English setup reference for API endpoints, model IDs, billing, and supported clients.

Welcome to Guishu LLM Token. This is the English customer edition of the Guishu Token guide. It has been rewritten for international users, with practical setup steps, clear pricing language, and a more familiar support style for UK and overseas customers. Last updated: 14 July 2026

1. Start Here

In most cases, you only need three things: your API key, the compatible API base URL, and the model ID you want to use.

What you need	Use this
Buy or top up	https://www.llm-token.cn/
Check balance and usage	https://token.gpt-agent.cc
International default API base URL	`https://gpt-agent.cc/v1`
Chat completions endpoint	`https://gpt-agent.cc/v1/chat/completions`
Image generation endpoint	`https://gpt-agent.cc/v1/images/generations`
Image web app	https://image2.gpt-agent.cc/

Configuration tip: Some clients ask for a Base URL, while others ask for the full endpoint. If a client asks for a Base URL, use https://gpt-agent.cc/v1. If it asks for a complete chat endpoint, use https://gpt-agent.cc/v1/chat/completions.

Recommended First Test

curl https://gpt-agent.cc/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [
      {"role": "user", "content": "Please reply with one short sentence."}
    ]
  }'

2. Buying, Balance and Billing

Self-service

Purchase and top up at llm-token.cn.
Check remaining balance and usage at token.gpt-agent.cc.
Use the same API key across supported models.

Enterprise support

For larger top-ups, invoices, enterprise onboarding or dedicated routing, contact your account manager or support contact.
Enterprise teams can request account-level guidance, deployment support and usage monitoring.

Billing unit: Guishu Token prices are listed in CNY. The baseline is 1x = CNY 40 per 100 million tokens, which is approximately CNY 0.40 per 1 million tokens. Higher-rate models are charged by multiplying this baseline.

Current rate example	Approx. price per 1M tokens	Example model IDs
0.8x	CNY 0.32	`claude-sonnet-4-6`
1x	CNY 0.40	`gpt-5.3-codex-spark`, `gpt-5.6-luna`, `claude-haiku-4-5-20251001`
4x	CNY 1.60	`gpt-5.5`, `gpt-5.6-sol`, `qwen3.7-plus`
8x	CNY 3.20	`qwen3.7-max`, `glm-5.2`
12x	CNY 4.80	`claude-sonnet-5`
20x	CNY 8.00	`claude-opus-4-6`, `claude-opus-4-7`, `claude-opus-4-8`
30x	CNY 12.00	`claude-fable-5`

Price Monitoring Skill

If your team uses OpenClaw or an automation bot, you can monitor the public model and pricing table for changes. The monitor detects new models, removed models, rate changes and price changes, then produces a notification that can be sent to a team chat or automation channel.

clawhub install feishu-public-table-monitor

Already installed? Update to the latest version:

clawhub --workdir ~/.openclaw/workspace update feishu-public-table-monitor --force

Latest Model Launches

New models now available: the English page has been synced with the Chinese master guide and price list.

Qwen

qwen3.6-plus - 1M context, vision supported. Good for long documents, code repositories, knowledge-base Q&A and Agent tool use.
qwen3.7-plus - 1M context, vision supported. Recommended for OpenClaw, Claude Code, Hermes, large codebases, document processing and image understanding.
qwen3.7-max - 1M context. Flagship text and reasoning model for complex reasoning, architecture planning, long-running Agents and high-value analysis.

Z.ai

glm-5.2 - 1M context, vision supported. Good for complex writing, analysis, coding, Agent engineering and image understanding.

Kimi

kimi-k2.7 - 256K context, vision supported. Good for long-document understanding, knowledge Q&A, coding assistance and multimodal office work.

MiniMax

MiniMax-M3 - 1M context, vision supported. Cost-effective model for long documents, Agents and multi-turn workflows.

StepFun

step-3.7-flash - 256K context, vision supported. Fast general-purpose model for coding, conversation and lightweight Agent tasks.

3. Model Catalogue

Current model pricing: this table mirrors the latest Chinese master price list. Baseline billing remains 1x = CNY 0.40 per 1M tokens; image models are billed per image or per second as shown. 2026-07-10 launch promo: gpt-5.6-sol, gpt-5.6-terra and gpt-5.6-luna were launched with temporary promotional rates. The promotion end date has not been published; check the current table before planning long-running workloads. Temporary Opus channel note: claude-opus-4-6, claude-opus-4-7 and claude-opus-4-8 remain on a temporary stable channel at 20x, equal to CNY 8.00 per 1M tokens, while keeping 1M context, multimodal input and high-cache capability.

Provider	Display name	Model ID	Rate / billing	Price	Context	Vision
Guishu optimised	Claude Sonnet 4.6 (Guishu optimised)	`claude-sonnet-4-6`	0.8x	CNY 0.32 / 1M tokens	1M	Supported
OpenAI	GPT-5.4	`gpt-5.4`	2x	CNY 0.80 / 1M tokens	1M	Supported
OpenAI	GPT-5.5	`gpt-5.5`	4x	CNY 1.60 / 1M tokens	256K	Supported
OpenAI / Codex	GPT-5.3 Codex Spark	`gpt-5.3-codex-spark`	1x	CNY 0.40 / 1M tokens	128K	Not supported
OpenAI	GPT Image 2	`gpt-image-2`	Per image	CNY 0.05–0.10 / image	Standard output	Generation model
OpenAI	GPT Image 2 4K	`gpt-image-2-4k`	Per image	CNY 0.5–1 / image	4K output	Generation model
GPT 5.6 series	GPT-5.6 Sol	`gpt-5.6-sol`	4x	CNY 1.60 / 1M tokens	353K	Supported
GPT 5.6 series	GPT-5.6 Terra	`gpt-5.6-terra`	2x	CNY 0.80 / 1M tokens	353K	Supported
GPT 5.6 series	GPT-5.6 Luna	`gpt-5.6-luna`	1x	CNY 0.40 / 1M tokens	353K	Supported
xAI / Grok	Grok 4.5	`grok-4.5`	3x	CNY 1.20 / 1M tokens	500K	Supported
Anthropic	Claude Haiku 4.5	`claude-haiku-4-5-20251001`	1x	CNY 0.40 / 1M tokens	256K	Supported
Anthropic	Claude Sonnet 5	`claude-sonnet-5`	12x	CNY 4.80 / 1M tokens	1M	Supported
Anthropic	Claude Fable 5	`claude-fable-5`	30x	CNY 12.00 / 1M tokens	1M	Supported
Anthropic	Claude Opus 4.6	`claude-opus-4-6`	20x	CNY 8.00 / 1M tokens	1M	Supported
Anthropic	Claude Opus 4.7	`claude-opus-4-7`	20x	CNY 8.00 / 1M tokens	1M	Supported
Anthropic	Claude Opus 4.8	`claude-opus-4-8`	20x	CNY 8.00 / 1M tokens	1M	Supported
Alibaba Cloud / Qwen	Qwen 3.6 Plus	`qwen3.6-plus`	3x	CNY 1.20 / 1M tokens	1M	Supported
Alibaba Cloud / Qwen	Qwen 3.7 Plus	`qwen3.7-plus`	4x	CNY 1.60 / 1M tokens	1M	Supported
Alibaba Cloud / Qwen	Qwen 3.7 Max	`qwen3.7-max`	8x	CNY 3.20 / 1M tokens	1M	Not supported
Meituan / LongCat	LongCat 2.0	`LongCat-2.0`	1x	CNY 0.40 / 1M tokens	1M	Not supported
Tencent Hunyuan	Hunyuan 3	`hy3`	1x	CNY 0.40 / 1M tokens	256K	Not supported
MiniMax	MiniMax M2.7	`MiniMax-M2.7`	Pending confirmation	Pending confirmation	196K	Pending confirmation
MiniMax	MiniMax M2.7 Highspeed	`MiniMax-M2.7-highspeed`	Pending confirmation	Pending confirmation	196K	Pending confirmation
MiniMax	MiniMax M3	`MiniMax-M3`	1x	CNY 0.40 / 1M tokens	1M	Supported
MiniMax	Image 01	`image-01`	Per image	CNY 0.2 / image	—	Generation model
MiniMax	Image 01 Live	`image-01-live`	Per second	CNY 2 / second	—	Generation model
StepFun	Step 3.7 Flash	`step-3.7-flash`	1x	CNY 0.40 / 1M tokens	256K	Supported
ByteDance / Doubao	Doubao Seed 2.0 Code	`doubao-seed-2.0-code`	3x	CNY 1.20 / 1M tokens	200K	Supported
ByteDance / Doubao	Doubao Seed 2.0 Pro	`doubao-seed-2.0-pro`	3x	CNY 1.20 / 1M tokens	128K	Supported
Xiaomi / MiMo	MiMo V2.5 Pro	`mimo-v2.5-pro`	3x	CNY 1.20 / 1M tokens	1M	Not supported
Xiaomi / MiMo	MiMo V2.5	`mimo-v2.5`	2x	CNY 0.80 / 1M tokens	1M	Supported
DeepSeek	DeepSeek V4 Pro	`deepseek-v4-pro`	7.5x	CNY 3.00 / 1M tokens	1M	Not supported
DeepSeek	DeepSeek V4 Flash	`deepseek-v4-flash`	2.5x	CNY 1.00 / 1M tokens	1M	Not supported
Moonshot AI / Kimi	Kimi K2.6	`kimi-k2.6`	2x	CNY 0.80 / 1M tokens	256K	Supported
Moonshot AI / Kimi	Kimi K2.7	`kimi-k2.7`	6x	CNY 2.40 / 1M tokens	256K	Supported
Zhipu AI / Z.ai	GLM 5.1	`glm-5.1`	5x	CNY 2.00 / 1M tokens	256K	Supported
Zhipu AI / Z.ai	GLM 5.2	`glm-5.2`	8x	CNY 3.20 / 1M tokens	1M	Supported

4. API Access for Developers

Regional API Base URLs

For customers outside Mainland China, use the nearest overseas node as your Base URL. Your API key, model IDs and request format stay the same; only the Base URL changes.

Customer location	Recommended API Base URL	Notes
Mainland China, including Fujian	`https://api.llm-token.cn/v1`	Mainland route. Use this if the overseas domains are blocked or unstable from a mainland network.
North America and South America	`https://gpt-agent.cc/v1`	Default Americas node, suitable for the US, Canada and Latin America.
Europe and Africa	`https://eu.gpt-agent.cc/v1`	European node, recommended for customers in Europe and Africa.
Southeast Asia, Hong Kong, Taiwan, Japan, Korea, Australia and New Zealand	`https://hk.gpt-agent.cc/v1`	Hong Kong node, recommended for Asia-Pacific and Oceania routes.

If you are unsure which node to choose, start with the physically closest region. If access is unstable, switch to a nearby node and test again.

Chat Completions

curl https://gpt-agent.cc/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {"role": "user", "content": "Summarise this project in three bullet points."}
    ]
  }'

Image Generation

curl https://gpt-agent.cc/v1/images/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A clean modern product banner for an AI platform, blue and white colour palette, professional SaaS style",
    "response_format": "url",
    "n": 1,
    "aspect_ratio": "16:9"
  }'

New on 14 July 2026: gpt-image-2-4k provides 4K image output and is priced at CNY 0.50-1.00 per image.

Image tip: URLs returned by image APIs may be temporary. Download or store generated images if they are needed for a website, campaign or production workflow.

Common Request Fields

Field	Purpose
`model`	The model ID. Copy it exactly from the model list.
`messages`	Used for chat-style requests.
`prompt`	Used for image generation or simple text-style tasks.
`response_format`	For images, `url` is usually easiest for testing and download.
`aspect_ratio`	Image ratio, for example `1:1`, `16:9` or `9:16`.

5. Tool Setup Guides

Universal setup pattern: choose an OpenAI-compatible or custom provider, enter the Guishu API base URL, paste your API key, then choose the model ID.

Tool or guide	English setup instructions
MiniMax / Guishu image generation	Use `https://gpt-agent.cc/v1/images/generations`. Choose `image-01`, `image-01-live` or `gpt-image-2` according to the required image workflow. Start with one image per request for testing.
OpenClaw	Open settings, add an OpenAI-compatible provider, set Base URL to `https://gpt-agent.cc/v1`, paste your API key, then select a model such as `claude-sonnet-4-6`, `MiniMax-M3` or `gpt-5.4`. For long-context work, confirm the client context window is not capped locally.
Tencent Cloud	When using a Tencent Cloud function, workflow or server-side app, store the Guishu API key as an environment variable and call the compatible endpoint from your backend. Avoid placing keys in frontend code.
Cherry Studio	Add a custom OpenAI-compatible provider. Use Base URL `https://gpt-agent.cc/v1`, paste your API key, and enter the model ID exactly as listed.
Claude Code	Use the supplied one-click script where available, or configure a compatible model route through your local provider settings. Recommended default: `claude-sonnet-4-6`. Use `claude-opus-4-8` or `claude-fable-5` only for high-value work.
Codex	Configure an OpenAI-compatible endpoint with `https://gpt-agent.cc/v1`. Use coding-focused models such as `gpt-5.3-codex-spark`, `gpt-5.4`, `doubao-seed-2.0-code` or `deepseek-v4-pro`.
Hermes	Configure the gateway or client provider with the Guishu base URL and API key. Recommended models are `claude-sonnet-4-6` for high concurrency and `MiniMax-M3` for long-context workflows.
gpt-image-2 image model	Use the image generation endpoint and set `model` to `gpt-image-2`. This model is best for higher-quality images, design assets and polished marketing visuals.
WorkBuddy	Add a custom AI provider. Set the Base URL to `https://gpt-agent.cc/v1`, paste the API key, then choose a model. If a saved model name fails, copy a model ID directly from this guide.
OpenCode	Use an OpenAI-compatible provider. For fast coding choose `gpt-5.3-codex-spark` or `step-3.7-flash`. For complex refactors choose `deepseek-v4-pro`, `gpt-5.5` or `claude-opus-4-8`.
VS Code	For extensions that support custom OpenAI-compatible providers, enter the Base URL, API key and model ID. Test with a short prompt before starting a long coding session.
Chatbox	Select a custom OpenAI-compatible source. Use Base URL `https://gpt-agent.cc/v1`, paste your API key, and select a model. If the client asks for the full endpoint, use `https://gpt-agent.cc/v1/chat/completions`.
Trae	Use the custom provider or OpenAI-compatible configuration. Choose a coding model and run a small test prompt before applying it to an existing repository.
Cursor	Use custom model/provider settings where available. Add the Guishu base URL and API key, then select a coding model. Keep high-rate models for complex planning or review rather than every autocomplete request.
Image web app	Open image2.gpt-agent.cc, choose the image model, enter your prompt and download the result after generation.

Recommended Tool Defaults

Scenario	Recommended models
Daily automation and high concurrency	`claude-sonnet-4-6`, `MiniMax-M3`, `mimo-v2.5`
Complex reasoning and high-quality writing	`gpt-5.5`, `deepseek-v4-pro`, `claude-opus-4-8`
Top-tier long-running Agent tasks	`claude-fable-5`
Fast code iteration	`gpt-5.3-codex-spark`, `doubao-seed-2.0-code`, `step-3.7-flash`, `kimi-k2.7`, `glm-5.2`
Image generation	`gpt-image-2`, `gpt-image-2-4k`, `image-01`, `image-01-live`

6. Image Prompting Guide

For image generation, a clear prompt normally produces a better result. A useful structure is:

A [ratio] [use case] image of [subject], in [style], with [colour palette], [composition], [important constraints].

Example:

A 16:9 marketing banner for an AI platform, clean SaaS style, blue and white colour palette, a subtle data visualisation background, premium and professional, no text.

For social media or article covers, use 16:9. For app icons and avatars, use 1:1. For mobile posters, use 9:16.

7. Troubleshooting

Issue	What to check
Authentication failed	Check that the header is exactly `Authorization: Bearer YOUR_API_KEY`. Make sure there are no extra spaces before or after the key.
Model not found	Copy the model ID exactly from the model list. Model names are case-sensitive and hyphen-sensitive.
Client rejects the URL	If the client asks for a Base URL, use `https://gpt-agent.cc/v1`. If it asks for a full endpoint, use `https://gpt-agent.cc/v1/chat/completions`.
Image URL expired	Download generated images promptly. Temporary image URLs are not intended as permanent asset hosting.
Context window appears too small	Some local clients cap context length in their own settings. Increase the local context window where supported, especially in OpenClaw or similar Agent tools.
Slow streaming or timeout	Image generation and long Agent tasks can take longer than normal chat. Increase client timeout settings and test with a shorter request first.
Balance seems wrong	Check usage at token.gpt-agent.cc. Billing is based on actual model rate and token usage recorded by the system.

OpenClaw 16k Context Fix

If OpenClaw reports a rate limit or context issue while the selected model supports a much larger context window, the local client may still be capped at 16k. Check the OpenClaw model or gateway configuration and raise the context setting to match the model you intend to use.

Support Case Style

When reporting an issue to support, please include:

Your API key name or account identifier, but never paste the full secret key in a public chat.
The model ID you used.
The client or tool name.
The Base URL or endpoint you configured.
The exact error message and approximate time of the request.

8. Coverage of the Chinese Source Documents

This English guide consolidates and localises the main Chinese guide and its linked child documents. The content has been rewritten for international customers rather than translated word-for-word.

Chinese source area	Where it appears in this English guide
Main Guishu Token user guide	Sections 1, 2, 4 and 7
Model list	Section 3
Model pricing and billing	Section 2 and Section 3
MiniMax image generation guide	Section 4 and Section 6
OpenClaw setup guide	Section 5 and OpenClaw context fix in Section 7
Tencent Cloud setup guide	Section 5
Cherry Studio setup guide	Section 5
Claude Code deployment guide	Section 5
Codex deployment guide	Section 5
Hermes deployment guide	Section 5
gpt-image-2 image model guide	Section 4 and Section 6
WorkBuddy setup guide	Section 5
OpenCode setup guide	Section 5
VS Code setup guide	Section 5
Chatbox setup guide	Section 5
Trae setup guide	Section 5
Cursor setup guide	Section 5
Web image model guide	Section 5 and Section 6
FAQ and customer cases	Section 7

Need help? For enterprise onboarding, invoicing, larger top-ups, dedicated routing or team deployment support, please contact your Guishu account manager or customer support contact.

Guishu LLM Token User Guide (English)