Ruby SDK

The Anthropic Ruby library provides convenient access to the Claude API from any Ruby 3.2.0+ application. It ships with comprehensive types and docstrings in Yard, RBS, and RBI. The standard library's net/http is used as the HTTP transport, with connection pooling through the connection_pool gem.

Installation

Add the gem to your application's Gemfile with Bundler:

bundle add anthropic

Requirements

Ruby 3.2.0 or higher.

Usage

anthropic = Anthropic::Client.new(
  api_key: ENV["ANTHROPIC_API_KEY"] # This is the default and can be omitted
)

message = anthropic.messages.create(
  max_tokens: 1024,
  messages: [{role: "user", content: "Hello, Claude"}],
  model: :"claude-opus-5"
)

message.content.each do |block|
  puts block.text if block.type == :text
end

For authentication options including Workload Identity Federation, see Authentication. If your API key is a personal or service account key with access to multiple workspaces, set the workspace ID in the anthropic-workspace-id request header; Select a workspace shows the per-request option for this SDK.

Streaming

The SDK provides support for streaming responses using Server-Sent Events (SSE).

anthropic = Anthropic::Client.new
stream = anthropic.messages.stream(
  max_tokens: 1024,
  messages: [{role: "user", content: "Hello, Claude"}],
  model: :"claude-opus-5"
)

stream.each do |message|
  puts(message.type)
end

Streaming helpers

This library provides several conveniences for streaming messages, for example:

anthropic = Anthropic::Client.new
stream = anthropic.messages.stream(
  max_tokens: 1024,
  messages: [{role: :user, content: "Say hello there!"}],
  model: :"claude-opus-5"
)

stream.text.each do |text|
  print(text)
end

Streaming with anthropic.messages.stream(...) exposes various helpers including accumulation and SDK-specific events.

Input schema and tool calling

The SDK provides helper mechanisms to define structured data classes for tools and let Claude automatically execute them. For detailed documentation on tool use patterns including the tool runner, see Tool Runner (SDK).

anthropic = Anthropic::Client.new
class CalculatorInput < Anthropic::BaseModel
  required :lhs, Float
  required :rhs, Float
  required :operator, Anthropic::InputSchema::EnumOf[:+, :-, :*, :/]
end

class Calculator < Anthropic::BaseTool
  input_schema CalculatorInput

  def call(expr)
    expr.lhs.public_send(expr.operator, expr.rhs)
  end
end

# Automatically handles tool execution loop
anthropic.beta.messages.tool_runner(
  model: "claude-opus-5",
  max_tokens: 1024,
  messages: [{role: "user", content: "What's 15 * 7?"}],
  tools: [Calculator.new]
).each_message { |message| puts message.content }

Structured outputs

For complete structured outputs documentation including Ruby examples, see Structured outputs.

Handling errors

When the library is unable to connect to the API, or if the API returns a non-success status code (that is, 4xx or 5xx response), a subclass of Anthropic::Errors::APIError is raised:

anthropic = Anthropic::Client.new
begin
  message = anthropic.messages.create(
    max_tokens: 1024,
    messages: [{role: "user", content: "Hello, Claude"}],
    model: :"claude-opus-5"
  )
rescue Anthropic::Errors::APIConnectionError => e
  puts("The server could not be reached")
  puts(e.cause)  # an underlying Exception, likely raised within `net/http`
rescue Anthropic::Errors::RateLimitError => e
  puts("A 429 status code was received; we should back off a bit.")
rescue Anthropic::Errors::APIStatusError => e
  puts("Another non-200-range status code was received")
  puts(e.status)
end

Error codes are as follows:

Retries

Certain errors will be automatically retried 2 times by default, with a short exponential backoff.

Connection errors (for example, because of a network connectivity problem), 408 Request Timeout, 409 Conflict, 429 Rate Limit, >=500 Internal errors, and timeouts are all retried by default.

You can use the max_retries option to configure or disable this:

# Configure the default for all requests:
anthropic = Anthropic::Client.new(
  max_retries: 0 # default is 2
)

# Or, configure per-request:
anthropic.messages.create(
  max_tokens: 1024,
  messages: [{role: "user", content: "Hello, Claude"}],
  model: :"claude-opus-5",
  request_options: {max_retries: 5}
)

Timeouts

By default, requests time out after 10 minutes. You can use the timeout option to configure this:

# Configure the default for all requests:
anthropic = Anthropic::Client.new(
  timeout: 20 # 20 seconds (default is 10 minutes)
)

# Or, configure per-request:
anthropic.messages.create(
  max_tokens: 1024,
  messages: [{role: "user", content: "Hello, Claude"}],
  model: :"claude-opus-5",
  request_options: {timeout: 5}
)

On timeout, Anthropic::Errors::APITimeoutError is raised.

Note that requests that time out are retried by default.

Pagination

List methods in the Claude API are paginated.

This library provides auto-paginating iterators with each list response, so you do not have to request successive pages manually:

anthropic = Anthropic::Client.new
page = anthropic.messages.batches.list(limit: 20)

# Fetch single item from page.
batch = page.data[0]
puts(batch.id)

# Automatically fetches more pages as needed.
page.auto_paging_each do |batch|
  puts(batch.id)
end

Alternatively, you can use the #next_page? and #next_page methods for more granular control working with pages.

anthropic = Anthropic::Client.new
page = anthropic.messages.batches.list(limit: 20)
loop do
  page.data&.each { |batch| puts(batch.id) }
  break unless page.next_page?
  page = page.next_page
end

File uploads

Request parameters that correspond to file uploads can be passed as raw contents, a Pathname instance, StringIO, or more.

anthropic = Anthropic::Client.new
require "pathname"

# Use `Pathname` to send the filename and/or avoid paging a large file into memory:
file_metadata = anthropic.files.upload(file: Pathname("/path/to/file"))

# Alternatively, pass file contents or a `StringIO` directly:
file_metadata = anthropic.files.upload(file: File.read("/path/to/file"))

# Or, to control the filename and/or content type:
file = Anthropic::FilePart.new(File.read("/path/to/file"), filename: "/path/to/file", content_type: "...")
file_metadata = anthropic.files.upload(file: file)

puts(file_metadata.id)

Note that you can also pass a raw IO descriptor, but this disables retries, as the library can't be sure if the descriptor is a file or pipe (which cannot be rewound).

Sorbet

This library provides comprehensive RBI definitions, and has no dependency on sorbet-runtime.

You can provide typesafe request parameters like so:

anthropic = Anthropic::Client.new
anthropic.messages.create(
  max_tokens: 1024,
  messages: [Anthropic::MessageParam.new(role: "user", content: "Hello, Claude")],
  model: :"claude-opus-5"
)

Or, equivalently:

anthropic = Anthropic::Client.new
# Hashes work, but are not typesafe:
anthropic.messages.create(
  max_tokens: 1024,
  messages: [{role: "user", content: "Hello, Claude"}],
  model: :"claude-opus-5"
)

# You can also splat a full Params class:
params = Anthropic::MessageCreateParams.new(
  max_tokens: 1024,
  messages: [Anthropic::MessageParam.new(role: "user", content: "Hello, Claude")],
  model: :"claude-opus-5"
)
anthropic.messages.create(**params)

Enums

Since this library does not depend on sorbet-runtime, it cannot provide T::Enum instances. Instead, the SDK provides "tagged symbols", which is always a primitive at runtime:

# :auto
puts(Anthropic::MessageCreateParams::ServiceTier::AUTO)

# Revealed type: `T.all(Anthropic::MessageCreateParams::ServiceTier, Symbol)`
T.reveal_type(Anthropic::MessageCreateParams::ServiceTier::AUTO)

Enum parameters have a "relaxed" type, so you can either pass in enum constants or their literal value:

# Using the enum constants preserves the tagged type information:
anthropic.messages.create(
  service_tier: Anthropic::MessageCreateParams::ServiceTier::AUTO,
  # ...
)

# Literal values are also permissible:
anthropic.messages.create(
  service_tier: :auto,
  # ...
)

BaseModel

All parameter and response objects inherit from Anthropic::Internal::Type::BaseModel, which provides several conveniences, including:

1. All fields, including unknown ones, are accessible with obj[:prop] syntax, and can be destructured with obj => {prop: prop} or pattern-matching syntax.

2. Structural equivalence for equality; if two API calls return the same values, comparing the responses with == will return true.

3. Both instances and the classes themselves can be pretty-printed.

4. Helpers such as #to_h, #deep_to_h, #to_json, and #to_yaml.

Concurrency and connection pooling

The Anthropic::Client instances are threadsafe, but are only fork-safe when there are no in-flight HTTP requests.

Each instance of Anthropic::Client has its own HTTP connection pool with a default size of 99. As such, the recommendation is to create the client once per application in most settings.

When all available connections from the pool are checked out, requests wait for a new connection to become available, with queue time counting toward the request timeout.

Unless otherwise specified, other classes in the SDK do not have locks protecting their underlying data structure.

Making custom or undocumented requests

Undocumented properties

You can send undocumented parameters to any endpoint, and read undocumented response properties, like so:

anthropic = Anthropic::Client.new
value = "example"
message =
  anthropic.messages.create(
    max_tokens: 1024,
    messages: [{role: "user", content: "Hello, Claude"}],
    model: :"claude-opus-5",
    request_options: {
      extra_query: {my_query_parameter: value},
      extra_body: {my_body_parameter: value},
      extra_headers: {"my-header": value}
    }
  )

puts(message[:my_undocumented_property])

Undocumented request params

If you want to explicitly send an extra param, you can do so with the extra_query, extra_body, and extra_headers under the request_options: parameter when making a request, as seen in the examples above.

Undocumented endpoints

To make requests to undocumented endpoints while retaining the benefit of auth, retries, and so on, you can make requests using anthropic.request, like so:

response = anthropic.request(
  method: :post,
  path: '/undocumented/endpoint',
  query: {"dog": "woof"},
  headers: {"useful-header": "interesting-value"},
  body: {"hello": "world"}
)

Platform integrations

The Ruby SDK supports the following platforms:

• Agent Platform: Anthropic::VertexClient. Requires the googleauth gem.
• Bedrock: Anthropic::BedrockMantleClient, or Anthropic::BedrockClient for the bedrock-runtime path. Anthropic::BedrockMantleClient requires the aws-sdk-core gem; Anthropic::BedrockClient requires the aws-sdk-bedrockruntime gem.
• Claude Platform on AWS: Part of the main anthropic gem (requires the aws-sdk-core gem). Provides Anthropic::AWSClient. Pass workspace_id: to the constructor or set the ANTHROPIC_AWS_WORKSPACE_ID environment variable (see Workspaces). Available in beta.
• Foundry: Not currently supported in the Ruby SDK. See Claude in Microsoft Foundry for supported SDKs.

Use Anthropic::BedrockMantleClient for new projects; Anthropic::BedrockClient remains for existing applications using the Bedrock InvokeModel API.

Semantic versioning

This package follows SemVer conventions.

This package considers improvements to the (non-runtime) *.rbi and *.rbs type definitions to be non-breaking changes.

Additional resources

• GitHub repository
• YARD documentation
• API reference
• Streaming Messages