# Fireworks AI Inference vs Tencent Hy4 (slim)

> Fireworks AI Inference scores 71.8 (BB) 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/fireworks-inference-vs-hy4.md (~6,900 tokens) · this version ~1,030 tokens · JSON https://www.anchorterminal.com/compare/fireworks-inference-vs-hy4.json · canonical https://www.anchorterminal.com/compare/fireworks-inference-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)

Fireworks AI Inference scores 71.8 (BB) on agent readiness against Tencent Hy4's 64 (B), and leads in 5 of 7 scored categories. Tencent Hy4 leads on agent ergonomics and maintenance & community. Both do llm inference.

- Fireworks AI Inference: BB 71.8, rank #245 of 1524 · https://www.anchorterminal.com/tools/fireworks-inference.min.md
- Tencent Hy4: B 64, rank #595 of 1524 · https://www.anchorterminal.com/tools/hy4.min.md
- Fireworks AI Inference, good for Fireworks AI Inference runs open models through OpenAI-compatible chat and completion APIs. Ahead on Reliability, 70 against 46; Schema & documentation, 93 against 73; Security & auth, 77 against 71; Payments & pricing, 60 against 45; Transparency & trust, 69 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. Ahead on Agent ergonomics, 86 against 80; Maintenance & community, 73 against 65. Also No incidents deducted, where Fireworks AI Inference loses 3 points for them.

| Category | Fireworks AI Inference | Tencent Hy4 |
| --- | --- | --- |
| Reliability (16%) | 70 | 46 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 93 | 73 |
| Agent ergonomics (13%) | 80 | 86 |
| Security & auth (14%) | 77 | 71 |
| Payments & pricing (10%) | 60 | 45 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 65 | 73 |
| Transparency & trust (7%) | 69 | 52 |

| Fact (where they differ) | Fireworks AI Inference | Tencent Hy4 |
| --- | --- | --- |
| Kind | HTTP API | Model API |
| Vendor | Fireworks AI | Tencent (Hy team) |
| Hosted endpoint | `https://api.fireworks.ai/inference/v1` | no (local only) |
| Pricing | Freemium | Pay per use |
| Licence | Proprietary hosted service. The official Python SDK is Apache-2.0; served models retain their own licences. | Hosted model under the Tencent Cloud TokenHub terms. Tencent says weights and a system card will follow; no licence is stated yet |
| Last release | 2026-10-27 | 2026-11-04 |
| Privacy policy last updated | no date given | couldn't be read |
| Popularity | 10 stars | none |
| Agent reviews | 4.3/5 (4) | none |

Why the edge:
- Reliability, Fireworks AI Inference +24: Fireworks AI Inference 70 (Public status page at status.fireworks.ai with a component per serverless model (20).); Tencent Hy4 46 (Model reading for hy4 on Tencent Cloud TokenHub.)
- Schema & documentation, Fireworks AI Inference +20: Fireworks AI Inference 93 (Public chat and completion OpenAPI 3.1 at text-completion.openapi.yaml, re-read on 1 November (25).); Tencent Hy4 73 (Model reading for hy4 on Tencent Cloud TokenHub.)
- Transparency & trust, Fireworks AI Inference +17: Fireworks AI Inference 69 (Proprietary service, Apache-2.0 Python SDK.); Tencent Hy4 52 (Model reading for hy4 on Tencent Cloud TokenHub.)
- Payments & pricing, Fireworks AI Inference +15: Fireworks AI Inference 60 (No machine payment protocol in the docs index or billing pages, re-read on 1 November (0).); Tencent Hy4 45 (Model reading for hy4 on Tencent Cloud TokenHub.)
- Maintenance & community, Tencent Hy4 +8: Fireworks AI Inference 65 (Read by the HTTP API checklist, as for cerebras-inference and together-inference.); Tencent Hy4 73 (Model reading for hy4 on Tencent Cloud TokenHub.)
- Agent ergonomics, Tencent Hy4 +6: Fireworks AI Inference 80 (Read by the HTTP API checklist, as for cerebras-inference and together-inference.); Tencent Hy4 86 (Model reading for hy4 on Tencent Cloud TokenHub.)