hypnex-openai 0.1.0

Drop-in OpenAI client for the Morpheus decentralized inference network (mor.org)

hypnex-openai (Python)

Drop-in OpenAI client for the Morpheus decentralized inference network (mor.org).

pip install hypnex-openai

from hypnex_openai import HypnexOpenAI

client = HypnexOpenAI(api_key="mor_...")  # get one at https://app.mor.org

response = client.chat.completions.create(
    model="mistral-31-24b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

HypnexOpenAI subclasses openai.OpenAI and points it at https://api.mor.org/api/v1. Streaming, tools, async, structured output — all work unchanged.

Models on the Morpheus network

The network exposes 60+ models via OpenAI-compatible endpoints. List them:

hypnex models

Or programmatically:

client.morpheus.active_models()           # full registry
client.morpheus.models_by_type("LLM")     # filter
client.morpheus.find_model("glm-5")       # lookup

Featured LLMs: mistral-31-24b, glm-5, qwen3-235b, qwen3-coder-480b-a35b-instruct, deepseek-r1:70b, minimax-m25. Embeddings: text-embedding-bge-m3. TTS: tts-kokoro. STT: whisper-1.

Drop-in for popular frameworks

Any framework that accepts a base_url accepts Morpheus:

# LangChain
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
    model="qwen3-235b",
    api_key=os.environ["HYPNEX_API_KEY"],
    base_url="https://api.mor.org/api/v1",
)

# CrewAI
from crewai import LLM
llm = LLM(
    model="openai/qwen3-235b",
    api_key=os.environ["HYPNEX_API_KEY"],
    base_url="https://api.mor.org/api/v1",
)

# llama-index
from llama_index.llms.openai_like import OpenAILike
llm = OpenAILike(
    model="qwen3-235b",
    api_base="https://api.mor.org/api/v1",
    api_key=os.environ["HYPNEX_API_KEY"],
    is_chat_model=True,
)

# instructor
import instructor
client = instructor.from_openai(HypnexOpenAI())

Morpheus-specific endpoints

client.morpheus.* exposes endpoints that have no OpenAI equivalent:

Method	What it does
balance()	Current MOR balance
transactions(limit=50)	Billing history
spending()	Cumulative usage
me()	User profile
list_keys() / create_key(name) / delete_key(id) / set_default_key(id)	API keys
link_wallet(addr, sig, msg) / get_wallet() / unlink_wallet()	Wallet binding
active_models() / find_model(name) / models_by_type(type)	Public registry

CLI

hypnex models                          # list
hypnex health                          # show api.mor.org health
hypnex chat "Hello" --model glm-5      # one-shot

Async

from hypnex_openai import AsyncHypnexOpenAI
client = AsyncHypnexOpenAI(api_key="mor_...")
r = await client.chat.completions.create(...)

Environment

• HYPNEX_API_KEY — your API key (required)
• HYPNEX_BASE_URL — override base URL (default https://api.mor.org/api/v1)

Tests

pip install -e ".[dev]"
pytest                                   # public smoke tests
HYPNEX_API_KEY=mor_... pytest          # also run authenticated tests

License

MIT