OpenCOReTechnologies/CORe-Pico-V2

TEXT GENERATIONPricing:Input $0.04 / Cached $0.008 / Output $0.08Concurrent Unit Cost:1Model Size:0.8BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Sep 15, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive Cold

CORe Pico V2 is a compact 0.6 billion parameter conversational model developed by CORe Technologies, designed for efficient deployment and interaction. It features a 32,768-token context length and excels at multi-turn chat, direct question answering, and structured tool calling. The model supports extended reasoning through explicit thinking modes, making it suitable for applications requiring lightweight, responsive conversational AI.

Loading preview...

CORe Pico V2 Overview

CORe Pico V2, developed by CORe Technologies, is a compact 0.6 billion parameter conversational model designed for efficient performance across various applications. It is a refined version of the Pico line, specifically optimized for conversational interactions and direct question answering. With a context length of 32,768 tokens, it supports extended dialogues and complex interactions.

Key Capabilities

  • Consistent Identity: Provides accurate and consistent answers to questions about its own identity (e.g., "Who are you?").
  • Direct Chat and Answers: Delivers concise and direct replies to factual questions and engages in multi-turn conversations.
  • Tool Calling: Capable of emitting structured JSON blocks for tool calls, enabling integration with external functions and services.
  • Extended Thinking Modes: Features /think and /no_think modes, allowing for explicit reasoning traces or direct responses based on the system prompt.
  • Compact Size: At 0.6 billion parameters, it is designed to run efficiently on diverse hardware, including edge devices.

Good For

  • Lightweight Conversational Agents: Ideal for applications requiring a small, fast, and responsive chatbot.
  • Tool-Augmented AI: Suitable for scenarios where the model needs to interact with external tools or APIs.
  • Interactive Q&A Systems: Effective for direct question answering and maintaining conversational flow.
  • Resource-Constrained Environments: Its compact size and efficient design make it well-suited for deployment in environments with limited computational resources.

Finetunes
1 models