> ## Documentation Index
> Fetch the complete documentation index at: https://docs.galtea.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Create Inference Result

> Create a new inference result log in a session.

## Returns

Returns an [InferenceResult](/concepts/product/version/session/inference-result) object.

## Example

```python theme={"system"}
inference_result = galtea.inference_results.create(
    session_id=session_id,
    input="What is the capital of France?",
    output="Paris",
    latency=150.5,
)
```

## Parameters

<ResponseField name="session_id" type="string" optional>
  The session ID to log the inference result to.

  <Note>Instead of a `session_id`, you can reference an existing session by its own conversation id (see the section below). Provide exactly one of the two.</Note>
</ResponseField>

<Accordion title="Log to an existing session by your own conversation ID">
  If you already created the session via the [sessions API](/sdk/api/session/service) with your own `custom_id`, reference it here with `session_custom_id` plus a `version_id` or `product_id` to append inference results to it. If no matching session exists, the call returns a `400` error — create it first via the sessions API.

  <ResponseField name="session_custom_id" type="string" optional>
    Your own conversation id, as an alternative to `session_id`. Galtea finds an existing session with this id (per version); the session is not created here. Requires `version_id` or `product_id`.
  </ResponseField>

  <ResponseField name="version_id" type="string" optional>
    The version the session is anchored to when using `session_custom_id`.

    <Note>Provide `version_id` or `product_id` (at least one) when using `session_custom_id`. If both are given, `version_id` wins and `product_id` is ignored.</Note>
  </ResponseField>

  <ResponseField name="product_id" type="string" optional>
    Product anchor used when no `version_id` is given with `session_custom_id`: Galtea finds the session with this custom id under the product (across its versions).
  </ResponseField>

  <Note>If no session matches the `session_custom_id` and anchor, the call returns a `400` error. Create the session first via the [sessions API](/sdk/api/session/service).</Note>
</Accordion>

<ResponseField name="input" type="string" optional>
  The input text/prompt.
</ResponseField>

<ResponseField name="output" type="string" optional>
  The generated output/response.
</ResponseField>

<ResponseField name="retrieval_context" type="string" optional>
  Context retrieved for RAG systems.

  <Note>When you set `retrieval_context`, Galtea also records it as a `RETRIEVER` trace on this inference result.</Note>
</ResponseField>

<ResponseField name="latency" type="float" optional>
  Latency in milliseconds.
</ResponseField>

<ResponseField name="usage_info" type="dict[str, int]" optional>
  Information about token usage during the model call.
  Possible keys include:

  * `input_tokens`: Number of input tokens sent to the model.
  * `output_tokens`: Number of output tokens generated by the model.
  * `cache_read_input_tokens`: Number of input tokens read from the cache.
</ResponseField>

<ResponseField name="cost_info" type="dict[str, float]" optional>
  Information about the cost per token during the model call.
  Possible keys include:

  * `cost_per_input_token`: Cost per input token sent to the model.
  * `cost_per_output_token`: Cost per output token generated by the model.
  * `cost_per_cache_read_input_token`: Cost per input token read from the cache.
</ResponseField>

<ResponseField name="conversation_simulator_version" type="string" optional>
  The version of Galtea's conversation simulator used to generate the user message (input). This should only be provided when logging a conversation that was generated using the simulator.
</ResponseField>

<ResponseField name="status" type="str | InferenceResultStatus" optional>
  The initial status of the inference result. Accepts a case-insensitive string or an `InferenceResultStatus` enum value. Valid values: `PENDING`, `GENERATED`, `FAILED`, `SKIPPED`. Other string values are sent to the API unchanged, so values added in newer API versions can be used; the API rejects invalid ones.

  The two typical SDK flows are:

  * **Omit (default)** to create the inference result as `GENERATED` — the right choice when the output is already known at create time.
  * **Pass `PENDING`** to log the inference result before the model call completes, then transition to `GENERATED` or `FAILED` via [`update()`](/sdk/api/inference-result/update) once the call resolves.

  Passing `FAILED` or `SKIPPED` directly is supported for callers that want to log a terminal-state IR explicitly (e.g. recording a known-bad turn or a skipped step).
</ResponseField>