Skip to main content

​
Overview

Kyma API gives you instant access to the best open source LLMs through a single endpoint. Compatible with both OpenAI and Anthropic SDKs. No credit card. No usage fees. Just get an API key and start building.

19 Free Models

Llama 4, Qwen 3, Gemma 4, GPT-OSS, Kimi K2 — all verified working.

~100ms Latency

Ultra-fast inference. Most models respond in under 200ms.

OpenAI Compatible

Drop-in replacement. Works with any OpenAI SDK, LangChain, Cursor, and more.

​
Why Kyma?

KymaOpenRouterDirect API
PriceFree$0.001+/tokenFree (limited)
Models19 open source200+ (paid)1 API only
Credit cardNeverRequiredVaries
Setup time30 seconds5 minutesPer-API signup
OpenAI SDK✅✅✅

​
How it works

Your App → Kyma API → Best Infrastructure (auto-selected)
                    ↳ Google (1M context)
Kyma automatically routes your request to the optimal infrastructure for each model. You don’t need to manage multiple API keys or deal with infrastructure.

​
Quick example

from openai import OpenAI

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

response = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Ready to start?

Get your API key and make your first request in 30 seconds →