--- title: "hy4-preview - Model Details & Comparison" description: "hy4-preview from Aihubmix: capabilities, context limits, pricing, and side-by-side comparisons with alternative models." url: "https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/aihubmix/hy4-preview" markdown: "https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/aihubmix/hy4-preview.md" --- # hy4-preview - Model Details & Comparison > hy4-preview from Aihubmix: capabilities, context limits, pricing, and side-by-side comparisons with alternative models. ## Important Links - [View MCP Gateway](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/resources/mcp-gateway.md) - [Features](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/#features) - [Enterprise](https://www.getmaxim.ai/enterprise) - [Pricing](https://www.getmaxim.ai/pricing) - [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 Aihubmix, one of 72 chat models they offer. It is priced at $0.84 per 1M input tokens and $2.53 per 1M output tokens, ranking 2159 out of 3648 chat models by cost and cheaper than 41% of models in this category. hy4-preview supports function calling, reasoning, web search, prompt caching, structured output — one of only 5 chat models with this combination. Its 1,049K-token context window is in the top 11% among chat models. ## Specifications - **Aihubmix Provider.** - **Chat Mode.** - **1,048,576 Max Input Tokens.** - **64,000 Max Output Tokens.** - **64,000 Max Tokens.** - **$0.84 / 1M tokens Input Price.** - **$2.53 / 1M tokens Output Price.** ## Capabilities hy4-preview supports: Function Calling, Reasoning, Web Search, Prompt Caching, Response Schema. ## hy4-preview Pricing Overview At $0.84 per 1M input tokens and $2.53 per 1M output tokens, hy4-preview ranks 2159 out of 3648 chat models by input cost. It is more expensive compared to the median of $0.57 for chat models, and is cheaper than 41% of models in this category. hy4-preview is one of 72 Aihubmix chat models, one of only 5 chat models combining function calling, prompt caching, reasoning, structured output, web search. its 1,049K-token context window places it in the top 11% of chat models. ## Models to Compare Alternatives to hy4-preview with comparable capabilities. | Model | Provider | Input $/1M | Output $/1M | | --- | --- | --- | --- | | anthropic.claude-haiku-4-5-20251001-v1:0 | AWS Bedrock | $1.00 | $5.00 | | gpt-5.4-mini | Azure | $0.75 | $4.50 | | gpt-5.4-mini-2026-03-17 | Azure | $0.75 | $4.50 | | claude-haiku-4-5 | Anthropic | $1.00 | $5.00 | | gemini-3.6-flash | Vertex AI | $0.75 | $3.75 | - [Compare anthropic.claude-haiku-4-5-20251001-v1:0](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/bedrock/anthropic.claude-haiku-4-5-20251001-v1-0.md) - [Compare gpt-5.4-mini](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/azure/gpt-5.4-mini.md) - [Compare gpt-5.4-mini-2026-03-17](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/azure/gpt-5.4-mini-2026-03-17.md) - [Compare claude-haiku-4-5](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/anthropic/claude-haiku-4-5.md) - [Compare gemini-3.6-flash](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/vertex_ai/gemini-3.6-flash.md) ## Related Resources - [Calculate hy4-preview costs](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/aihubmix/model/hy4-preview.md) - [All Aihubmix pricing](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/llm-cost-calculator/provider/aihubmix.md) ## FAQ ### Is hy4-preview cheaper than anthropic.claude-haiku-4-5-20251001-v1:0? Yes. hy4-preview costs $0.84 per 1M input tokens compared to anthropic.claude-haiku-4-5-20251001-v1:0's $1.00 per 1M input tokens, making it 18% more affordable. Both are chat models and share support for vision, function calling, reasoning, web search, prompt caching, structured output. ### How does hy4-preview pricing compare to the average chat model? hy4-preview input pricing is $0.84 per 1M tokens, which is 49% above the median of $0.57 for chat models. It ranks 2159 out of 3648 chat models by input cost, making it cheaper than 41% of models in this category. For output, it costs $2.53 per 1M tokens compared to the median of $1.65. ### What makes hy4-preview different from other Aihubmix models? Among Aihubmix's 72 chat models, hy4-preview ranks 39 by input cost. Its combination of function calling, prompt caching, reasoning, structured output, web search is shared by only 4 other chat models. ### What are the best alternatives to hy4-preview? The most comparable chat models to hy4-preview are: anthropic.claude-haiku-4-5-20251001-v1:0 from AWS Bedrock ($1.00/1M input tokens); gpt-5.4-mini from Azure ($0.75/1M input tokens); gpt-5.4-mini-2026-03-17 from Azure ($0.75/1M input tokens); claude-haiku-4-5 from Anthropic ($1.00/1M 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 11% of chat models by context window size (rank 304 of 3577). 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 $0.84 and generating 1M output tokens costs $2.53. ## Related Resources - [Aihubmix models](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/provider/aihubmix.md) - [Model library](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library.md) - [LLM cost calculator](https://maxim-root-proxy-preview.getmaxim.workers.dev/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) - [Enterprise: Bifrost enterprise](https://www.getmaxim.ai/enterprise) - [Book a Demo: Bifrost demo](https://www.getmaxim.ai/book-a-demo) - [Resources: Bifrost resources](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/resources.md) --- *This is a markdown version of [https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/aihubmix/hy4-preview](https://maxim-root-proxy-preview.getmaxim.workers.dev/bifrost/model-library/compare/aihubmix/hy4-preview) for AI/LLM consumption.*