Skip to main content

kyma-ai

Official Python client for Kyma API — free LLM API gateway. Every open source model, one endpoint.

Install

pip install kyma-ai

Quick Start

from kyma_ai import Kyma

kyma = Kyma(api_key="kyma-your-key")

# Simple: ask a question
reply = kyma.ask("Explain quantum computing simply")
print(reply)

# Streaming
for chunk in kyma.ask_stream("Write a poem"):
    print(chunk, end="", flush=True)

# Full control: OpenAI-compatible chat
response = kyma.chat.completions.create(
    model="llama-3.3-70b",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"},
    ],
)
print(response.choices[0].message.content)

Available Models

models = kyma.list_models()
for m in models:
    print(m["id"], m.get("name"))

20+ models from Meta, Google, Alibaba, OpenAI, NVIDIA, and more. All free to start.

Check Balance

info = kyma.get_balance()
print(f"Balance: ${info['balance']:.2f}")

OpenAI SDK Compatible

Kyma wraps the official OpenAI SDK. Access it directly:

openai_client = kyma.openai
# Use any OpenAI SDK feature

Get Your API Key

  1. Sign up at kymaapi.com
  2. Get your kyma- API key from the dashboard
  3. Start building!

Links

Metadata

Release files for kyma-ai 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for kyma-ai 0.1.0
File Size Uploaded
kyma_ai-0.1.0.tar.gz 3.4 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for kyma-ai 0.1.0
File Interpreter ABI Platform
kyma_ai-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 7.1 kB

Release files / kyma_ai-0.1.0.tar.gz

Download URL kyma_ai-0.1.0.tar.gz
Size 3.4 kB
Tags Source
SHA-256 checksum
How to use checksums
cb6e865e9c8d3da3350e3013fbbadca3492fd199e678fda2ba7cde3a930b2ec0
BLAKE2b-256 checksum
How to use checksums
633982675a17c1ca2e1d1824868e3c6b5d4b89cdd3b6b43a000ec2b5e0080701
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.0

Release files / kyma_ai-0.1.0-py3-none-any.whl

Download URL kyma_ai-0.1.0-py3-none-any.whl
Size 3.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
cc99c11bb5b931db02e1356f41db2c99580262ea876254d28540a67e4c34d79a
BLAKE2b-256 checksum
How to use checksums
1fd15ef57721df84f1693cc333b8189e496efff004a7a8bf420ff68408c70c7e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.13.0

Release history Release notifications | RSS feed

This release

0.1.0 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page