# Hy4 flash API prices

Hy4 flash (hy-flash) — 1.0M context, 66k max output.
11 metered per-token offers from 13 providers, in USD per 1M tokens.
Prices as of 2026-11-22.

| Provider | API model ID | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- | --- |
| Hugging Face | `tencent/Hy4-flash` | $0.035 | $0.1405 | — | 1.0M |
| NanoGPT | `tencent/hy4-flash` | $0.035 | $0.1405 | $0.0015 | 1.0M |
| Novita AI | `tencent/hy4-flash` | $0.035 | $0.1405 | $0.0015 | 1.0M |
| OpenRouter | `tencent/hy4-flash` | $0.035 | $0.1405 | $0.0015 | 1.0M |
| Vercel AI Gateway | `tencent/hy4-flash` | $0.035 | $0.1405 | $0.0015 | 1.0M |
| Kilo Gateway | `tencent/hy4-flash` | $0.07 | $0.281 | $0.003 | 1.0M |
| DevPass (LLM Gateway) | `hy4-flash` | $0.07 | $0.281 | $0.003 | 1.0M |
| LLM Gateway | `tencent/hy4-flash` | $0.07 | $0.281 | $0.003 | 1.0M |
| Vivgrid | `hy4-flash` | $0.07 | $0.281 | $0.01 | 1.0M |
| Kenari | `hy4-flash` | $0.0714 | $0.2857 | $0.0043 | 1.0M |
| CrossModel | `tencent/hy4-flash` | $0.08 | $0.32 | $0.0032 | 1.0M |

## Summary

- Cheapest input: $0.035 per 1M tokens (Hugging Face)
- Cheapest output: $0.1405 per 1M tokens (Hugging Face)
- First-party: not listed separately
- Free offers: Kenari, OpenCode, OpenCode Go
- Subscription plans (not per-token): none
- Released: 2026-11-16
- Inputs: image, text

## FAQ

### What is the cheapest Hy4 flash API?

As of Nov 22, 2026, Hugging Face has the lowest Hy4 flash output price at $0.1405 per 1M tokens, and Hugging Face has the lowest input price at $0.035 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Hy4 flash?

13 providers list Hy4 flash on Sovyron; 11 of them sell it at a metered per-token price.

### Is Hy4 flash free?

3 providers list a free-tier offer: Kenari, OpenCode, OpenCode Go. Free tiers usually have rate limits.

### Is Hy4 flash included in a subscription plan?

Yes. One flat-rate plan includes it; the cheapest is OpenCode OpenCode Go at $10/month.

### What is the context window of Hy4 flash?

Hy4 flash supports a 1.0M-token context window and up to 66k output tokens.

## Recent price changes

| Date | Provider | Input $/1M | Output $/1M | Change |
| --- | --- | --- | --- | --- |
| 2026-11-20 | Novita AI | $0.07 → $0.035 | $0.281 → $0.1405 | −50% |

HTML page: https://sovyron.com/models/hy4-flash/
Full dataset: https://sovyron.com/data/catalog.json
