ModelSmarterStart intake
ModelsPlansDocs
Browse documentationTap to expand
Documentation overview

Developer tools

CursorClaude CodeCodexQwen CodeOpenCodeKilo CLILingmaQoderOpenClawCustom Agent CLICherry StudioChatboxClinePostmanDifyToken Plan Multimodal Generation

All sections

Scroll
Product basicsBilling and pricingAPI setupModel inferenceDeveloper toolsOperationsSecurity and complianceTutorials and support

Developer tool setup

Claude Code

Configure Claude Code with Model Studio or Token Plan credentials, then verify the selected model before handing it to developers.

Developer toolsOfficial source

Who this is for

Developers, technical support, and procurement staff preparing a customer handoff.

Configuration reference

Values to confirm before setup

ANTHROPIC_BASE_URL

https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic

ANTHROPIC_AUTH_TOKEN

Token Plan Team Edition dedicated API key

Model slots

ANTHROPIC_MODEL, SMALL_FAST, HAIKU, SONNET, OPUS, SUBAGENT all set to supported model

Setup flow

Practical steps

  1. 01Install Node.js 18+ and Claude Code, then verify `claude --version`.
  2. 02Confirm which commercial route the customer bought: Token Plan Team Edition, Coding Plan, or pay-as-you-go Model Studio.
  3. 03Paste only the matching API key into the tool settings or environment variables.
  4. 04Set the matching base URL. Do not reuse a Base URL from another package.
  5. 05Use a model that the selected Token Plan route supports. For Claude Code, configure every model slot so the client does not fall back to Anthropic's official service.
  6. 06Restart the tool, select the configured model, and run a short smoke test.

The three values that must match

Most connection failures come from mixing a key, endpoint, and model from different plans or regions. Confirm the API key source first, then choose the matching base URL, then use a model name supported by that route.

  • API key: Model Studio pay-as-you-go, Token Plan, and Coding Plan keys are not interchangeable.
  • Base URL: region-specific endpoints are not universal.
  • Model name: use the exact published model identifier, including suffixes such as qwen3.7-plus or glm-5.1 where required.

Security baseline

Use environment variables or an application secret manager. Do not paste production API keys into public code, screenshots, frontend JavaScript, or customer-facing support tickets.

Handoff checklist

Before delivery, record the plan type, model name, endpoint, owner, renewal date, and whether usage is charged from a seat quota, shared quota, or pay-as-you-go account.

Common mistakes

Check these before escalating

  • Using a normal Model Studio API key with Token Plan endpoints will fail or bill the wrong route.
  • Some free editions of third-party tools do not allow custom model providers.
  • DeepSeek V3.2 is not available through the Anthropic protocol route in Claude Code.
  • Set hasCompletedOnboarding to true if the client tries to call Anthropic login services.

Related guides

Token Plan Team Edition Overview

Token Plan Team Edition is a credit-based subscription for supported AI coding and agent tools. It is different from pay-as-you-go API usage.

OpenAI-Compatible Chat API

Most OpenAI-compatible integrations need only three changes: API key, base URL, and model name. The hard part is choosing the correct plan and endpoint.

Rate Limits and Quota Errors

Rate limits are calculated by account, model, and aggregate API-key usage. A customer quote should include traffic assumptions and an escalation path.

Usage Monitoring and Cost Control

Production buyers need visibility into call volume, token consumption, success rate, quota remaining, and monthly replenishment.