Grok 4.3 - Kyma API

Overview

grok-4.3 is xAI’s frontier model on Kyma. It combines a 1M-token context window with strong reasoning and tool use, and sits in a balanced cost band — a solid pick for general work, agentic coding, and reasoning over long inputs without paying premium-tier prices.

Specs

Field	Value
Model ID	`grok-4.3`
Best for	General work, reasoning, agentic coding, long context
Context window	1M
Max output tokens	32K
Input modalities	Text
Output modalities	Text
Tool calling	Yes
Structured outputs	Yes
Reasoning	Yes
Prompt caching	Yes
Speed	Medium
Cost band	Balanced
Release stage	Stable

Use this when

You want a frontier-quality general model at a balanced price.
You build agents that lean on tool calling across long sessions.
You need a large (1M) context window for big codebases or documents.
You want strong reasoning without committing to a premium cost band.

Pick something else when

You want the strongest tool-heavy agent behavior: use kimi-k2.6.
You need top reasoning depth: use deepseek-v4-pro.
You want the cheapest strong default: use qwen-3.6-plus.

Example

from openai import OpenAI

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

response = client.chat.completions.create(
    model="grok-4.3",
    messages=[
        {"role": "system", "content": "You are a senior software engineer."},
        {"role": "user", "content": "Refactor this module and explain each change."}
    ]
)

Agent query example

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

Qwen 3.6 Plus GLM 5.1

​Overview

​Specs

​Use this when

​Pick something else when

​Example

​Agent query example