> ## 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. # Inference Result > A single turn in a conversation between a user and an AI system ## What is an Inference Result? An inference result is a single turn in a conversation — one user input paired with one AI output. It belongs to a [session](/concepts/product/version/session) and can optionally include metadata like latency, token usage, cost, and retrieval context (for RAG evaluations). You can create inference results from the [Galtea dashboard](https://platform.galtea.ai/) (using [Endpoint Connections](/concepts/product/endpoint-connection)) or programmatically using the [Galtea SDK](/sdk/api/inference-result/service). ## SDK Integration Manage inference results using the Python SDK ## Inference Result Properties The session to which the inference result belongs. The input text or prompt for the inference result. For most runs this is a plain string. For phone (voice) runs, when the simulated user's audio was captured, this is a content-parts envelope `{"user_message": "", "content": [{"type": "audio", "uri": "...", "transcript": "..."}]}` — the `user_message` field is the canonical scored scalar. Access the envelope via the SDK's `.input_data` field and the spoken transcript via `.input`. The generated output or response for the inference result. For most runs this is a plain string. For phone (voice) runs, when the agent's audio was captured, this is a content-parts envelope `{"assistant_message": "", "content": [{"type": "audio", "uri": "...", "transcript": "..."}]}` — the `assistant_message` field is the canonical scored scalar. Access the envelope via the SDK's `.actual_output_data` field and the scored transcript via `.actual_output`. Retrieval context is not a stored field on the inference result. It is derived from the inference result's [`RETRIEVER` trace spans](/concepts/product/version/session/trace#retrieval-context-in-retriever-traces). You can still supply `retrieval_context` when logging (on create, update, or an agent response); Galtea records it as a `RETRIEVER` trace. If your agent already emits traces, we recommend sending `RETRIEVER` spans directly instead. This keeps one source of truth and lets you capture several retrieval steps per turn, which a single `retrieval_context` value cannot. The latency in milliseconds for the model's response. Token usage information for the inference result. Cost information for the inference result. The W3C trace ID for the root span created during [Direct Inference](/concepts/product/endpoint-connection). This is the same trace ID propagated to your endpoint via the `traceparent` header, enabling correlation with your OTEL-instrumented service. Only present when the inference was generated via Direct Inference with W3C trace context propagation enabled. ## Related How Galtea's concepts connect — diagram + per-entity quick reference. The conversation that groups inference results together. Score inference results using metrics. Capture internal operations linked to inference results.