# Response Object

div
strong
🔨 In Development
 — This section is still being developed and may change.


Represents a model response generated by the Aitronos API. Contains the generated output, metadata about the generation process, and usage statistics.

## Properties

**`id`** string

Unique identifier for the response. Format: `resp_` followed by alphanumeric characters.

**`object`** string

Object type identifier. Always `response`.

**`createdAt`** integer

Unix timestamp (seconds) when the response was created.

**`model`** string

The model used to generate the response. Example: `gpt-4o`, `claude-3-5-sonnet`, `o3-preview`.

**`choices`** array

Array of completion choices generated by the model. Typically contains one choice unless `n` parameter is used.

details
summary
Show structure
Each choice object contains:

**`index`** integer

The index of this choice in the array.

**`message`** object

The generated message content.

details
summary
Show message properties
**`role`** string

The role of the message. Always `assistant` for model responses.

**`content`** string or array

The generated text content or structured content array.

**`toolCalls`** array optional

Array of tool calls made by the model during generation.

details
summary
Show tool call structure
**`id`** string

Unique identifier for the tool call.

**`type`** string

Type of tool. One of `function`, `fileSearch`, `webSearch`, `codeInterpreter`, `image_generation`, `computer_use_preview`, `mcp`.

**`function`** object optional

Function call details (when type is `function`).

**`name`** string

Name of the function called.

**`arguments`** string

JSON string of function arguments.

**`refusal`** string optional

If the model refused to generate content, this contains the refusal explanation.

**`finishReason`** string

Reason why the model stopped generating. Values:

- `stop` - Natural completion
- `length` - Reached max output synapses limit
- `toolCalls` - Model called tools
- `content_filter` - Content filtered by moderation
- `function_call` - Deprecated, use `toolCalls`


**`logprobs`** object optional

Log probability information for generated tokens (when `logprobs: true`).

details
summary
Show logprobs structure
**`content`** array

Array of token log probability objects.

**`refusal`** array optional

Log probabilities for refusal content.

**`usage`** object

Token and synapse usage statistics for this request.

details
summary
Show usage properties
**`inputNeurons`** integer

Number of neurons consumed by input context (prompt, conversation history, system instructions).

**`outputSynapses`** integer

Number of synapses generated in the response output.

**`totalSynapses`** integer

Total synapses consumed (input neurons + output synapses + reasoning synapses).

**`reasoningSynapses`** integer optional

Synapses used for internal reasoning (reasoning models only).

**`cacheReadNeurons`** integer optional

Neurons read from prompt cache (when caching is enabled).

**`cacheCreationNeurons`** integer optional

Neurons written to prompt cache for future requests.

**`organizationId`** string

The organization ID that owns this response.

**`threadId`** string optional

The thread ID this response belongs to (if part of a conversation thread).

**`metadata`** object optional

Custom metadata attached to the response request.

**`systemFingerprint`** string optional

Fingerprint representing the backend configuration used for this response. Useful for debugging and tracking model versions.

**`serviceTier`** string optional

The service tier used for processing. Values: `auto`, `default`.

## Returns

A [ResponseObjectResponse](#responseobjectresponse) object containing the API response data.

## Example Response

Text Response

```json
{
  "id": "resp_abc123xyz789",
  "object": "response",
  "createdAt": 1728057600,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris. It has been the country's capital since 508 CE and is known for its art, culture, and iconic landmarks like the Eiffel Tower."
      },
      "finishReason": "stop",
      "logprobs": null
    }
  ],
  "usage": {
    "inputNeurons": 24,
    "outputSynapses": 38,
    "totalSynapses": 62,
    "cacheReadNeurons": 0,
    "cacheCreationNeurons": 0
  },
  "organizationId": "org_xyz789",
  "threadId": null,
  "metadata": {},
  "systemFingerprint": "fp_2024_10_04",
  "serviceTier": "default"
}
```

With Tool Calls

```json
{
  "id": "resp_def456uvw123",
  "object": "response",
  "createdAt": 1728057650,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "toolCalls": [
          {
            "id": "call_abc123",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"location\":\"San Francisco\",\"unit\":\"celsius\"}"
            }
          }
        ]
      },
      "finishReason": "tool_calls",
      "logprobs": null
    }
  ],
  "usage": {
    "inputNeurons": 156,
    "outputSynapses": 28,
    "totalSynapses": 184
  },
  "organizationId": "org_xyz789",
  "threadId": "thread_conversation_001",
  "metadata": {
    "user_id": "user_12345",
    "session_id": "sess_abc"
  },
  "systemFingerprint": "fp_2024_10_04",
  "serviceTier": "default"
}
```

With Reasoning

```json
{
  "id": "resp_reasoning_789",
  "object": "response",
  "createdAt": 1728057700,
  "model": "o3-preview",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "To solve this problem, we need to find the optimal path through the graph. After analyzing all possible routes, the shortest path is A → C → E → G with a total distance of 47 units."
      },
      "finishReason": "stop",
      "logprobs": null
    }
  ],
  "usage": {
    "inputNeurons": 892,
    "outputSynapses": 156,
    "reasoningSynapses": 2847,
    "totalSynapses": 3895
  },
  "organizationId": "org_xyz789",
  "threadId": null,
  "metadata": {},
  "systemFingerprint": "fp_o3_2024_10_04",
  "serviceTier": "default"
}
```

Content Filtered

```json
{
  "id": "resp_filtered_456",
  "object": "response",
  "createdAt": 1728057750,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "refusal": "I cannot provide instructions for creating harmful substances or devices. This request violates our safety guidelines."
      },
      "finishReason": "content_filter",
      "logprobs": null
    }
  ],
  "usage": {
    "inputNeurons": 45,
    "outputSynapses": 23,
    "totalSynapses": 68
  },
  "organizationId": "org_xyz789",
  "threadId": null,
  "metadata": {},
  "systemFingerprint": "fp_2024_10_04",
  "serviceTier": "default"
}
```

## Related

- [Create response](/docs/api-reference/responses/create) - Generate a new model response
- [Streaming events](/docs/api-reference/objects/streaming-events) - Real-time response streaming
- [Input message](/docs/api-reference/objects/input-message) - Input message format