Skip to main content

Usage guide

Setup, environment variables, and Python/JavaScript/Go usage examples.

​
AnthropicLLM

Anthropic Claude LLM plugin. Wraps the Anthropic Messages API with optional extended thinking support, streaming-first generation, and tool/function calling.

​
Constructor

​
api_key
str | None
Anthropic API key. Falls back to the ANTHROPIC_API_KEY environment variable when omitted.
​
model
AnthropicLLMModel | str
default:"claude-sonnet-4-20250514"
Claude model ID to use. Defaults to "claude-sonnet-4-20250514" (Claude Sonnet 4). Other options include "claude-opus-4-20250514" (most capable), "claude-haiku-3-5-20241022" (fastest/cheapest). Accepts any AnthropicLLMModel enum value or a raw string model ID.
​
temperature
float
default:"0.7"
Sampling temperature in [0.0, 1.0]. Lower values produce more deterministic output; higher values increase creativity. Defaults to 0.7.
​
max_output_tokens
int
default:"1024"
Maximum number of tokens the model may generate per response. Defaults to 1024. The legacy max_tokens kwarg is accepted for backward compatibility and overrides this value when it equals the default.
​
top_p
float | None
Nucleus sampling probability mass in (0.0, 1.0]. Mutually exclusive with temperature: set one or the other, not both. Defaults to None (disabled).
​
top_k
int | None
Restrict sampling to the top-K most likely tokens at each step. Defaults to None (disabled).
​
stop_sequences
list[str] | str | None
One or more strings at which the model will stop generating. Accepts a single string or a list of strings. Defaults to None.
​
thinking_budget
int | None
Token budget for Claude’s extended thinking (chain-of-thought reasoning). None disables thinking; set to a positive integer (e.g. 1024) to enable. The legacy thinking={"budget_tokens": N} kwarg is also accepted.

​
aclose

Release any resources held by the provider.

​
cancel_current_generation

Cancel the in-progress generation for the active session, if any.

​
chat

Generate a streamed chat completion.
​
messages
Any
required
The conversation history to send to the model.
​
tools
Any
Optional tool definitions the model may call.
​
conversational_graph
Any
Optional conversational graph guiding the exchange.
​
returns
AsyncIterator[LLMResponse]
LLMResponse: Response chunks produced as the model generates output.

​
emit

Emit an event, invoking all registered handlers with the given arguments. Handlers are called in registration order. Coroutine handlers are scheduled on the running event loop. If the emitter is closed, the call is a no-op.
​
event
T
required
The event to emit.

​
off

Remove a previously registered handler for an event. If the handler is not registered for the event, the call is a no-op.
​
event
T
required
The event the handler was registered for.
​
callback
Callable[..., Any]
required
The handler to remove.

​
on

Register a handler for an event. Can be used directly by passing a callback, or as a decorator when callback is omitted.
​
event
T
required
The event to listen for.
​
callback
Callable[..., Any] | None
The handler to invoke when the event is emitted. If None, a decorator is returned that registers the decorated function.
​
returns
Callable[..., Any]
The registered callback when callback is provided, otherwise a decorator that registers and returns the function it wraps.

​
AnthropicLLMModel