Parallel is a real-time web search and content extraction platform built for LLMs and AI applications.
ChatParallel is an OpenAI-compatible chat interface to Parallel’s models. The speed model is a low-latency conversational model with no citations; the research models (lite, base, core) browse the web and return per-field citations and structured output via JSON schema.
ChatParallel is the canonical class name. The earlier ChatParallelWeb continues to work as an alias for the same class.Overview
Integration details
Model features
Choosing a model
speed does not honor response_format, so with_structured_output() raises a clear error there. Use a research model when you need parsed pydantic output or per-field citations.
Setup
To access Parallel models, install thelangchain-parallel integration package and acquire a Parallel API key.
Installation
Credentials
Head to Parallel to sign up and generate an API key. SetPARALLEL_API_KEY in your environment:
Instantiation
ChatParallel API reference for the full set of available parameters.
Invocation
Chaining
Chain the model with a prompt template:Structured output
On the research models (lite, base, core), ChatParallel.with_structured_output(...) binds a JSON-schema response_format and returns a parsed pydantic object (or dict). Calling it on speed raises a ValueError, since speed silently ignores response_format.
method="json_schema" (the default), method="json_mode", and method="function_calling" are all accepted. Pass include_raw=True to receive the full {"raw", "parsed", "parsing_error"} envelope and capture parser failures:
Citations
Research models populateAIMessage.response_metadata["basis"] with per-field citations, the model’s reasoning, and a confidence label. response_metadata["interaction_id"] is surfaced for multi-turn context chaining; system_fingerprint is forwarded when present.
Streaming
ChatParallel supports per-token streaming:
Async
Token usage
Parallel does not currently provide token usage metadata.usage_metadata is None.
Response metadata
response_metadata additionally carries basis (per-field citations), interaction_id (for multi-turn chaining), and system_fingerprint when available.
Error handling
The integration raisesValueError with a descriptive message on common failure modes:
OpenAI compatibility
ChatParallel accepts many OpenAI Chat Completions API parameters for drop-in OpenAI-client migration. Advanced parameters such as tools, tool_choice, top_p, and frequency_penalty are accepted but ignored by the Parallel API.
ChatParallel.with_structured_output(...) (see Structured output) over passing response_format directly. It works on the research models and returns a parsed object.
Message handling
The integration merges consecutive messages of the same type to satisfy API requirements:API reference
For detailed documentation, head to theChatParallel API reference or the Parallel chat API quickstart.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

