)
- Schema & documentation, Beam 1.0 +11: Tencent Hy4 73 (Model reading for hy4 on Tencent Cloud TokenHub.); Beam 1.0 84 (Model reading.)
- Reliability, Beam 1.0 +6: Tencent Hy4 46 (Model reading for hy4 on Tencent Cloud TokenHub.); Beam 1.0 52 (Hosted lines, for the Reflection API.)