Sonar Pro - Kyma API

Overview

Sonar Pro integrates live search directly into its generation pipeline. It performs multi-step queries to retrieve current information and returns detailed answers with explicit citations. The model accepts text and image inputs and outputs text only. On Kyma, it runs with a 200,000-token context window and an 8,000-token maximum output. It does not support function calling, structured outputs, or reasoning traces, and it operates at a medium speed tier. It is classified as a premium tier model, and each request incurs a per-request search fee on top of standard token costs. Kyma handles routing with automatic failover and includes exact request costs in the usage.cost field. Prompt caching is supported, and cached input prefixes are billed at this model’s cached input rate. The X-Kyma-Model header confirms the active model for every response.

Specs

Field	Value
Model ID	`sonar-pro`
Best for	Deep web research, complex current-events questions, longer cited reports
Context window	200,000
Max output tokens	8K
Input modalities	Text, Image
Output modalities	Text
Tool calling	No
Structured outputs	No
Prompt caching	Yes
Speed	Medium
Cost band	Premium
Release stage	Stable

Pricing

	Per 1M tokens
Input	$4.05
Output	$20.25

Use this when

Deep web research — Query complex topics and retrieve synthesized answers grounded in live sources.
Current events analysis — Track recent developments and generate summaries based on up-to-date reporting.
Long-form cited reports — Draft detailed documents with inline citations and multi-step information gathering.
Image-assisted research — Analyze uploaded images alongside live web queries to contextualize visual data.

Not ideal for

Do not use this model for low-latency conversational chat, function calling, or tasks requiring strict JSON formatting.

Pick something else when

You need function calling or tool use: use gpt-5.6-terra or qwen-3.7-max.
You need fast, low-cost conversational responses: use gemini-3.5-flash-lite or deepseek-v4-flash.
You require strict JSON or structured outputs: use qwen-3.7-plus or gemini-3.6-flash.

Example

from openai import OpenAI

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

response = client.chat.completions.create(
    model="sonar-pro",
    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=frontier-open"

FAQ

Does Sonar Pro support function calling or structured outputs? No. The model does not support tools or structured output modes; it is optimized for text generation with web citations. How is search pricing handled on Kyma? Each request incurs a per-request search fee in addition to standard token costs, billed separately from the input and output rates. Can I cache prompts to reduce costs? Yes. Prompt caching is supported, and Kyma bills cached input prefixes at this model’s cached input rate.

​Overview

​Specs

​Pricing

​Use this when

​Not ideal for

​Pick something else when

​Example

​Agent query example

​FAQ