Skip to main content
pip install openai

​
Setup

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://llm.orchid.ac/v1",
    api_key=os.environ["ORCHID_API_KEY"],
)

​
Chat completion

response = client.chat.completions.create(
    model="orchid01",
    messages=[
        {"role": "system", "content": "You are a financial analyst."},
        {"role": "user",   "content": "Summarise this 10-K filing..."},
    ],
    max_tokens=4096,
    temperature=0.1,
)
print(response.choices[0].message.content)

​
Streaming

stream = client.chat.completions.create(
    model="orchid01",
    messages=[{"role": "user", "content": "Analyse this credit agreement..."}],
    stream=True,
)
for chunk in stream:
    piece = chunk.choices[0].delta.content or ""
    if piece:
        print(piece, end="", flush=True)

​
Thinking mode

response = client.chat.completions.create(
    model="orchid01",
    messages=[{"role": "user", "content": "Complex multi-step analysis..."}],
    max_tokens=16384,
    extra_body={"orchid": {"thinking": True}},
)

reasoning = response.choices[0].message.model_extra.get("reasoning_content", "")
answer    = response.choices[0].message.content

​
With grounding score

response = client.chat.completions.create(
    model="orchid01",
    messages=[
        {"role": "user", "content": f"Filing:\n\n{filing_text}\n\nWhat was Q3 revenue?"}
    ],
    extra_body={"orchid": {"dehallucinate": True}},
)

answer  = response.choices[0].message.content
orchid  = response.model_extra.get("orchid", {})
score   = orchid.get("score", 1.0)
grounded = orchid.get("grounded", True)

print(f"Answer: {answer}")
print(f"Grounding score: {score} ({'✓' if grounded else '⚠ check flagged spans'})")