{
  "openapi": "3.1.0",
  "info": {
    "title": "Subconscious API",
    "version": "1.0.0",
    "description": "OpenAI-compatible inference API"
  },
  "servers": [
    {
      "url": "https://api.subconscious.dev/v1"
    }
  ],
  "security": [
    {
      "bearerAuth": []
    }
  ],
  "paths": {
    "/chat/completions": {
      "post": {
        "operationId": "createChatCompletion",
        "summary": "Create a chat completion",
        "description": "Generates a model response for the given conversation. This endpoint is fully compatible with the OpenAI Chat Completions API.",
        "x-codeSamples": [
          {
            "lang": "python",
            "label": "Python (OpenAI SDK)",
            "source": "from openai import OpenAI\n\nclient = OpenAI(\n    api_key=\"your-api-key\",\n    base_url=\"https://api.subconscious.dev/v1\",\n)\n\nresponse = client.chat.completions.create(\n    model=\"subconscious/tim-qwen3.6-27b\",\n    messages=[{\"role\": \"user\", \"content\": \"What is the capital of France?\"}],\n)\n\nprint(response.choices[0].message.content)"
          },
          {
            "lang": "javascript",
            "label": "Node.js (OpenAI SDK)",
            "source": "import OpenAI from \"openai\";\n\nconst client = new OpenAI({\n  apiKey: \"your-api-key\",\n  baseURL: \"https://api.subconscious.dev/v1\",\n});\n\nconst response = await client.chat.completions.create({\n  model: \"subconscious/tim-qwen3.6-27b\",\n  messages: [{ role: \"user\", content: \"What is the capital of France?\" }],\n});\n\nconsole.log(response.choices[0].message.content);"
          },
          {
            "lang": "bash",
            "label": "cURL",
            "source": "curl https://api.subconscious.dev/v1/chat/completions \\\n  -H \"Authorization: Bearer YOUR_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"model\": \"subconscious/tim-qwen3.6-27b\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}]\n  }'"
          }
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "type": "object",
                "required": ["model", "messages"],
                "properties": {
                  "model": {
                    "type": "string",
                    "description": "The model to use for completion.",
                    "enum": ["subconscious/tim-qwen3.6-27b"],
                    "example": "subconscious/tim-qwen3.6-27b"
                  },
                  "messages": {
                    "type": "array",
                    "description": "The conversation history. Each message has a role and content.",
                    "items": {
                      "type": "object",
                      "required": ["role", "content"],
                      "properties": {
                        "role": {
                          "type": "string",
                          "enum": ["system", "user", "assistant"],
                          "description": "The role of the message author."
                        },
                        "content": {
                          "type": "string",
                          "description": "The content of the message."
                        }
                      }
                    },
                    "example": [
                      {"role": "user", "content": "What is the capital of France?"}
                    ]
                  },
                  "stream": {
                    "type": "boolean",
                    "default": false,
                    "description": "If true, responses are streamed as Server-Sent Events. Each event is a ChatCompletionChunk object. The stream ends with `data: [DONE]`."
                  },
                  "max_tokens": {
                    "type": "integer",
                    "description": "Maximum number of tokens to generate in the response."
                  },
                  "max_completion_tokens": {
                    "type": "integer",
                    "description": "An alternative to max_tokens. Maximum number of tokens to generate."
                  },
                  "temperature": {
                    "type": "number",
                    "minimum": 0,
                    "maximum": 2,
                    "description": "Sampling temperature between 0 and 2. Lower values make output more focused and deterministic, while higher values make it more creative."
                  },
                  "top_p": {
                    "type": "number",
                    "minimum": 0,
                    "maximum": 1,
                    "description": "Nucleus sampling parameter. Only considers tokens whose cumulative probability exceeds this threshold."
                  },
                  "frequency_penalty": {
                    "type": "number",
                    "minimum": -2,
                    "maximum": 2,
                    "description": "Penalizes tokens based on their frequency in the text so far."
                  },
                  "presence_penalty": {
                    "type": "number",
                    "minimum": -2,
                    "maximum": 2,
                    "description": "Penalizes tokens based on whether they appear in the text so far."
                  },
                  "stop": {
                    "oneOf": [
                      {"type": "string"},
                      {"type": "array", "items": {"type": "string"}, "maxItems": 4}
                    ],
                    "description": "Up to 4 sequences where the model will stop generating."
                  },
                  "response_format": {
                    "type": "object",
                    "description": "Constrains the response format. Use `{\"type\": \"json_object\"}` for valid JSON or `{\"type\": \"json_schema\", \"json_schema\": {...}}` for schema-constrained output.",
                    "properties": {
                      "type": {
                        "type": "string",
                        "enum": ["text", "json_object", "json_schema"]
                      },
                      "json_schema": {
                        "type": "object",
                        "description": "The JSON schema to constrain the output to. Required when type is json_schema.",
                        "properties": {
                          "name": {
                            "type": "string",
                            "description": "A name for the schema."
                          },
                          "schema": {
                            "type": "object",
                            "description": "The JSON Schema object."
                          }
                        }
                      }
                    }
                  },
                  "stream_options": {
                    "type": "object",
                    "description": "Options for streaming responses.",
                    "properties": {
                      "include_usage": {
                        "type": "boolean",
                        "description": "If true, include token usage in the final streamed chunk."
                      }
                    }
                  },
                  "chat_template_kwargs": {
                    "type": "object",
                    "description": "Subconscious extension. Controls model-specific features like thinking mode.",
                    "properties": {
                      "enable_thinking": {
                        "type": "boolean",
                        "description": "If true, enables step-by-step reasoning. The model will output its reasoning in <think> tags before the final answer."
                      }
                    }
                  }
                }
              }
            }
          }
        },
        "responses": {
          "200": {
            "description": "Successful completion",
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "id": {
                      "type": "string",
                      "description": "A unique identifier for the completion.",
                      "example": "chatcmpl-abc123"
                    },
                    "object": {
                      "type": "string",
                      "enum": ["chat.completion"],
                      "description": "The object type."
                    },
                    "created": {
                      "type": "integer",
                      "description": "Unix timestamp of when the completion was created.",
                      "example": 1716000000
                    },
                    "model": {
                      "type": "string",
                      "description": "The model used for the completion.",
                      "example": "subconscious/tim-qwen3.6-27b"
                    },
                    "choices": {
                      "type": "array",
                      "items": {
                        "type": "object",
                        "properties": {
                          "index": {
                            "type": "integer"
                          },
                          "message": {
                            "type": "object",
                            "properties": {
                              "role": {
                                "type": "string",
                                "enum": ["assistant"]
                              },
                              "content": {
                                "type": "string",
                                "description": "The generated message content."
                              }
                            }
                          },
                          "finish_reason": {
                            "type": "string",
                            "enum": ["stop", "length"],
                            "description": "The reason the model stopped generating."
                          }
                        }
                      }
                    },
                    "usage": {
                      "type": "object",
                      "properties": {
                        "prompt_tokens": {
                          "type": "integer",
                          "description": "Number of tokens in the prompt."
                        },
                        "completion_tokens": {
                          "type": "integer",
                          "description": "Number of tokens in the generated completion."
                        },
                        "total_tokens": {
                          "type": "integer",
                          "description": "Total number of tokens used."
                        }
                      }
                    }
                  }
                }
              }
            }
          },
          "400": {
            "description": "Bad request due to invalid parameters or unsupported options"
          },
          "401": {
            "description": "Unauthorized because of a missing or invalid API key"
          },
          "429": {
            "description": "Rate limited due to too many requests or tokens per minute"
          },
          "500": {
            "description": "Internal server error"
          }
        }
      }
    },
    "/messages": {
      "post": {
        "operationId": "createMessage",
        "summary": "Create a message",
        "description": "Generates a model response for the given conversation. This endpoint is fully compatible with the Anthropic Messages API, so you can use the Anthropic SDK by pointing its base URL at Subconscious.",
        "security": [
          {"apiKeyAuth": []},
          {"bearerAuth": []}
        ],
        "x-codeSamples": [
          {
            "lang": "python",
            "label": "Python (Anthropic SDK)",
            "source": "from anthropic import Anthropic\n\nclient = Anthropic(\n    auth_token=\"your-api-key\",\n    base_url=\"https://api.subconscious.dev\",\n)\n\nmessage = client.messages.create(\n    model=\"subconscious/tim-qwen3.6-27b\",\n    max_tokens=1024,\n    messages=[{\"role\": \"user\", \"content\": \"What is the capital of France?\"}],\n)\n\nprint(message.content[0].text)"
          },
          {
            "lang": "javascript",
            "label": "Node.js (Anthropic SDK)",
            "source": "import Anthropic from \"@anthropic-ai/sdk\";\n\nconst client = new Anthropic({\n  authToken: \"your-api-key\",\n  baseURL: \"https://api.subconscious.dev\",\n});\n\nconst message = await client.messages.create({\n  model: \"subconscious/tim-qwen3.6-27b\",\n  max_tokens: 1024,\n  messages: [{ role: \"user\", content: \"What is the capital of France?\" }],\n});\n\nconsole.log(message.content[0].text);"
          },
          {
            "lang": "bash",
            "label": "cURL",
            "source": "curl https://api.subconscious.dev/v1/messages \\\n  -H \"x-api-key: YOUR_API_KEY\" \\\n  -H \"anthropic-version: 2023-06-01\" \\\n  -H \"content-type: application/json\" \\\n  -d '{\n    \"model\": \"subconscious/tim-qwen3.6-27b\",\n    \"max_tokens\": 1024,\n    \"messages\": [{\"role\": \"user\", \"content\": \"What is the capital of France?\"}]\n  }'"
          }
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "type": "object",
                "required": ["model", "messages", "max_tokens"],
                "properties": {
                  "model": {
                    "type": "string",
                    "description": "The model to use for completion.",
                    "enum": ["subconscious/tim-qwen3.6-27b"],
                    "example": "subconscious/tim-qwen3.6-27b"
                  },
                  "messages": {
                    "type": "array",
                    "description": "The conversation history. Each message has a role and content. Content is either a string or an array of content blocks (text, image, tool_use, tool_result, thinking).",
                    "items": {
                      "type": "object",
                      "required": ["role", "content"],
                      "properties": {
                        "role": {
                          "type": "string",
                          "enum": ["user", "assistant"],
                          "description": "The role of the message author. System prompts are passed via the top-level `system` field, not as a message."
                        },
                        "content": {
                          "oneOf": [
                            {"type": "string"},
                            {
                              "type": "array",
                              "items": {
                                "type": "object",
                                "description": "A content block. `type` selects the block shape: `text` ({text}), `image` ({source}), `tool_use` ({id, name, input}), `tool_result` ({tool_use_id, content, is_error}), `thinking` ({thinking}).",
                                "properties": {
                                  "type": {
                                    "type": "string",
                                    "enum": ["text", "image", "tool_use", "tool_result", "thinking"]
                                  },
                                  "text": {"type": "string"},
                                  "source": {
                                    "type": "object",
                                    "description": "Image source. Either base64 ({type:\"base64\", media_type, data}) or url ({type:\"url\", url}).",
                                    "properties": {
                                      "type": {"type": "string", "enum": ["base64", "url"]},
                                      "media_type": {"type": "string", "example": "image/png"},
                                      "data": {"type": "string"},
                                      "url": {"type": "string"}
                                    }
                                  },
                                  "id": {"type": "string", "description": "tool_use block id."},
                                  "name": {"type": "string", "description": "tool_use block tool name."},
                                  "input": {"type": "object", "description": "tool_use block arguments."},
                                  "tool_use_id": {"type": "string", "description": "tool_result block: the id of the tool_use it answers."},
                                  "content": {"description": "tool_result block content (string or array of blocks)."},
                                  "is_error": {"type": "boolean", "description": "tool_result block: whether the tool call errored."},
                                  "thinking": {"type": "string", "description": "thinking block reasoning text."}
                                }
                              }
                            }
                          ]
                        }
                      }
                    },
                    "example": [
                      {"role": "user", "content": "What is the capital of France?"}
                    ]
                  },
                  "max_tokens": {
                    "type": "integer",
                    "description": "The maximum number of tokens to generate before stopping. Required.",
                    "example": 1024
                  },
                  "system": {
                    "oneOf": [
                      {"type": "string"},
                      {"type": "array", "items": {"type": "object", "properties": {"type": {"type": "string", "enum": ["text"]}, "text": {"type": "string"}}}}
                    ],
                    "description": "A system prompt: a string or an array of text content blocks."
                  },
                  "stream": {
                    "type": "boolean",
                    "default": false,
                    "description": "If true, responses are streamed as Server-Sent Events using the Anthropic event protocol (`message_start`, `content_block_start`, `content_block_delta`, `content_block_stop`, `message_delta`, `message_stop`)."
                  },
                  "temperature": {
                    "type": "number",
                    "minimum": 0,
                    "maximum": 1,
                    "description": "Amount of randomness injected into the response."
                  },
                  "top_p": {
                    "type": "number",
                    "minimum": 0,
                    "maximum": 1,
                    "description": "Nucleus sampling parameter."
                  },
                  "top_k": {
                    "type": "integer",
                    "description": "Only sample from the top K options for each subsequent token."
                  },
                  "stop_sequences": {
                    "type": "array",
                    "items": {"type": "string"},
                    "description": "Custom text sequences that will cause the model to stop generating."
                  },
                  "tools": {
                    "type": "array",
                    "description": "Definitions of tools the model may use.",
                    "items": {
                      "type": "object",
                      "required": ["name", "input_schema"],
                      "properties": {
                        "name": {"type": "string"},
                        "description": {"type": "string"},
                        "input_schema": {"type": "object", "description": "JSON Schema for the tool's input."}
                      }
                    }
                  },
                  "tool_choice": {
                    "type": "object",
                    "description": "How the model should use the provided tools.",
                    "properties": {
                      "type": {"type": "string", "enum": ["auto", "any", "tool"]},
                      "name": {"type": "string", "description": "Required when type is `tool`: the tool the model must use."}
                    }
                  },
                  "thinking": {
                    "type": "object",
                    "description": "Enable extended thinking. When enabled, the response includes `thinking` content blocks before the final `text` block.",
                    "properties": {
                      "type": {"type": "string", "enum": ["enabled"]},
                      "budget_tokens": {"type": "integer", "description": "Token budget for reasoning."}
                    }
                  },
                  "metadata": {
                    "type": "object",
                    "description": "An object describing metadata about the request.",
                    "properties": {
                      "user_id": {"type": "string"}
                    }
                  },
                  "chat_template_kwargs": {
                    "type": "object",
                    "description": "Subconscious extension. Controls model-specific features such as auto-compaction (Subconscious Cache).",
                    "properties": {
                      "enable_auto_compaction": {
                        "type": "boolean",
                        "description": "If false, disables automatic context compaction so you can control Subconscious Cache manually."
                      }
                    }
                  }
                }
              }
            }
          }
        },
        "responses": {
          "200": {
            "description": "Successful message",
            "content": {
              "application/json": {
                "schema": {
                  "type": "object",
                  "properties": {
                    "id": {
                      "type": "string",
                      "description": "A unique identifier for the message.",
                      "example": "msg_abc123"
                    },
                    "type": {
                      "type": "string",
                      "enum": ["message"],
                      "description": "The object type."
                    },
                    "role": {
                      "type": "string",
                      "enum": ["assistant"]
                    },
                    "content": {
                      "type": "array",
                      "description": "An array of content blocks. Text blocks ({type:\"text\", text}), thinking blocks ({type:\"thinking\", thinking, signature}), and tool_use blocks ({type:\"tool_use\", id, name, input}).",
                      "items": {
                        "type": "object",
                        "properties": {
                          "type": {"type": "string", "enum": ["text", "thinking", "tool_use"]},
                          "text": {"type": "string"},
                          "thinking": {"type": "string"},
                          "signature": {"type": "string"},
                          "id": {"type": "string"},
                          "name": {"type": "string"},
                          "input": {"type": "object"}
                        }
                      }
                    },
                    "model": {
                      "type": "string",
                      "example": "subconscious/tim-qwen3.6-27b"
                    },
                    "stop_reason": {
                      "type": "string",
                      "enum": ["end_turn", "max_tokens", "tool_use"],
                      "description": "The reason the model stopped generating."
                    },
                    "stop_sequence": {
                      "type": ["string", "null"],
                      "description": "The custom stop sequence that was generated, if any."
                    },
                    "usage": {
                      "type": "object",
                      "properties": {
                        "input_tokens": {"type": "integer", "description": "Number of input tokens used."},
                        "output_tokens": {"type": "integer", "description": "Number of output tokens generated."},
                        "cache_read_input_tokens": {"type": "integer", "description": "Number of input tokens read from cache."}
                      }
                    }
                  }
                }
              }
            }
          },
          "400": {
            "description": "Bad request due to invalid parameters or unsupported options"
          },
          "401": {
            "description": "Unauthorized because of a missing or invalid API key"
          },
          "429": {
            "description": "Rate limited due to too many requests or tokens per minute"
          },
          "500": {
            "description": "Internal server error"
          }
        }
      }
    }
  },
  "components": {
    "securitySchemes": {
      "bearerAuth": {
        "type": "http",
        "scheme": "bearer",
        "description": "API key from your Subconscious dashboard"
      },
      "apiKeyAuth": {
        "type": "apiKey",
        "in": "header",
        "name": "x-api-key",
        "description": "API key from your Subconscious dashboard. Accepted by the Anthropic Messages endpoints in place of the Authorization header, for use with the Anthropic SDK."
      }
    }
  }
}