Model calls

How should I fill in the Base URL?

Learn how Base URL, /v1 paths, API Key, and Model ID should match in Claude Code, Codex CLI, Cursor, Cline, and other tools. Includes examples and fixes.

Short answer

The Base URL must match the protocol expected by your tool. Claude Code usually uses the Anthropic-compatible root address. Codex CLI, Cursor, Cline, OpenCode, OpenClaw, and other external tools usually use the OpenAI-compatible /v1 address.

In BetterToken:

Use case	Base URL
Claude Code / Anthropic-compatible	`https://bettertoken.ai`
Codex CLI / OpenAI-compatible	`https://bettertoken.ai/v1`
Cursor, Cline, OpenCode, OpenClaw	`https://bettertoken.ai/v1`

Use https://bettertoken.ai for Claude Code and https://bettertoken.ai/v1 for Codex CLI and OpenAI-compatible tools. Choose the endpoint for the protocol your client uses.

Why there are different Base URLs

Different SDKs append paths in different ways.

Protocol or tool type	Common behavior
OpenAI-compatible SDK	Usually calls resources such as chat completions or responses under `/v1`
Anthropic-compatible SDK	Usually appends message endpoint paths itself, so you should not add `/v1` again
Built-in tool provider	May append paths automatically, or may ask you for a complete Base URL

Use https://bettertoken.ai for Claude Code and https://bettertoken.ai/v1 for Codex CLI and OpenAI-compatible tools. Choose the endpoint for the protocol your client uses.

Quick reference

Tool	Recommended setup
Claude Code	`https://bettertoken.ai`, with a BetterToken API key
Claude Desktop Gateway	Follow the Gateway page, including the auth scheme
Codex CLI	`https://bettertoken.ai/v1`, with a BetterToken API key
Cursor	`https://bettertoken.ai/v1`, with a BetterToken API key
Cline	`https://bettertoken.ai/v1`, using an OpenAI Compatible provider
OpenCode / OpenClaw	`https://bettertoken.ai/v1`, with a BetterToken API key

Common errors

Error or symptom	Possible cause
`404 Not Found`	The Base URL path does not match the SDK’s expected path
`model not found`	Check the exact Model ID in the model plaza and enter it in the client model settings.
`invalid_api_key`	The API Key and Base URL are from different services
Authentication works, but the model is unavailable	Check the exact Model ID in the model plaza and enter it in the client model settings.
Requests keep failing	An Anthropic-compatible address was used in an OpenAI-compatible tool, or the reverse

Recommended troubleshooting order

Confirm whether the tool expects OpenAI-compatible or Anthropic-compatible API.
Check whether the Base URL matches that protocol.
Check whether the API Key is from the same service.
Copy the exact Model ID from the model plaza.
Send a minimal test request, such as hello.

Code examples

OpenAI-compatible tools usually use the /v1 address:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://bettertoken.ai/v1"
)

response = client.chat.completions.create(
    model="your-model-id",
    messages=[{"role": "user", "content": "hello"}]
)

Claude / Anthropic-compatible setups usually use the root address:

import anthropic

client = anthropic.Anthropic(
    api_key="YOUR_API_KEY",
    base_url="https://bettertoken.ai"
)

message = client.messages.create(
    model="your-model-id",
    max_tokens=1024,
    messages=[{"role": "user", "content": "hello"}]
)

About BetterToken

BetterToken provides both Anthropic-compatible and OpenAI-compatible access. You can manage API Keys, balance, and usage records in the same dashboard, but each client still needs the protocol address it supports.

Quick rule: Claude Code uses https://bettertoken.ai; Codex CLI, Cursor, Cline, OpenCode, and OpenClaw use https://bettertoken.ai/v1.