For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
  • About NVIDIA NeMo Relay
    • Overview
    • Architecture
    • Ecosystem
    • Concepts
    • Release Notes
  • Getting Started
    • Agent Runtime Primer
    • Prerequisites
    • Installation
    • Configuration / Setup
    • Quick Start
  • NVIDIA NeMo Relay CLI
    • About
    • Basic Usage
    • Claude Code
    • Codex
    • Cursor
    • Hermes Agent
  • Supported Integrations
    • About
    • OpenClaw Plugin Guide
    • LangChain Integration Guide
    • LangGraph Integration Guide
    • Deep Agents Integration Guide
  • Instrument Applications
    • About
    • Adding Scopes and Marks
    • Instrument a Tool Call
    • Instrument an LLM Call
    • Add Middleware
    • Code Examples
  • Observability Plugin
    • About
    • Configuration
    • Agent Trajectory Interchange Format (ATIF)
    • Agent Trajectory Observability Format (ATOF)
    • OpenTelemetry
    • OpenInference
  • Adaptive Plugin
    • About
    • Configuration
    • Adaptive Cache Governor (ACG)
    • Adaptive Hints
  • NeMo Guardrails Plugin
    • About
    • Configuration
  • Integrate into Frameworks
    • About
    • Adding Scopes
    • Wrap Tool Calls
    • Wrap LLM Calls
    • Handle Non-Serializable Data
    • Using Codecs
    • Provider Codecs
    • Provider Response Codecs
    • Code Examples
  • Build Plugins
    • About
    • Define a Plugin
    • Validate Plugin Configuration
    • Plugin Configuration Files
    • Register Plugin Behavior
    • Design Plugin Configuration
    • NeMo Guardrails Example Plugin
    • Code Examples
  • Contribute
    • About
    • Development Setup
    • Workflow and Reviews
    • Testing and Documentation
  • Reference
    • APIs
      • Python Library Reference
      • Node.js Library Reference
      • Rust Library Reference
        • nemo-relay
          • api
          • codec
            • anthropic
            • openai_chat
            • openai_responses
            • request
            • response
              • AnnotatedLlmResponse
              • ResponseToolCall
              • Usage
              • ApiSpecificResponse
              • FinishReason
            • streaming
            • traits
          • config_editor
          • error
          • json
          • observability
          • plugin
          • plugins
          • stream
          • editor_config
        • nemo-relay-adaptive
        • nemo-relay-ffi
    • Performance
  • Resources
    • Support and FAQs
    • Glossary
    • Troubleshooting Guide
    • Community
    • Legal
NVIDIANVIDIA
Developer-friendly docs for your API
Privacy Policy | Your Privacy Choices | Terms of Service | Accessibility | Corporate Policies | Product Security | Contact

Copyright © 2026, NVIDIA Corporation.

LogoLogo
On this page
  • Variants
  • OpenAIChat
  • Fields
  • logprobs: Option<Json>
  • system_fingerprint: Option<String>
  • service_tier: Option<String>
  • OpenAIResponses
  • Fields
  • output_items: Option<Vec<Json>>
  • status: Option<String>
  • incomplete_details: Option<Json>
  • previous_response_id: Option<String>
  • store: Option<bool>
  • service_tier: Option<String>
  • truncation: Option<Json>
  • reasoning: Option<Json>
  • input_tokens_details: Option<Json>
  • output_tokens_details: Option<Json>
  • AnthropicMessages
  • Fields
  • object_type: Option<String>
  • role: Option<String>
  • stop_reason: Option<String>
  • stop_sequence: Option<String>
  • service_tier: Option<String>
  • container: Option<Json>
  • content_blocks: Option<Vec<Json>>
  • Custom
  • Fields
  • api_name: String
  • data: Json
  • Trait Implementations
  • impl Clone for ApiSpecificResponse
  • clone
  • clone_from
  • impl Debug for ApiSpecificResponse
  • fmt
  • impl<'de> Deserialize<'de> for ApiSpecificResponse
  • deserialize
  • impl PartialEq for ApiSpecificResponse
  • eq
  • ne
  • impl Serialize for ApiSpecificResponse
  • serialize
  • impl StructuralPartialEq for ApiSpecificResponse
ReferenceAPIsRust Library Referencenemo-relaycodecresponse

Enum ApiSpecific Response

||View as Markdown|
Previous

Struct Usage

Next

Enum Finish Reason

Generated from cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-ffi.

pub enum ApiSpecificResponse {
    OpenAIChat {
        logprobs: Option<Json>,
        system_fingerprint: Option<String>,
        service_tier: Option<String>,
    },
    OpenAIResponses {
        output_items: Option<Vec<Json>>,
        status: Option<String>,
        incomplete_details: Option<Json>,
        previous_response_id: Option<String>,
        store: Option<bool>,
        service_tier: Option<String>,
        truncation: Option<Json>,
        reasoning: Option<Json>,
        input_tokens_details: Option<Json>,
        output_tokens_details: Option<Json>,
    },
    AnthropicMessages {
        object_type: Option<String>,
        role: Option<String>,
        stop_reason: Option<String>,
        stop_sequence: Option<String>,
        service_tier: Option<String>,
        container: Option<Json>,
        content_blocks: Option<Vec<Json>>,
    },
    Custom {
        api_name: String,
        data: Json,
    },
}

API-specific response data that cannot be normalized across providers.

Each variant captures fields unique to a particular LLM API, stored via internal tagging on the "api" key.

Variants

OpenAIChat

OpenAIChat

OpenAI Chat Completions-specific fields.

Fields

logprobs: Option<Json>

Token-level log probabilities (raw JSON, too complex to normalize).

system_fingerprint: Option<String>

System fingerprint for reproducibility.

service_tier: Option<String>

Processing tier used (e.g., “default”).

OpenAIResponses

OpenAIResponses

OpenAI Responses API-specific fields.

Fields

output_items: Option<Vec<Json>>

Full output items array for direct access.

status: Option<String>

Response status (e.g., “completed”, “incomplete”).

incomplete_details: Option<Json>

Details about why the response is incomplete.

previous_response_id: Option<String>

Echoed previous response ID for conversation continuation.

store: Option<bool>

Whether this response is marked for server-side storage.

service_tier: Option<String>

Service tier used for the response.

truncation: Option<Json>

Truncation behavior metadata.

reasoning: Option<Json>

Reasoning configuration/result metadata.

input_tokens_details: Option<Json>

Raw input token details payload.

output_tokens_details: Option<Json>

Raw output token details payload.

AnthropicMessages

AnthropicMessages

Anthropic Messages API-specific fields.

Fields

object_type: Option<String>

Anthropic object type (typically "message").

role: Option<String>

Anthropic response role (typically "assistant").

stop_reason: Option<String>

Raw Anthropic stop_reason.

stop_sequence: Option<String>

Which stop sequence was matched (if any).

service_tier: Option<String>

Anthropic response service tier when present.

container: Option<Json>

Anthropic container payload when present.

content_blocks: Option<Vec<Json>>

Full content blocks array for direct access.

Custom

Custom

Custom/unknown API - catch-all for user-implemented codecs.

Fields

api_name: String

API identifier.

data: Json

Opaque API-specific data.

Trait Implementations

impl Clone for ApiSpecificResponse

impl Clone for ApiSpecificResponse

clone

fn clone(&self) -> ApiSpecificResponse

clone_from

fn clone_from(&mut self, source: &Self)

impl Debug for ApiSpecificResponse

impl Debug for ApiSpecificResponse

fmt

fn fmt(&self, f: &mut Formatter<'_>) -> Result

impl<'de> Deserialize<'de> for ApiSpecificResponse

impl<'de> Deserialize<'de> for ApiSpecificResponse

deserialize

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
    __D: Deserializer<'de>,

impl PartialEq for ApiSpecificResponse

impl PartialEq for ApiSpecificResponse

eq

fn eq(&self, other: &ApiSpecificResponse) -> bool

ne

fn ne(&self, other: &Rhs) -> bool

impl Serialize for ApiSpecificResponse

impl Serialize for ApiSpecificResponse

serialize

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>where
    __S: Serializer,

impl StructuralPartialEq for ApiSpecificResponse

impl StructuralPartialEq for ApiSpecificResponse