🧠 Thinking & Reasoning

Extended thinking gives you visibility into the model's step-by-step reasoning process for complex problems that require careful analysis.

10x

Better on complex tasks

64K

Max thinking tokens

100%

Reasoning transparency

How It Works

When extended thinking is enabled, the model takes time to reason through the problem before providing a final answer. You can see the full chain of thought.

💬

User: "What's the probability of getting at least 2 heads in 5 coin flips?"

🧠 Thinking...

This is a binomial probability problem. I need to find P(X ≥ 2) where X is the number of heads in 5 flips. P(X ≥ 2) = 1 - P(X < 2) = 1 - [P(X=0) + P(X=1)] For a fair coin, p = 0.5 and n = 5. P(X=0) = C(5,0) × 0.5⁰ × 0.5⁵ = 1 × 1 × 0.03125 = 0.03125 P(X=1) = C(5,1) × 0.5¹ × 0.5⁴ = 5 × 0.5 × 0.0625 = 0.15625 P(X < 2) = 0.03125 + 0.15625 = 0.1875 P(X ≥ 2) = 1 - 0.1875 = 0.8125 Let me verify: 0.8125 = 81.25%

✨ Answer

The probability of getting at least 2 heads in 5 coin flips is 81.25% (or 13/16 as a fraction).

Enable Extended Thinking

Python

from mythicdot import MythicDot

client = MythicDot()

response = client.messages.create(
    model="mythic-4-thinking",
    max_tokens=16000,
    thinking={
        "type": "enabled",
        "budget_tokens": 10000  # Max tokens for thinking
    },
    messages=[
        {
            "role": "user",
            "content": "Solve this step by step: If x² + 5x + 6 = 0, what is x?"
        }
    ]
)

# Access thinking blocks
for block in response.content:
    if block.type == "thinking":
        print("Thinking:", block.thinking)
    elif block.type == "text":
        print("Answer:", block.text)
                

Best Use Cases

🔬

Scientific Analysis

Complex calculations, research questions, data interpretation

💻

Code Debugging

Step through logic, identify bugs, trace execution

📊

Strategic Planning

Multi-step decisions, trade-off analysis, optimization

🧩

Problem Solving

Puzzles, logic problems, mathematical proofs

Standard vs Extended Thinking

⚡ Standard Mode

Immediate responses
Great for simple queries
Lower latency
Lower cost per token
Hidden reasoning

🧠 Extended Thinking

Deliberate reasoning
Excels at complex tasks
Higher latency (worth it)
Thinking tokens charged
Full transparency

Try Extended Thinking

Give your model time to think through complex problems.

Try in Playground → Reasoning Models →