indigo-owl-4

indigo-owl-4 is Liutong’s reasoning model. It is optimized for tasks that require careful, multi-step thinking — math, logic, code analysis, and structured problem solving.

Capabilities

Complex mathematical reasoning and proofs
Multi-step logical deduction
Code review and architectural analysis
Scientific reasoning and hypothesis testing
Strategic planning and decision analysis

When to use indigo-owl-4

Use this model when accuracy on hard problems matters more than speed. indigo-owl-4 takes additional time to “think” through problems before responding, which produces significantly better results on challenging tasks.

For simple Q&A or conversation, crimson-falcon-4 is faster and more cost-effective.

API usage

from openai import OpenAI

client = OpenAI(
    base_url="https://api.liutong.llby.org/v1",
    api_key="lt_your_api_key",
)

response = client.chat.completions.create(
    model="indigo-owl-4",
    messages=[
        {"role": "user", "content": "Prove that the square root of 2 is irrational."},
    ],
)

print(response.choices[0].message.content)

Parameters

Parameter	Type	Default	Description
`max_tokens`	int	—	Maximum tokens to generate.
`stream`	bool	false	Enable streaming responses.

Note: Reasoning models may not support all parameters that chat models do (e.g., temperature may be fixed). The model manages its own reasoning strategy internally.

Endpoint

POST /v1/chat/completions

See the full Chat Completions API reference.

Search Documentation