These docs track the main branch and may describe unreleased features. The stable documentation lives at docs.docker.com.

PopNow

Use PopNow models with Docker Agent.

Overview

PopNow provides chat models from several vendors through one OpenAI-compatible API, billed per token in USD. Docker Agent includes built-in support for PopNow as a provider alias.

Setup

  1. Create a PopNow API key

  2. Set the environment variable:

    export POPNOW_API_KEY=your-api-key
    

Usage

Inline Syntax

Use a PopNow model by prefixing its model ID with popnow/:

agents:
  root:
    model: popnow/deepseek/v4-flash/chat
    description: Assistant using PopNow
    instruction: You are a helpful assistant.

Docker Agent splits only the first slash, so the vendor prefix and task suffix in PopNow model IDs are preserved.

Named Model

For more control over parameters:

models:
  popnow_deepseek:
    provider: popnow
    model: deepseek/v4-flash/chat
    temperature: 0.7
    max_tokens: 8192

agents:
  root:
    model: popnow_deepseek
    description: Assistant using PopNow
    instruction: You are a helpful assistant.

Available Models

PopNow model IDs end in a task suffix, and chat models use /chat:

Model ID Model
deepseek/v4-flash/chat DeepSeek V4 Flash
moonshot/kimi-k3/chat Kimi K3

Model IDs are case-sensitive. Check the PopNow model catalog for current IDs and availability. Only models with the chat task work with Docker Agent.

PopNow is not in the models.dev catalog, so Docker Agent has no catalog-derived pricing or context limits for these models. Attachment capabilities conservatively fall back to text-only; image and PDF attachments are dropped, with a warning logged once per model.

If you have verified that your chosen model accepts a particular attachment type, set models.<name>.capabilities to override detection. See Attachment Capability Overrides for all supported flags.

How It Works

PopNow is implemented as a built-in alias in Docker Agent:

Because PopNow serves models from many vendors, some of which reject multiple leading system messages, Docker Agent coalesces its per-source system messages into one.

Example: Code Assistant

agents:
  coder:
    model: popnow/deepseek/v4-flash/chat
    description: Code assistant using PopNow
    instruction: |
      You are an expert programmer.
      Write clean code and follow language best practices.
    toolsets:
      - type: filesystem
      - type: shell
      - type: think