Claude Haiku 4.5 Thinking

Anthropic’s Claude Haiku 4.5 with extended thinking enabled. Fast reasoning for math, coding, and analysis at low cost.

Claude Haiku 4.5 Thinking is the extended thinking variant of Claude Haiku 4.5, available through AnyFast via an OpenAI-compatible interface. It combines Haiku’s speed and cost-efficiency with step-by-step internal reasoning, delivering improved accuracy on complex tasks while remaining significantly faster and cheaper than larger thinking models.

Key capabilities

• OpenAI-compatible — Works as a drop-in replacement with the OpenAI SDK
• Extended thinking — Step-by-step internal reasoning enabled by default
• Fast + affordable — Thinking capability at Haiku-level speed and cost
• Streaming — Supports real-time token streaming via SSE
• Strong reasoning — Improved accuracy on math, logic, and multi-step problems

Quick example

cURL

curl https://www.anyfast.ai/v1/messages \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-haiku-4-5-20251001-thinking",
    "messages": [
      { "role": "user", "content": "Solve step by step: If a train travels 120 km in 2 hours, then slows down and travels 80 km in 3 hours, what is the average speed for the entire trip?" }
    ]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

response = client.chat.completions.create(
    model="claude-haiku-4-5-20251001-thinking",
    messages=[
        {"role": "user", "content": "Solve step by step: If a train travels 120 km in 2 hours, then slows down and travels 80 km in 3 hours, what is the average speed for the entire trip?"}
    ]
)

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

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://www.anyfast.ai/v1"
)

stream = client.chat.completions.create(
    model="claude-haiku-4-5-20251001-thinking",
    messages=[
        {"role": "user", "content": "Write a proof that there are infinitely many prime numbers."}
    ],
    stream=True
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

Parameters

Parameter	Type	Required	Description
model	string	Yes	Must be claude-haiku-4-5-20251001-thinking
messages	array	Yes	List of { role, content } objects
max_tokens	integer	No	Maximum tokens to generate
temperature	float	No	0–2. Controls randomness. Default: 1
stream	boolean	No	Enable SSE streaming. Default: false
top_p	float	No	Nucleus sampling threshold. Default: 1
stop	string / array	No	Sequences that stop generation

API Reference

View the interactive API playground for Claude Haiku 4.5 Thinking.