Other tool integrations

LAYSO AI supports OpenAI-, Anthropic-, and Gemini-compatible protocols. A tool can usually connect when it allows a custom API URL, API key, and model ID.

One key for every platform model

LAYSO AI bills at the selected model's current price. Every successful request has an itemized charge; failed tasks are not charged.

Before you begin

1. Create and copy a key from LAYSO AI API Keys ↗.
2. Copy an exact model ID from LAYSO AI Models & Pricing ↗.
3. Confirm the tool supports a custom provider, Base URL, or endpoint.
4. Identify whether the tool uses the OpenAI, Anthropic, or Gemini protocol.

General configuration rules

Identify the protocol

Tool protocol	Base or root URL	API key header
OpenAI compatible	https://api.layso.ai/v1	Authorization: Bearer <LAYSO_API_KEY>
Native Anthropic	https://api.layso.ai	x-api-key: <LAYSO_API_KEY>
Native Gemini	https://api.layso.ai	x-goog-api-key: <LAYSO_API_KEY>

Anthropic and Gemini clients should receive the root URL and build the native request path themselves. Do not append /anthropic, /gemini, or /v1beta.

Identify the URL field type

Some tools expect a Base URL while others expect a complete request endpoint. They are not interchangeable.

Field or purpose	URL
OpenAI Base URL / API Base	https://api.layso.ai/v1
OpenAI Chat Completions endpoint	https://api.layso.ai/v1/chat/completions
OpenAI Responses endpoint	https://api.layso.ai/v1/responses
Anthropic Base URL	https://api.layso.ai
Gemini Base URL	https://api.layso.ai

Avoid duplicated paths

If the tool appends /v1/chat/completions automatically, enter only https://api.layso.ai/v1. Use the complete request URL only when the field explicitly asks for an endpoint.

Continue (VS Code / JetBrains)

Continue ↗ is an AI coding assistant for VS Code and JetBrains. Current versions prefer ~/.continue/config.yaml; the old config.json format is deprecated.

Add this to ~/.continue/config.yaml:

name: LAYSO AI
version: 1.0.0
schema: v1

models:
  - name: LAYSO AI Model
    provider: openai
    model: <MODEL_ID>
    apiBase: https://api.layso.ai/v1
    apiKey: ${{ secrets.LAYSO_API_KEY }}
    roles:
      - chat
      - edit
      - apply

Create a LAYSO_API_KEY entry in Continue's secret management and use a key from API Keys ↗. Reload the IDE and select LAYSO AI Model from the model picker.

Aider

Aider ↗ supports OpenAI-compatible endpoints. Keep the key in a local environment variable instead of committing it to the repository.

macOS / Linux / WSL

export OPENAI_API_BASE="https://api.layso.ai/v1"
export OPENAI_API_KEY="<LAYSO_API_KEY>"
aider --model openai/<MODEL_ID>

Windows PowerShell

$env:OPENAI_API_BASE = "https://api.layso.ai/v1"
$env:OPENAI_API_KEY = "<LAYSO_API_KEY>"
aider --model openai/<MODEL_ID>

The first openai/ tells Aider to use an OpenAI-compatible transport. Replace <MODEL_ID> with the full gateway model ID shown on Models & Pricing. The same values can be stored in Aider's .env or .aider.conf.yml files.

BoltAI (macOS)

1. Open BoltAI → Preferences → Providers.
2. Add a Custom OpenAI provider.
3. Set Base URL to https://api.layso.ai/v1.
4. Paste a key from API Keys ↗.
5. Enter the exact model ID from Models & Pricing ↗.
6. Save and send a short message to verify the connection.

TypingMind

TypingMind's custom model field expects a complete Chat Completions endpoint:

Field	Value
Name	LAYSO AI or any preferred name
Endpoint	https://api.layso.ai/v1/chat/completions
Model ID	<MODEL_ID>
Custom Header	Authorization
Header Value	Bearer <LAYSO_API_KEY>

Open Models → Add Custom Model, fill in the fields, then test and save. Use the exact model ID from Models & Pricing ↗.

Chatbox

Chatbox supports an OpenAI-compatible provider, but its API Host field may differ from a conventional Base URL. Follow the dedicated Chatbox setup guide to avoid adding or omitting /v1 incorrectly.

Custom integration

GUI tools

1. Open the tool's provider, model service, or API settings.
2. Select OpenAI Compatible, Anthropic, or Gemini.
3. Enter the URL based on whether the field expects a Base URL or full endpoint.
4. Paste a key from API Keys ↗.
5. Enter the exact <MODEL_ID>; do not guess an alias.
6. Test, save, and select LAYSO AI as the active provider.

Code and command-line tools

Validate the key and network with the Models endpoint:

curl https://api.layso.ai/v1/models \
  -H "Authorization: Bearer $LAYSO_API_KEY"

Then make a minimal Chat Completions request:

curl https://api.layso.ai/v1/chat/completions \
  -H "Authorization: Bearer $LAYSO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<MODEL_ID>",
    "messages": [{"role": "user", "content": "Say hello in one sentence."}]
  }'

After a successful request, open LAYSO AI Usage Logs ↗ to verify the model, token usage, and itemized charge.

Authentication and troubleshooting

401 or 403

Copy the key again and check for spaces or line breaks. Also confirm that the tool sends the header required by the selected protocol.

404

This usually means a Base URL was confused with a full endpoint, or the tool appended /v1 twice. Read the tool's field description and compare it with this page's URL table.

Unknown model

Copy the exact ID from Models & Pricing ↗. One LAYSO AI key can access all platform models, so separate keys are unnecessary.

The connection works but features are missing

The tool may require capabilities such as the Responses API, tool calls, image input, or structured output. Confirm that both the tool and selected model support the required feature. Accepting an API key does not guarantee complete compatibility.

No billing record appears

First confirm that the task succeeded. Successful requests create itemized charges; failed tasks are not charged.