Crate openrouter_rust 

OpenRouter Rust Client

A comprehensive, type-safe Rust client library for the OpenRouter API.

Features

• Chat Completions API: Full support for /v1/chat/completions endpoint
• Responses API (Beta): Support for the new /v1/responses endpoint
• Anthropic Messages API: Support for /v1/messages endpoint
• Embeddings API: Text and image embeddings support
• Streaming: Real-time streaming responses using Server-Sent Events
• Models API: List and filter available models
• Providers API: List available providers
• Generation API: Retrieve generation metadata
• Type-Safe: Comprehensive types for all API requests and responses
• Builder Pattern: Ergonomic builder APIs for constructing requests
• Error Handling: Detailed error types for different failure scenarios

Quick Start

use openrouter_rust::{OpenRouterClient, ChatCompletionBuilder};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    // Create a client
    let client = OpenRouterClient::builder()
        .api_key("your-api-key")
        .build()?;

    // Build a request
    let request = ChatCompletionBuilder::new("openai/gpt-3.5-turbo")
        .user_message("What is the meaning of life?")
        .build();

    // Send the request
    let response = client.chat_completion(request).await?;
     
    if let Some(ref content) = response.choices[0].message.content {
        println!("Response: {}", content);
    }
     
    Ok(())
}

Feature Flags

• chat (default): Enable chat completions API
• responses: Enable Responses API (Beta)
• streaming (default): Enable streaming support
• embeddings: Enable embeddings API
• anthropic: Enable Anthropic Messages API
• providers: Enable providers API
• models: Enable models API
• generations: Enable generation metadata API

Examples

See the examples/ directory for more comprehensive examples.

Re-exports

pub use client::OpenRouterClient;

pub use client::OpenRouterClientBuilder;

pub use error::OpenRouterError;

pub use error::Result;

pub use chat::ChatCompletionBuilder;

pub use chat::ChatCompletionRequest;

pub use chat::ChatCompletionResponse;

pub use chat::ChatCompletionBuilder as ChatRequestBuilder;

pub use chat::Choice;

pub use streaming::ChatCompletionStream;

pub use streaming::ChatCompletionChunk;

pub use streaming::StreamingChoice;

pub use streaming::DeltaMessage;

pub use streaming::collect_stream;

pub use providers::Provider;

pub use providers::ProvidersResponse;

pub use models::Model;

pub use models::ModelsResponse;

pub use models::ModelsCountResponse;

pub use models::PublicPricing;

pub use models::ModelArchitecture;

pub use models::TopProviderInfo;

pub use models::PerRequestLimits;

pub use models::DefaultParameters;

pub use models::ListModelsParams;

pub use generations::GenerationResponse;

pub use generations::GenerationData;

pub use generations::ProviderResponse;

pub use types::Message;

pub use types::Role;

pub use types::Function;

pub use types::Tool;

pub use types::ToolChoice;

pub use types::ResponseFormat;

pub use types::Usage;

pub use types::Plugin;

pub use types::ProviderPreferences;

Modules

chat

client

error

generations

models

providers

streaming

types