nineth 0.5.2

model sdk built by the 9th ditrict at tooig

nineth

nineth is the Python SDK for the 1984 model API, built by the 9th District at Tooig.

---

Install

pip install nineth
export NINETH_API_KEY="your-api-key"

---

How it works

Every request goes through client.model.request(...).

• Pass a task. Get a response.
• Set stream=True to receive text as it arrives, word by word.
• Per request, you can opt into persistent sessions, built-in services, included services, a base-provider override, and debug telemetry.
• The server still runs the worker loop and manages the actual task state.

---

Models

Name	Description
1984-m3-0317	Most capable. Best for research and complex tasks.
1984-m2-preview	Fast and powerful. Good for most tasks.
1984-m2-light	Lightweight, quick general tasks.
1984-m1-unified	High-throughput unified model.
1984-m0-brute	Compact efficient model.
1984-m0-sm	Smallest model, fastest responses.

Set a default at client creation or pass model= per call.

---

Cookbook

1 — Get a response

The simplest case. Ask something, get the answer.

from nineth import NinethClient

with NinethClient(default_model="1984-m3-0317") as client:
    response = client.model.request("Give me a tight BTC market brief.")
    print(response["final_response"])

response is a plain dict. The text is always in response["final_response"].

---

2 — Stream the response live

Set stream=True to print text as it arrives.

from nineth import NinethClient

with NinethClient(default_model="1984-m3-0317") as client:
    for event in client.model.request("Summarise crude oil today.", stream=True):
        if event["type"] == "model_delta":
            print(event["data"]["text"], end="", flush=True)

The last event in the stream is type: result and contains the full final_response alongside iterations.

---

3 — Choose a different model per request

from nineth import NinethClient

with NinethClient() as client:
    response = client.model.request(
        "What happened with Nvidia earnings?",
        model="1984-m2-light",
    )
    print(response["final_response"])

---

4 — Control reasoning depth

Use reasoning to hint at how deeply the model should think before answering. Valid values: "low", "medium", "high". Leave it out to use the model default.

from nineth import NinethClient

with NinethClient(default_model="1984-m3-0317") as client:
    response = client.model.request(
        "Analyse the macro impact of a Fed rate pause.",
        reasoning="high",
    )
    print(response["final_response"])

---

5 — Show the model's reasoning

Set show_reasoning=True to include the model's internal chain-of-thought. This is off by default.

from nineth import NinethClient

with NinethClient(default_model="1984-m3-0317") as client:
    response = client.model.request(
        "Walk me through whether gold is trending or ranging.",
        reasoning="medium",
        show_reasoning=True,
    )
    for block in response.get("thinking", []):
        print("[thinking]", block)
    print(response["final_response"])

---

6 — Limit how many turns the model takes

max_iterations controls how many model turns the server runs. The default is 10. Most tasks finish in 1–3 turns.

from nineth import NinethClient

with NinethClient(default_model="1984-m3-0317") as client:
    response = client.model.request(
        "Give me a one-paragraph ETH brief.",
        max_iterations=2,
    )
    print(response["final_response"])

---

7 — Async usage

import asyncio
from nineth import AsyncNinethClient

async def main():
    async with AsyncNinethClient(default_model="1984-m3-0317") as client:
        response = await client.model.request(
            "Summarise macro risk factors this week.",
        )
        print(response["final_response"])

asyncio.run(main())

Async streaming works the same way:

import asyncio
from nineth import AsyncNinethClient

async def main():
    async with AsyncNinethClient(default_model="1984-m3-0317") as client:
        async for event in await client.model.request(
            "Research BTC ETF flows.", stream=True
        ):
            if event["type"] == "model_delta":
                print(event["data"]["text"], end="", flush=True)

asyncio.run(main())

---

8 — Health check

No API key needed. Use this to verify the endpoint is reachable.

from nineth import NinethClient

with NinethClient() as client:
    print(client.health())
# {'status': 'ok', 'timestamp': '2026-04-04T00:00:00+00:00'}

---

9 — Point the SDK at a different endpoint

from nineth import NinethClient

with NinethClient(
    base_url="https://your-deployment.modal.run",
    api_key="your-key",
    default_model="1984-m3-0317",
) as client:
    response = client.model.request("Hello.")
    print(response["final_response"])

Or use environment variables:

export NINETH_BASE_URL="https://your-deployment.modal.run"
export NINETH_MODEL="1984-m3-0317"

---

10 — Force the base Together provider path

Set base_system=True to set to task specific models

from nineth import NinethClient

with NinethClient(default_model="1984-m2-preview") as client:
    response = client.model.request(
        "Summarise today's macro tape.",
        base_system=True,
    )
    print(response["final_response"])

base_system only changes the provider path. It does not change the model alias map automatically. If you need a Together-specific model that is not the current alias target, pass the raw Together model name in model=.

---

11 — Persist and reuse a session

Set cache=True to persist the task session and receive a reusable session_id. Pass that session_id back into later requests to continue the same task memory.

from nineth import NinethClient

with NinethClient(default_model="1984-m3-0317") as client:
    first = client.model.request(
        "Start a running research notebook for crude oil.",
        cache=True,
    )
    session_id = first["session_id"]

    second = client.model.request(
        "Continue from the last note and add today's macro drivers.",
        cache=True,
        session_id=session_id,
    )
    print(second["final_response"])

If cache=False, the task is treated as one-shot and no session_id is exposed.

---

12 — Opt into built-in services

Built-in services are off by default.

• default_service=False: no built-in services
• default_service=True: all built-in services
• default_service=[...]: only the named built-in services

from nineth import NinethClient

with NinethClient(default_model="1984-m3-0317") as client:
    response = client.model.request(
        "Research OPEC headlines and summarise the impact.",
        default_service=["search_news", "search_web"],
    )
    print(response["final_response"])

---

13 — Use one include_service surface for custom services

include_service is the only custom-service surface you need.

• If a path exists in your application process, the SDK loads that schema.py locally, exposes its schema to the model, executes the emitted service call in your process, and resumes the run through the callback protocol.
• If a path does not exist locally, the SDK passes it through to the API server as a server-hosted schema.py path.

This keeps the public surface small while still supporting both local and server-managed tools.

Local callback example:

from nineth import NinethClient

with NinethClient(default_model="1984-m3-0317") as client:
    response = client.model.request(
        "Use my local weather tool and compare it with today's oil move.",
        default_service=["search_web"],
        include_service=["./services/weather/schema.py"],
    )
    print(response["final_response"])

Server-hosted path example:

from nineth import NinethClient

with NinethClient(default_model="1984-m3-0317") as client:
    response = client.model.request(
        "Use the custom weather service and compare it with market risk sentiment.",
        default_service=["search_web"],
        include_service=["/srv/app/services/weather/schema.py"],
    )
    print(response["final_response"])

Minimal local schema.py shape:

from typing import Any, Dict


class WeatherServiceManager:
    def get_weather(self, location: str) -> Dict[str, Any]:
        return {"location": location, "forecast": "sunny"}


weather_services = {
    "get_weather": {
        "name": "get_weather",
        "description": "Return a tiny weather forecast.",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string"}
            },
            "required": ["location"],
            "additionalProperties": False,
        },
    }
}


weather_implementations = {
    "get_weather": lambda manager: manager.get_weather,
}

14 — Enable debug telemetry

Set debug=True to keep the worker's structured telemetry in the buffered response or streamed events.

from nineth import NinethClient

with NinethClient(default_model="1984-m3-0317") as client:
    response = client.model.request(
        "Research market risk and show the internal trace.",
        default_service=["search_news"],
        debug=True,
    )
    print(response.get("events", []))

---

Response shape

Buffered (stream=False)

{
    "final_response": "Bitcoin is trading near...",
    "iterations": 2,
    "usage": {"prompt_tokens": 412, "completion_tokens": 88, "total_tokens": 500},
    "thinking": [],          # only populated when show_reasoning=True
    "service_calls": [...],
    "service_responses": [...],
    "events": [...],
}

Only final_response and iterations are guaranteed to be present on every response.

Streaming (stream=True)

Each loop iteration yields a dict:

# Text arriving live
{"type": "model_delta", "data": {"text": "Bitcoin is trading..."}}

# Tool calls the model made
{"type": "service_call",     "data": {"service_name": "search_web", "params": {...}}}
{"type": "service_response", "data": {"service_name": "search_web", "success": True, "summary": {...}}}

# Final summary — always the last event
{"type": "result", "data": {"final_response": "...", "iterations": 2}}

---

Error handling

from nineth import NinethClient, NinethAPIError

with NinethClient(default_model="1984-m3-0317") as client:
    try:
        response = client.model.request("Analyse ETH.")
    except NinethAPIError as exc:
        print("API error:", exc)
    except ValueError as exc:
        print("Configuration error:", exc)

---

Authentication

Set NINETH_API_KEY in your environment or pass api_key= to the client constructor. That key can be any one key registered by the server's NINETH_API_KEYS registry. The health check endpoint does not require a key.