# Hy4 preview API prices

Hy4 preview (Hy) — 1.0M context, 66k max output.
15 metered per-token offers from 15 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Vancine | $0.67 | $2 | $0.034 | 1.0M |
| Kilo Gateway | $0.7506 | $2.2509 | $0.0378 | 1.0M |
| OpenRouter | $0.7506 | $2.2509 | $0.0378 | 1.0M |
| Deep Infra | $0.834 | $2.501 | $0.042 | 1.0M |
| Eden AI | $0.834 | $2.501 | $0.042 | 1.0M |
| Eden AI | $0.834 | $2.501 | $0.042 | 1.0M |
| Hugging Face | $0.834 | $2.501 | — | 1.0M |
| DevPass (LLM Gateway) | $0.834 | $2.501 | $0.042 | 1.0M |
| LLM Gateway | $0.834 | $2.501 | $0.042 | 1.0M |
| NanoGPT | $0.834 | $2.501 | $0.042 | 1.0M |
| OpenCode Go | $0.834 | $2.501 | $0.042 | 1.0M |
| Tencent TokenHub | $0.834 | $2.501 | $0.042 | 1.0M |
| Vercel AI Gateway | $0.834 | $2.501 | $0.042 | 1.0M |
| AIHubMix | $0.845 | $2.535 | $0.0423 | 1.0M |
| CrossModel | $0.96 | $2.88 | $0.048 | 1.0M |

## Summary

- Cheapest input: $0.67 per 1M tokens (Vancine)
- Cheapest output: $2 per 1M tokens (Vancine)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): Tencent Token Plan
- Released: 2026-08-28
- Inputs: text

## FAQ

### What is the cheapest Hy4 preview API?

As of Oct 4, 2026, Vancine has the lowest Hy4 preview output price at $2 per 1M tokens, and Vancine has the lowest input price at $0.67 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer Hy4 preview?

15 providers list Hy4 preview on Sovyron; 15 of them sell it at a metered per-token price.

### Is Hy4 preview free?

No provider in the Sovyron catalog lists a free tier for Hy4 preview.

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

Yes. 1 flat-rate plan(s) include it; the cheapest is OpenCode OpenCode Go at $10/month.

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

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

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