Your privacy choices

Allow optional cookies for referral attribution, visit analytics, and Google Ads purchase measurement.

LLM API Gateway

One API key.GPT, Claude, Grok & Chinese LLMs.

Connect GPT, Claude, Grok, DeepSeek, Qwen, Kimi, GLM, MiniMax, Doubao, Hunyuan, MiMo, StepFun, and LongCat through one prepaid key—then keep the endpoint your client already understands.

Get API accessView models & pricingTop up credits
  1. POST /v1/chat/completions
  2. POST /v1/responses
  3. POST /v1/messages
Connect without a rewriteapi.llm-token.cn/v1
curl https://api.llm-token.cn/v1/chat/completions \  --header "Authorization: Bearer YOUR_API_KEY" \  --header "Content-Type: application/json" \  --data '{  "model": "MODEL_ID",  "messages": [{ "role": "user", "content": "Explain why the sky is blue." }]}'
200 OKOpenAI-compatible
{  "model": "MODEL_ID",  "output": "A clear response, streamed through one compatible gateway."}
Connect without a rewrite

Keep your client. Change the model.

The gateway exposes OpenAI-compatible Chat Completions and Responses routes plus an Anthropic-compatible Messages route. Check the tutorial for the exact Base URL, path, and model ID.

01OpenAI-compatiblePOST /v1/chat/completions
02ResponsesPOST /v1/responses
03MessagesPOST /v1/messages
00Base URLhttps://api.llm-token.cn/v1
Read setup guides
Model catalog

Choose a route for your workload

36Model catalog
Pricing

Showing 36 of 36 models

  • Claude Sonnet 4.6
  • GPT-5.4
  • GPT-5.5
  • GPT-5.3 Codex Spark
  • GPT Image 2
  • GPT Image 2 4K
  • GPT-5.6 Sol
  • GPT-5.6 Terra
  • Grok 4.6
  • Grok 4.5
  • Claude Haiku 4.5
  • Claude Sonnet 5
  • Claude Fable 5
  • Claude Opus 4.6
  • Claude Opus 4.7
  • Claude Opus 4.8
  • Claude Opus 5
  • Qwen 3.6 Plus
  • Qwen 3.7 Plus
  • Qwen 3.7 Max
  • Qwen 3.8 Max
  • LongCat 2.0
  • Hunyuan 3
  • MiniMax M3
  • Image 01
  • Image 01 Live
  • Step 3.7 Flash
  • Doubao Seed 2.1 Turbo
  • MiMo V2.5 Pro
  • MiMo V2.5
  • DeepSeek V4 Pro
  • DeepSeek V4 Flash
  • Kimi K3
  • GLM 5.1
  • GLM 5.2
  • GLM 5.3
Model catalog

Build with the model you need

  1. Code & agents

    Use Codex CLI, Claude Code, Cursor, OpenCode, or your own app with a familiar API.

    Docs

  2. Reasoning & chat

    Route everyday chat, long-context work, and reasoning to GPT, Claude, DeepSeek, Qwen, Kimi, or GLM.

    Docs

  3. Vision & images

    Choose supported vision and image-generation routes from the live model catalog before you call them.

    Docs
Start in 3 steps

From a prepaid balance to your first request.

  1. Choose a plan

    Pick prepaid credits for the models and volume you expect.

  2. Add credits

    Complete checkout with a payment method shown for your account.

  3. Send a request

    Copy the API key, set the documented Base URL, and send a test call.

Get API accessTop up credits
Support

Common questions

How do I buy an API key?

Open the access page, choose a package, enter the delivery email, and complete payment. New credentials are delivered according to the checkout instructions; also check the spam folder.

How do I top up an existing API key?

Use the top-up page and enter the existing key carefully. Never paste a full key into a public ticket, group chat, screenshot, or shared document.

Where can I check balance and usage?

Use the official quota portal linked on this site. Enter the key only on that official page and never send the full credential to support.

Which Base URL should I use?

Use https://api.llm-token.cn/v1 everywhere. It is a globally routed entry point (nodes in East China, South China, Hong Kong, Singapore, the US, and Germany) that automatically connects you to the fastest route.

Which API formats are supported?

Chat Completions-compatible, Responses-compatible, and Messages-compatible formats are available. Select the format expected by your library, client, or agent workflow.

Which model families are available?

The catalog covers major GPT, Claude, Grok, DeepSeek, Qwen, Doubao, Kimi, GLM, MiniMax, Hunyuan, StepFun, MiMo, and LongCat families. Check the pricing page for current versions, capabilities, and rates.

Are image generation and multimodal inputs supported?

Yes, for models marked with those capabilities in the live catalog. Confirm whether the selected model accepts image URLs, Base64 input, or produces images, and follow its dedicated request format.

How is pricing calculated?

Credits are prepaid and deducted using the live rate for each model, including input/output tokens, multipliers, or per-task fees where applicable. Review the pricing page before purchase or production use.

Read the full FAQ
LLM API Gateway

Ready to send a real request?

Start with one key, follow the client-specific tutorial, and switch models by changing the model ID.

Get API accessView models & pricing