Muse Spark 1.1 - Kyma API

Overview

Meta’s Muse Spark tier. 1M context, vision, file input, reasoning — it spends ~160 tokens thinking before a one-word answer.

Specs

Field	Value
Model ID	`muse-spark-1.1`
Best for	Long-context reasoning where thinking time is acceptable
Context window	1.048576M
Max output tokens	8K
Input modalities	Text, Image, Video, File, Audio
Output modalities	Text
Tool calling	Yes
Structured outputs	Yes
Prompt caching	No
Vision	Yes
Reasoning	Yes
Speed	Medium
Cost band	Premium
Release stage	Stable

Pricing

	Per 1M tokens
Input	$1.542
Output	$5.243

Example

from openai import OpenAI

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

response = client.chat.completions.create(
    model="muse-spark-1.1",
    messages=[{"role": "user", "content": "..."}],
    tools=[...],  # function calling supported
)

Agent query example

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

curl "https://kymaapi.com/v1/models?recommended_for=chat&tools=true&quality_tier=frontier-open"

​Overview

​Specs

​Pricing

​Example

​Agent query example

Overview

Specs

Pricing

Example

Agent query example