TokenBuddy gateway details

A third-party multi-model API relay where one key works across three protocols: OpenAI-compatible endpoints (Chat Completions and Responses at https://tokenbuddy.cc/v1), Anthropic Messages, and the native Gemini API (at https://tokenbuddy.cc). Its public model marketplace lists chat models including GPT, Claude, Gemini, Grok, DeepSeek, GLM, and Kimi, plus gpt-image image generation and Seedance video models; the docs cover setup for clients such as Codex, Claude Code, Gemini CLI, OpenCode, and WorkBuddy. Group names and model attributions are platform-reported and do not establish official authorization.

Best for: For individual developers who want one key shared across clients such as Codex, Claude Code, and Gemini CLI and can accept small Alipay prepayments.

Current status

Test yourself

Latency reference

Depends on your deployment

/models check

Public model marketplace; the docs defer to GET /v1/models

Last verified

2026-10-28

Status notes

The website, setup docs, model marketplace, and top-up code shop were accessible. Time-to-first-token figures and the OK / slow status in the marketplace are platform-reported; AI Beyond has not signed up, made paid requests, or tested latency. No dedicated public status page has been verified.

Pricing mode

Billed per token; the model marketplace lists prices in CNY per 1M tokens, and video models are billed per request. GPT and Claude models come in an economy group and a -full stable / full-strength group at different prices. For example, on 2026-10-28 the page showed gpt-5.6-sol (economy) at CNY 0.693 input / CNY 4.158 output, claude-sonnet-5 (economy) at CNY 1 / CNY 5, and claude-sonnet-5-full (full-strength group) at CNY 4 / CNY 20. Prices change; check the marketplace. Top-ups are bought as codes from a separate top-up code shop: the product page offers only "Epay - Alipay" as a payment method, a $100 code costs CNY 100, and the code is redeemed for credit on the website's Redeem page.

Price tags

Pay-as-you-go

Free quota

The submitter states there is no free quota; public pages list no free quota or free trial

Usually you create an API key in the platform console, then replace the SDK's baseURL, model name, and auth details per the docs. Test streaming, function calling, error codes, and rate limits before launch.

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AI_GATEWAY_API_KEY,
  baseURL: "https://tokenbuddy.cc/v1"
});

const response = await client.chat.completions.create({
  model: "gpt-5.6-sol",
  messages: [{ role: "user", content: "Test one call through an AI gateway." }]
});

• Supported models: OpenAI, Claude, Gemini, Grok, DeepSeek, GLM, Moonshot.
• Capabilities: OpenAI-compatible, Image generation.
• Documentation completeness: High; stability not tested.

• Not an official OpenAI, Anthropic, Google, or xAI service; official authorization and upstream sources have not been verified. The model marketplace says each public model is "strictly bound to its upstream account pool", and the docs attribute 5xx errors to the upstream pool temporarily having no available account. "Full-strength", "stable", and "economy" are the platform's own tier names; AI Beyond has not verified how the tiers actually differ. Time-to-first-token figures and the OK / slow status in the marketplace are platform-reported. The site also offers ChatGPT / Claude membership top-up on users' behalf. Top-up codes are paid through a third-party Epay channel, are single-use and case-sensitive; buy small denominations. The terms of service, usage policy, and related login-agreement documents are empty, and no refund policy has been verified. The submitter says the dashboard has balance and usage-detail pages; AI Beyond has not signed in to verify this, and it does not establish a public balance-query or log-query API. The site configuration lists no public contact details and the docs direct users to customer support; the contact email provided by the submitter, a81237232@163.com, is not shown on the website. No dedicated public status page has been verified.
• Third-party relay pricing, models, and availability can change, so re-check them periodically.

Is TokenBuddy compatible with the OpenAI API?

This entry is marked as supporting the OpenAI-compatible format, but the exact base_url, model names, and parameters still follow the official docs.

Is TokenBuddy ready for production?

Run a small-traffic load test, rate-limit test, and error-code test first, and confirm the billing rules; keep a backup provider for important workloads.