Sonar - Kyma API

Overview

Sonar integrates real-time web search into its generation process, returning answers grounded in current sources along with citations. It accepts text and image inputs, but outputs text only. The model operates with a 127,072-token context window and caps output at 4,096 tokens. On Kyma, you can call this model using the search alias. It supports prompt caching, which bills repeated prefixes at this model’s cached input rate. Requests route through automatic failover, and you can verify exact routing and cost in the usage.cost field and X-Kyma-Model response header. Each request incurs a small per-request search fee on top of standard token billing. The model does not support tool calling, structured outputs, or explicit reasoning traces. It is optimized for direct, cited answers rather than complex multi-step agentic workflows or long-form generation beyond its output limit.

Specs

Field	Value
Model ID	`sonar`
Best for	Live web search, current events, research with citations
Context window	127,072
Max output tokens	4K
Input modalities	Text, Image
Output modalities	Text
Tool calling	No
Structured outputs	No
Prompt caching	Yes
Speed	Medium
Cost band	Balanced
Release stage	Stable

Pricing

	Per 1M tokens
Input	$1.35
Output	$1.35

Use this when

Live Event Tracking — Fetches current developments and cites sources automatically.
Technical Research — Answers engineering questions using up-to-date documentation.
Content Drafting — Generates articles and summaries grounded in recent web data.
Visual Analysis — Processes uploaded images alongside live web queries for context.

Not ideal for

Avoid this model for agentic workflows requiring tool use, structured JSON outputs, or long-form generation exceeding 4,096 tokens.

Pick something else when

You need tool calling or structured JSON outputs: use qwen-3.7-max.
You need long-form generation beyond 4,096 tokens: use deepseek-v4-pro.
You need explicit chain-of-thought reasoning traces: use deepseek-r1.

Example

from openai import OpenAI

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="ky-...")

response = client.chat.completions.create(
    model="sonar",
    messages=[{"role": "user", "content": "..."}],
)

Agent query example

Ask the API which models fit, instead of hardcoding an id:

curl "https://kymaapi.com/v1/models?recommended_for=chat&quality_tier=strong"

FAQ

Does this model support function calling or tool use? No, Sonar does not support tool calling or structured outputs. It is designed for direct, cited text responses. How does billing work for the search component? Each request incurs a small per-request search fee on top of the standard token-based pricing. Can I use prompt caching with this model? Yes, repeated prompt prefixes are cached and billed at this model’s cached input rate.

Alias	Resolves to
`search`	`sonar`

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ

​Related aliases