Skip to main content

​
Reasoning Configuration

You can configure the reasoning behavior using the reasoning parameter: 
curl -X POST https://aihubmix.com/v1/responses \
  -H "Authorization: Bearer YOUR_AIHUBMIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5",
    "input": "Plan a week-long trip to the US for me.",
    "reasoning": {
      "effort": "high"
    },
    "max_output_tokens": 5000
  }'

​
Reasoning Intensity

The effort parameter controls how much computational resource the model invests in reasoning, essentially dictating the level of reasoning effort.
Reasoning LevelDescription
minimalBasic reasoning with minimal computation
lowLightweight reasoning suitable for simple questions
mediumBalanced reasoning suitable for moderately complex problems
highDeep reasoning suitable for complex issues

​
Using Reasoning in Conversations

The reasoning feature can also be utilized in multi-turn dialogues: 
import requests

url = "https://aihubmix.com/v1/responses"

headers = {
    "Authorization": "Bearer YOUR_AIHUBMIX_API_KEY",
    "Content-Type": "application/json",
}

data = {
    "model": "kimi-k2.5",
    "input": [
        {
            "type": "message",
            "role": "user",
            "content": [
                {
                    "type": "input_text",
                    "text": "What is your favorite animal?",
                }
            ],
        },
        {
            "type": "message",
            "role": "assistant",
            "id": "msg_123",
            "status": "completed",
            "content": [
                {
                    "type": "output_text",
                    "text": "I don't have a favorite animal.",
                    "annotations": []
                }
            ],
        },
        {
            "type": "message",
            "role": "user",
            "content": [
                {
                    "type": "input_text",
                    "text": "Why is the sky blue?",
                }
            ],
        },
    ],
    "reasoning": {
        "effort": "high"
    },
    "max_output_tokens": 5000,
}

response = requests.post(url, headers=headers, json=data)

print(response.status_code)
print(response.json())

​
Responses Containing Reasoning Information

When reasoning is enabled, the API returns results that include reasoning data: 
{
  "id": "resp_051e00420efb9e150069aff6a18418819591abb7ce5f8487ed",
  "object": "response",
  "created_at": 1773139617,
  "status": "completed",
  "background": false,
  "completed_at": 1773139621,
  "content_filters": [
    {
      "blocked": false,
      "source_type": "completion",
      "content_filter_raw": [],
      "content_filter_results": {},
      "content_filter_offsets": {
        "start_offset": 0,
        "end_offset": 1147,
        "check_offset": 0
      }
    }
  ],
  "error": null,
  "frequency_penalty": 0.0,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": 5000,
  "max_tool_calls": null,
  "model": "gpt-54",
  "output": [
    {
      "id": "rs_051e00420efb9e150069aff6a32f948195996db3ff98314ef2",
      "type": "reasoning",
      "summary": []
    },
    {
      "id": "msg_051e00420efb9e150069aff6a33d808195825716a666d8ba8b",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "logprobs": [],
          "text": "The sky looks blue because of how sunlight interacts with Earth’s atmosphere.\n\n1. **Sunlight isn’t just “white”**\nSunlight is made of many colors (red, orange, yellow, green, blue, violet), each with different wavelengths.\n\n2. **Air scatters short wavelengths more**\nAs sunlight passes through the atmosphere, it hits gas molecules and tiny particles.\n- Shorter wavelengths (blue, violet) are scattered in all directions much more than longer wavelengths (red, orange).\n- This effect is called **Rayleigh scattering**.\n\n3. **We see more blue than violet**\n- Our eyes are more sensitive to blue than to violet.\n- Some violet light is also absorbed higher in the atmosphere.\nSo the scattered light we perceive is mostly blue.\n\n4. **Why sunsets are red/orange**\nAt sunrise and sunset, sunlight passes through much more atmosphere.\n- Most of the blue light gets scattered out of the direct path.\n- The remaining light reaching your eyes from the Sun is richer in reds and oranges."
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0.0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": null,
  "reasoning": {
    "effort": "high",
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "store": true,
  "temperature": 1.0,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 1.0,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 35,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 267,
    "output_tokens_details": {
      "reasoning_tokens": 29
    },
    "total_tokens": 302
  },
  "user": null,
  "metadata": {}
}

​
Usage Recommendations

  1. Choose the appropriate reasoning effort level: Use high for complex issues and low for simple tasks.
  2. Consider token usage: Reasoning will increase token consumption.
  3. Utilize streaming: For longer reasoning chains, streaming can enhance user experience.
  4. Provide context: Give the model sufficient context to enable effective reasoning.
Last updated: 2026-06-01