POST
/
v1
/
responses
curl -X POST https://www.anyfast.ai/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-2025-08-07",
    "input": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "1+2+3+4+5....9985"
          }
        ]
      }
    ],
    "tools": [],
    "text": {
      "format": {
        "type": "text"
      },
      "verbosity": "medium"
    },
    "reasoning": {
      "effort": "medium",
      "summary": "auto"
    },
    "stream": true,
    "store": true
  }'

{
  "id": "resp_01",
  "object": "response",
  "created_at": 1677652288,
  "status": "completed",
  "model": "gpt-5-2025-08-07",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "The sum of 1+2+3+...+9985 = 9985 × 9986 / 2 = 49,855,055"
        }
      ]
    }
  ],
  "reasoning": {
    "effort": "medium",
    "summary": null
  },
  "usage": {
    "input_tokens": 15,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 128,
    "output_tokens_details": {
      "reasoning_tokens": 96
    },
    "total_tokens": 143
  }
}
Create model responses using GPT-5 with thinking mode enabled for deep reasoning and complex problem solving.

​
Request Parameters

​
model
string
required
The model ID to use. Example: gpt-5-2025-08-07
​
input
array
required
Array of input messages. Each message supports input_text content type.
​
tools
array
Array of tools the model may call during generation.
​
text
object
Configuration for model text response.
  • format (object): Output format. type is always "text"
  • verbosity (string): Response verbosity level. Options: low, medium, high
​
reasoning
object
Reasoning configuration for the thinking chain.
  • effort (string): Reasoning effort level. Options: minimal, low, medium, high
  • summary (string): Reasoning summary mode. Options: auto, concise, detailed
​
stream
boolean
default:"false"
Set to true to enable streaming via server-sent events.
​
store
boolean
default:"true"
Whether to store the generated response for later retrieval via API.
curl -X POST https://www.anyfast.ai/v1/responses \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-2025-08-07",
    "input": [
      {
        "role": "user",
        "content": [
          {
            "type": "input_text",
            "text": "1+2+3+4+5....9985"
          }
        ]
      }
    ],
    "tools": [],
    "text": {
      "format": {
        "type": "text"
      },
      "verbosity": "medium"
    },
    "reasoning": {
      "effort": "medium",
      "summary": "auto"
    },
    "stream": true,
    "store": true
  }'

{
  "id": "resp_01",
  "object": "response",
  "created_at": 1677652288,
  "status": "completed",
  "model": "gpt-5-2025-08-07",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "The sum of 1+2+3+...+9985 = 9985 × 9986 / 2 = 49,855,055"
        }
      ]
    }
  ],
  "reasoning": {
    "effort": "medium",
    "summary": null
  },
  "usage": {
    "input_tokens": 15,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 128,
    "output_tokens_details": {
      "reasoning_tokens": 96
    },
    "total_tokens": 143
  }
}