ChatOpenRouter

Internal method that handles batching and configuration for a runnable It takes a function, input values, and optional configuration, and returns a promise that resolves to the output values.

Filter out large/inappropriate fields from invocation params for tracing metadata. Removes fields like tools, functions, messages, response_format that can be large.

Non-streaming generation. Sends a single request and returns the complete response with the generated message and token usage.

Create a unique cache key for a specific call to a specific language model.

Get the identifying parameters of the LLM.

Stream chat model events using the new content-block-centric protocol.

Override this method to provide native event streaming from the provider SDK. The default implementation bridges from _streamResponseChunks by synthesizing lifecycle events from ChatGenerationChunk objects.

Event lifecycle

MessageStart
  -> ContentBlockStart(index, contentBlock)
    -> ContentBlockDelta(index, delta) ...
  -> ContentBlockFinish(index, contentBlock)
-> MessageFinish(reason, usage?)

Content blocks may interleave (e.g., parallel tool calls). The only invariant: a block's start precedes its deltas, and its deltas precede its finish.

Default streaming implementation. Subclasses should override this method if they support streaming output.

Streaming generation. Opens an SSE connection and yields one ChatGenerationChunk per delta received from the API. The stream pipeline is: raw bytes -> text -> SSE events -> JSON-parsed deltas.

Helper method to transform an Iterator of Input values into an Iterator of Output values, with callbacks. Use this to implement stream() or transform() in Runnable subclasses.

Assigns new fields to the dict output of this runnable. Returns a new runnable.

Convert a runnable to a tool. Return a new instance of RunnableToolLike which contains the runnable, name, description and schema.

Default implementation of batch, which calls invoke N times. Subclasses should override this method if they can batch more efficiently.

Returns a new Runnable with the given tools bound into every call. Equivalent to .withConfig({ tools, ...kwargs }).

Generates chat based on the input messages.

Generates a prompt based on the input prompt values.

Returns metadata for LangSmith tracing (provider, model name, temperature, etc.).

Wraps getLsParams() and always appends ls_integration. This ensures the integration tag is present even when partner packages fully override getLsParams().

Get the number of tokens in the content.

Merges constructor-level defaults with per-call overrides into the API request body (everything except messages, which is added later).

Invokes the chat model with a single input.

Pick keys from the dict output of this runnable. Returns a new runnable.

Create a new runnable sequence that runs each individual runnable in series, piping the output of one runnable into another runnable or runnable-like.

Stream output in chunks.

Generate a stream of events emitted by the internal steps of the runnable.

Use to create an iterator over StreamEvents that provide real-time information about the progress of the runnable, including StreamEvents from intermediate results.

A StreamEvent is a dictionary with the following schema:

• event: string - Event names are of the format: on_[runnable_type]_(start|stream|end).
• name: string - The name of the runnable that generated the event.
• run_id: string - Randomly generated ID associated with the given execution of the runnable that emitted the event. A child runnable that gets invoked as part of the execution of a parent runnable is assigned its own unique ID.
• tags: string[] - The tags of the runnable that generated the event.
• metadata: Record<string, any> - The metadata of the runnable that generated the event.
• data: Record<string, any>

Below is a table that illustrates some events that might be emitted by various chains. Metadata fields have been omitted from the table for brevity. Chain definitions have been included after the table.

ATTENTION This reference table is for the V2 version of the schema.

+----------------------+-----------------------------+------------------------------------------+
| event                | input                       | output/chunk                             |
+======================+=============================+==========================================+
| on_chat_model_start  | {"messages": BaseMessage[]} |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_chat_model_stream |                             | AIMessageChunk("hello")                  |
+----------------------+-----------------------------+------------------------------------------+
| on_chat_model_end    | {"messages": BaseMessage[]} | AIMessageChunk("hello world")            |
+----------------------+-----------------------------+------------------------------------------+
| on_llm_start         | {'input': 'hello'}          |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_llm_stream        |                             | 'Hello'                                  |
+----------------------+-----------------------------+------------------------------------------+
| on_llm_end           | 'Hello human!'              |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_chain_start       |                             |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_chain_stream      |                             | "hello world!"                           |
+----------------------+-----------------------------+------------------------------------------+
| on_chain_end         | [Document(...)]             | "hello world!, goodbye world!"           |
+----------------------+-----------------------------+------------------------------------------+
| on_tool_start        | {"x": 1, "y": "2"}          |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_tool_end          |                             | {"x": 1, "y": "2"}                       |
+----------------------+-----------------------------+------------------------------------------+
| on_retriever_start   | {"query": "hello"}          |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_retriever_end     | {"query": "hello"}          | [Document(...), ..]                      |
+----------------------+-----------------------------+------------------------------------------+
| on_prompt_start      | {"question": "hello"}       |                                          |
+----------------------+-----------------------------+------------------------------------------+
| on_prompt_end        | {"question": "hello"}       | ChatPromptValue(messages: BaseMessage[]) |
+----------------------+-----------------------------+------------------------------------------+

The "on_chain_*" events are the default for Runnables that don't fit one of the above categories.

In addition to the standard events above, users can also dispatch custom events.

Custom events will be only be surfaced with in the v2 version of the API!

A custom event has following format:

+-----------+------+------------------------------------------------------------+
| Attribute | Type | Description                                                |
+===========+======+============================================================+
| name      | str  | A user defined name for the event.                         |
+-----------+------+------------------------------------------------------------+
| data      | Any  | The data associated with the event. This can be anything.  |
+-----------+------+------------------------------------------------------------+

Here's an example:

import { RunnableLambda } from "@langchain/core/runnables";
import { dispatchCustomEvent } from "@langchain/core/callbacks/dispatch";
// Use this import for web environments that don't support "async_hooks"
// and manually pass config to child runs.
// import { dispatchCustomEvent } from "@langchain/core/callbacks/dispatch/web";

const slowThing = RunnableLambda.from(async (someInput: string) => {
  // Placeholder for some slow operation
  await new Promise((resolve) => setTimeout(resolve, 100));
  await dispatchCustomEvent("progress_event", {
   message: "Finished step 1 of 2",
 });
 await new Promise((resolve) => setTimeout(resolve, 100));
 return "Done";
});

const eventStream = await slowThing.streamEvents("hello world", {
  version: "v2",
});

for await (const event of eventStream) {
 if (event.event === "on_custom_event") {
   console.log(event);
 }
}

Create a ChatModelStream for the given input.

Returns a stream object that is both AsyncIterable<ChatModelStreamEvent> and PromiseLike<AIMessage>, with typed sub-stream accessors for .text, .toolCalls, .reasoning, and .usage.

Default implementation of transform, which buffers input and then calls stream. Subclasses should override this method if they can start producing output while input is still being generated.

Bind config to a Runnable, returning a new Runnable.

Create a new runnable from the current one that will try invoking other passed fallback runnables if the initial invocation fails.

Bind lifecycle listeners to a Runnable, returning a new Runnable. The Run object contains information about the run, including its id, type, input, output, error, startTime, endTime, and any tags or metadata added to the run.

Add retry logic to an existing runnable.

Returns a Runnable that forces the model to produce output conforming to outputSchema (a Zod schema or plain JSON Schema object).

The extraction strategy (JSON Schema response format, function calling, or JSON mode) is chosen automatically based on model capabilities — see resolveOpenRouterStructuredOutputMethod. You can override this via config.method.

When config.includeRaw is true the returned object contains both the raw BaseMessage and the parsed output, with a fallback that sets parsed: null if the parser throws.

The name of the serializable. Override to provide an alias or to preserve the serialized module name in minified environments.

Implemented as a static method to support loading logic.