Japan32K contextAPIJapanese

Explore PLaMo 2 Prime

Use Preferred Networks' domestic Japanese foundation model through its OpenAI-compatible chat API.

Model

plamo-2.2-prime

Input

Configure your request

System prompt Optional

Set the model role and response instructions.

Conversation history Optional

Optional prior system, user, and assistant messages as JSON. Message names are also supported.

Your message

Parameters

Stream responseReturn response chunks as they are generated. Include streaming usageEmit token usage before the streaming terminator.

Temperature

Top P

Maximum output tokens

PLaMo 2.2 Prime permits up to 4,096 output tokens.

Number of responses

Presence penalty

Frequency penalty

Seed

Stop sequences

Response format

JSON Schema

Used when JSON Schema output is selected.

Function tools (JSON)

Tool choice

Safety identifier

Do not send personal or sensitive information.