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

# sonar - Model Details & Comparison

> sonar 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 sonar

sonar is a chat model from Kyma, one of 83 chat models they offer. It is priced at $1.35 per 1M input tokens and $1.35 per 1M output tokens, ranking 2829 out of 4042 chat models by cost and cheaper than 30% of models in this category. sonar supports vision, prompt caching. It accepts up to 127K input tokens.

## Specifications

- **Kyma Provider.**
- **Chat Mode.**
- **127,072 Max Input Tokens.**
- **4,096 Max Output Tokens.**
- **$1.35 / 1M tokens Input Price.**
- **$1.35 / 1M tokens Output Price.**

## Capabilities

sonar supports: Vision, Prompt Caching.

## sonar Pricing Overview

At $1.35 per 1M input tokens and $1.35 per 1M output tokens, sonar ranks 2829 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 30% of models in this category.

sonar is one of 83 Kyma chat models, with support for vision, prompt caching.

## Models to Compare

Alternatives to sonar with comparable capabilities.

| Model | Provider | Input $/1M | Output $/1M |
| --- | --- | --- | --- |
| 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 |
| us.amazon.nova-2-pro-preview-20251202-v1:0 | AWS Bedrock | $1.38 | $11.00 |
| apac.anthropic.claude-haiku-4-5-20251001-v1:0 | AWS Bedrock | $1.10 | $5.50 |

## Related Resources

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

## FAQ

### Is sonar cheaper than amazon.nova-2-pro-preview-20251202-v1:0?

No. sonar costs $1.35 per 1M input tokens while amazon.nova-2-pro-preview-20251202-v1:0 costs $1.25 per 1M input tokens, making amazon.nova-2-pro-preview-20251202-v1:0 7% more affordable for input. However, sonar may offer different capabilities or performance characteristics that justify the price difference.

### How does sonar pricing compare to the average chat model?

sonar input pricing is $1.35 per 1M tokens, which is 125% above the median of $0.60 for chat models. It ranks 2829 out of 4042 chat models by input cost, making it cheaper than 30% of models in this category. For output, it costs $1.35 per 1M tokens compared to the median of $1.80.

### What makes sonar different from other Kyma models?

Among Kyma's 83 chat models, sonar ranks 45 by input cost.

### What are the best alternatives to sonar?

The most comparable chat models to sonar are: 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); eu.amazon.nova-2-pro-preview-20251202-v1:0 from AWS Bedrock ($1.38/1M input tokens); us.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 do I calculate sonar costs?

sonar 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 $1.35 and generating 1M output tokens costs $1.35.

## 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/sonar](https://www.getmaxim.ai/bifrost/model-library/compare/kyma/sonar) for AI/LLM consumption.*