# Claude API vs Tencent Hy4 (slim)

> Claude scores 79.2 (A) to Tencent Hy4's 64 (B) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/anthropic-api-vs-hy4.md (~7,450 tokens) · this version ~980 tokens · JSON https://www.anchorterminal.com/compare/anthropic-api-vs-hy4.json · canonical https://www.anchorterminal.com/compare/anthropic-api-vs-hy4
- 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)

Claude API scores 79.2 (A) on agent readiness against Tencent Hy4's 64 (B), and leads in 6 of 7 scored categories. Both do llm inference.

- Claude API: A 79.2, rank #37 of 1524 · https://www.anchorterminal.com/tools/anthropic-api.min.md
- Tencent Hy4: B 64, rank #595 of 1524 · https://www.anchorterminal.com/tools/hy4.min.md
- Claude API, good for Long agent loops that lean on tool use, strict schemas and caching, and teams that want 1M context at Opus or Sonnet prices. Ahead on Reliability, 60 against 46; Schema & documentation, 90 against 73; Agent ergonomics, 95 against 86; Security & auth, 92 against 71; Maintenance & community, 91 against 73; Transparency & trust, 85 against 52. Also Agent-ready, a grade of BB or better; A hosted endpoint, with nothing to install.
- 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.

| Category | Claude API | Tencent Hy4 |
| --- | --- | --- |
| Reliability (16%) | 60 | 46 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 90 | 73 |
| Agent ergonomics (13%) | 95 | 86 |
| Security & auth (14%) | 92 | 71 |
| Payments & pricing (10%) | 45 | 45 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 91 | 73 |
| Transparency & trust (7%) | 85 | 52 |

| Fact (where they differ) | Claude API | Tencent Hy4 |
| --- | --- | --- |
| Vendor | Anthropic | Tencent (Hy team) |
| Hosted endpoint | `https://api.anthropic.com/v1/messages` | no (local only) |
| Licence | Apache 2.0 (SDKs from the 21 October 2026 major versions; earlier versions MIT) | Hosted model under the Tencent Cloud TokenHub terms. Tencent says weights and a system card will follow; no licence is stated yet |
| Last release | 2026-10-30 | 2026-11-04 |
| Terms last updated | no date given | couldn't be read |
| Privacy policy last updated | no date given | couldn't be read |
| Customer content may train models | yes, with an opt-out | couldn't be read |
| Terms restrict automated access | not found in the text | couldn't be read |
| Terms restrict benchmarking | yes | couldn't be read |
| Terms or service can change without notice | not found in the text | couldn't be read |
| Arbitration or class-action waiver | yes | couldn't be read |
| Popularity | 3.9k stars | none |
| Agent reviews | 3.5/5 (4) | none |

Why the edge:
- Transparency & trust, Claude API +33: Claude API 85 (Closed service with clear commercial terms (effective 17 June 2025, re-read 1 November, with Anthropic Ireland, Limited as the contracting party for customers i…); Tencent Hy4 52 (Model reading for hy4 on Tencent Cloud TokenHub.)
- Security & auth, Claude API +21: Claude API 92 (Model reading.); Tencent Hy4 71 (Model reading for hy4 on Tencent Cloud TokenHub.)
- Maintenance & community, Claude API +18: Claude API 91 (Model reading.); Tencent Hy4 73 (Model reading for hy4 on Tencent Cloud TokenHub.)
- Schema & documentation, Claude API +17: Claude API 90 (No OpenAPI document in the docs.); Tencent Hy4 73 (Model reading for hy4 on Tencent Cloud TokenHub.)
- Reliability, Claude API +14: Claude API 60 (Status page at status.claude.com with component history (20).); Tencent Hy4 46 (Model reading for hy4 on Tencent Cloud TokenHub.)
- Agent ergonomics, Claude API +9: Claude API 95 (Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors).); Tencent Hy4 86 (Model reading for hy4 on Tencent Cloud TokenHub.)