Thinking/Reasoning models represent a new generation of LLMs specifically trained to expose their internal reasoning process. Unlike traditional LLMs that only show final outputs, thinking models like Claude 3.7 Sonnet, OpenAI o1/o3, and Deepseek R1 are designed to “think out loud” - producing a detailed chain of thought before delivering their final response.

These reasoning-optimized models are built to excel in tasks requiring complex analysis, multi-step problem solving, and structured logical thinking. Portkey makes these advanced models accessible through a unified API specification that works consistently across providers.

​
Supported Thinking Models

Portkey currently supports the following thinking-enabled models:

  • Anthropic: claude-3-7-sonnet-latest
  • Google Vertex AI: anthropic.claude-3-7-sonnet@20250219
  • Amazon Bedrock: claude-3-7-sonnet

More thinking models will be supported as they become available.

​
Using Thinking Mode

  1. You must set strict_open_ai_compliance=False in your headers or client configuration
  2. The thinking response is returned in a different format than standard completions
  3. For streaming responses, the thinking content is in response_chunk.choices[0].delta.content_blocks

Extended thinking API through Portkey is currently in beta.

​
Basic Example

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
    virtual_key="VIRTUAL_KEY",   # Add your provider's virtual key
    strict_open_ai_compliance=False  # Required for thinking mode
)

# Create the request
response = portkey.chat.completions.create(
  model="claude-3-7-sonnet-latest",
  max_tokens=3000,
  thinking={
      "type": "enabled",
      "budget_tokens": 2030  # Maximum tokens to use for thinking
  },
  stream=False,
  messages=[
      {
          "role": "user",
          "content": [
              {
                  "type": "text",
                  "text": "when does the flight from new york to bengaluru land tomorrow, what time, what is its flight number, and what is its baggage belt?"
              }
          ]
      }
  ]
)
print(response)

# For streaming responses, handle content_blocks differently
# response = portkey.chat.completions.create(
#   ...same config as above but with stream=True
# )
# for chunk in response:
#     if chunk.choices[0].delta:
#         content_blocks = chunk.choices[0].delta.get("content_blocks")
#         if content_blocks is not None:
#             for content_block in content_blocks:
#                 print(content_block)

​
Multi-Turn Conversations

For multi-turn conversations, include the previous thinking content in the conversation history:

from portkey_ai import Portkey

# Initialize the Portkey client
portkey = Portkey(
    api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
    virtual_key="VIRTUAL_KEY",   # Add your provider's virtual key
    strict_open_ai_compliance=False
)

# Create the request
response = portkey.chat.completions.create(
  model="claude-3-7-sonnet-latest",
  max_tokens=3000,
  thinking={
      "type": "enabled",
      "budget_tokens": 2030
  },
  stream=False,
  messages=[
      {
          "role": "user",
          "content": [
              {
                  "type": "text",
                  "text": "when does the flight from baroda to bangalore land tomorrow, what time, what is its flight number, and what is its baggage belt?"
              }
          ]
      },
      {
          "role": "assistant",
          "content": [
                  {
                      "type": "thinking",
                      "thinking": "The user is asking several questions about a flight from Baroda (also known as Vadodara) to Bangalore:\n1. When does the flight land tomorrow\n2. What time does it land\n3. What is the flight number\n4. What is the baggage belt number at the arrival airport\n\nTo properly answer these questions, I would need access to airline flight schedules and airport information systems. However, I don't have:\n- Real-time or scheduled flight information\n- Access to airport baggage claim allocation systems\n- Information about specific flights between these cities\n- The ability to look up tomorrow's specific flight schedules\n\nThis question requires current, specific flight information that I don't have access to. Instead of guessing or providing potentially incorrect information, I should explain this limitation and suggest ways the user could find this information.",
                      "signature": "EqoBCkgIARABGAIiQBVA7FBNLRtWarDSy9TAjwtOpcTSYHJ+2GYEoaorq3V+d3eapde04bvEfykD/66xZXjJ5yyqogJ8DEkNMotspRsSDKzuUJ9FKhSNt/3PdxoMaFZuH+1z1aLF8OeQIjCrA1+T2lsErrbgrve6eDWeMvP+1sqVqv/JcIn1jOmuzrPi2tNz5M0oqkOO9txJf7QqEPPw6RG3JLO2h7nV1BMN6wE="
                  }
          ]
      },
      {
          "role": "user",
          "content": "thanks that's good to know, how about to chennai?"
      }
  ]
)
print(response)

​
Understanding Response Format

When using thinking-enabled models, be aware of the special response format:

The assistant’s thinking response is returned in the response_chunk.choices[0].delta.content_blocks array, not the response.choices[0].message.content string.

This is especially important for streaming responses, where you’ll need to specifically parse and extract the thinking content from the content blocks.

​
When to Use Thinking Models

Thinking models are particularly valuable in specific use cases:

​
FAQs