Chat

Chat Completions

Query LLM using text and, for vision-capable models, image data. This endpoint supports multiple models (up to 5, comma-separated) in the model field. Specify the appropriate request format depending on whether the model is text-based or vision-capable.

An array of responses: will be returned for multi-model queries.

Please refer to the ChatCompletionRequest for text-based models and VisionChatCompletionRequest for vision-capable models for detailed request formats.

post/v1/chat/completions

Request

  • Base URL: https://apipie.ai
  • URL: https://apipie.ai/v1/chat/completions
  • Auth: one of:
    • HTTP bearer
    • API key in header x-api-key

Request body

OR

Example request

{
  "messages": [
    {
      "role": "system",
      "content": "Respond in Swedish."
    },
    {
      "role": "assistant",
      "content": "additional data to help the system answer the users prompt"
    },
    {
      "role": "user",
      "content": "Why the sky is blue?"
    }
  ],
  "user": "12345",
  "inline_cli": "all",
  "model": "gpt-3.5-turbo",
  "provider": "openai",
  "memory": true,
  "mem_session": "test3746",
  "mem_expire": 60,
  "mem_clear": 1,
  "mem_msgs": 10,
  "mem_length": 20,
  "shortMem": 3,
  "longMem": 2,
  "rag_tune": "my-files",
  "routing": "perf",
  "temperature": 1,
  "top_p": 1,
  "repetition_penalty": 1,
  "n": 1,
  "beam_size": 1,
  "search_whitelist": [
    "apnews.com",
    "bbc.com",
    "reuters.com"
  ],
  "search_blacklist": [
    "cnn.com",
    "foxnews.com"
  ],
  "web_search_options": {
    "search_context_size": "medium"
  },
  "search_provider": "valyu",
  "search_lang": "en",
  "search_geo": "US",
  "max_tokens": 300,
  "stream_errors": true,
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state, e.g., San Francisco, CA"
            },
            "unit": {
              "type": "string",
              "enum": [
                "celsius",
                "fahrenheit"
              ]
            }
          },
          "required": [
            "location"
          ]
        }
      }
    }
  ],
  "tool_choice": "auto",
  "tools_model": "claude-3-5-sonnet",
  "integrity": 12,
  "integrity_model": "gpt-3.5-turbo"
}

Response

Result of the Query

idstring required

Unique identifier for the completion.

objectstring required

Type of the returned object, usually set to chat.completion.

createdinteger required

UTC timestamp of when the completion was created.

providerstring required

Provider of the AI service.

modelstring required

AI model used for generating the completion.

search_lengthinteger

Character count augmented to the prompt by the search.

search_latency_msinteger

Latency in milliseconds added by the search and processing.

system_fingerprintstring required

Unique fingerprint of the system configuration used.

Changes

No recorded changes to this operation across all 1 revision of this API.