---
title: "hy4-preview - Model Details & Comparison"
description: "hy4-preview from Kyma: capabilities, context limits, pricing, and side-by-side comparisons with alternative models."
url: "https://www.getmaxim.ai/bifrost/model-library/compare/kyma/hy4-preview"
markdown: "https://www.getmaxim.ai/bifrost/model-library/compare/kyma/hy4-preview.md"
---

# hy4-preview - Model Details & Comparison

> hy4-preview from Kyma: capabilities, context limits, pricing, and side-by-side comparisons with alternative models.

## Important Links

- [View MCP Gateway](https://www.getmaxim.ai/resources/mcp-gateway.md)
- [Features](https://www.getmaxim.ai/bifrost/#features)
- [Enterprise](https://www.getmaxim.ai/enterprise)
- [Pricing](https://www.getmaxim.ai/pricing.md)
- [Docs](https://docs.getbifrost.ai)
- [GitHub](https://github.com/maximhq/bifrost)
- [Book a Demo](https://www.getmaxim.ai/book-a-demo)

## About hy4-preview

hy4-preview is a chat model from Kyma, one of 83 chat models they offer. It is priced at $1.13 per 1M input tokens and $3.38 per 1M output tokens, ranking 2636 out of 4042 chat models by cost and cheaper than 35% of models in this category. hy4-preview supports function calling, reasoning, structured output. Its 1,049K-token context window is in the top 15% among chat models.

## Specifications

- **Kyma Provider.**
- **Chat Mode.**
- **1,048,576 Max Input Tokens.**
- **64,000 Max Output Tokens.**
- **$1.13 / 1M tokens Input Price.**
- **$3.38 / 1M tokens Output Price.**

## Capabilities

hy4-preview supports: Function Calling, Reasoning, Response Schema.

## hy4-preview Pricing Overview

At $1.13 per 1M input tokens and $3.38 per 1M output tokens, hy4-preview ranks 2636 out of 4042 chat models by input cost. It is more expensive compared to the median of $0.60 for chat models, and is cheaper than 35% of models in this category.

hy4-preview is one of 83 Kyma chat models, with support for function calling, reasoning, structured output. its 1,049K-token context window places it in the top 15% of chat models.

## Models to Compare

Alternatives to hy4-preview with comparable capabilities.

| Model | Provider | Input $/1M | Output $/1M |
| --- | --- | --- | --- |
| abliterated-model | Abliteration | $1.00 | $3.00 |
| abliterated-model-large-flash | Abliteration | $1.00 | $2.00 |
| amazon.nova-2-pro-preview-20251202-v1:0 | AWS Bedrock | $1.25 | $10.00 |
| apac.amazon.nova-2-pro-preview-20251202-v1:0 | AWS Bedrock | $1.38 | $11.00 |
| eu.amazon.nova-2-pro-preview-20251202-v1:0 | AWS Bedrock | $1.38 | $11.00 |

## Related Resources

- [Calculate hy4-preview costs](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/kyma/model/hy4-preview.md)
- [All Kyma pricing](https://www.getmaxim.ai/bifrost/llm-cost-calculator/provider/kyma.md)

## FAQ

### Is hy4-preview cheaper than abliterated-model?

No. hy4-preview costs $1.13 per 1M input tokens while abliterated-model costs $1.00 per 1M input tokens, making abliterated-model 11% more affordable for input. However, hy4-preview may offer different capabilities or performance characteristics that justify the price difference.

### How does hy4-preview pricing compare to the average chat model?

hy4-preview input pricing is $1.13 per 1M tokens, which is 88% above the median of $0.60 for chat models. It ranks 2636 out of 4042 chat models by input cost, making it cheaper than 35% of models in this category. For output, it costs $3.38 per 1M tokens compared to the median of $1.80.

### What makes hy4-preview different from other Kyma models?

Among Kyma's 83 chat models, hy4-preview ranks 42 by input cost.

### What are the best alternatives to hy4-preview?

The most comparable chat models to hy4-preview are: abliterated-model from Abliteration ($1.00/1M input tokens); abliterated-model-large-flash from Abliteration ($1.00/1M input tokens); amazon.nova-2-pro-preview-20251202-v1:0 from AWS Bedrock ($1.25/1M input tokens); apac.amazon.nova-2-pro-preview-20251202-v1:0 from AWS Bedrock ($1.38/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.

### How large is hy4-preview's context window?

hy4-preview supports up to 1,048,576 input tokens, placing it in the top 15% of chat models by context window size (rank 413 of 4003). This makes it suitable for processing long documents, extensive code repositories, or maintaining detailed conversation histories.

### How do I calculate hy4-preview costs?

hy4-preview is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $1.13 and generating 1M output tokens costs $3.38.

## Related Resources

- [Model library](https://www.getmaxim.ai/bifrost/model-library.md)
- [LLM cost calculator](https://www.getmaxim.ai/bifrost/llm-cost-calculator.md)
- [Docs: Bifrost docs](https://docs.getbifrost.ai)
- [GitHub: maximhq/bifrost](https://github.com/maximhq/bifrost)
- [Pricing: Bifrost pricing](https://www.getmaxim.ai/pricing.md)
- [Enterprise: Bifrost enterprise](https://www.getmaxim.ai/enterprise)
- [Book a Demo: Bifrost demo](https://www.getmaxim.ai/book-a-demo)
- [Resources: Bifrost resources](https://www.getmaxim.ai/resources.md)

---

*This is a markdown version of [https://www.getmaxim.ai/bifrost/model-library/compare/kyma/hy4-preview](https://www.getmaxim.ai/bifrost/model-library/compare/kyma/hy4-preview) for AI/LLM consumption.*