Integration
Claude Code with no limits: connect our models in a minute
Subscription limits run out mid-task and per-token API billing grows with every agent step. Connect Claude Code to GLM 5.3 or Qwen 3.8 Max with three environment variables and let the agent work as long as needed at a fixed price.
Why connect it
Claude Code is a strong terminal agent, but long sessions quickly hit subscription limits or a token bill. Every agent step is a new request with a large context.
In compatible mode Claude Code sends requests to Tenzo Cloud. The interface and commands stay the same, only the model behind them changes: GLM 5.3 for code and agents, Qwen 3.8 Max for large projects.
How to connect Claude Code
You need a key from the dashboard: 3 free hours start right after sign-up. Replace tc-your-key with your key.
Get a key
Sign up and create a key under API keys. You can restrict it by IP, models and expiry right away.
Set the environment variables
Open a terminal in your project folder and run the commands. They apply to this terminal window only.
export ANTHROPIC_BASE_URL=https://tenzo-cloud.com export ANTHROPIC_AUTH_TOKEN=tc-your-key export ANTHROPIC_MODEL=glm-5.3 export ANTHROPIC_SMALL_FAST_MODEL=glm-5.3 claudeKeep the settings
To avoid typing them every time, add the env block to ~/.claude/settings.json or the export lines to ~/.zshrc or ~/.bashrc.
{ "env": { "ANTHROPIC_BASE_URL": "https://tenzo-cloud.com", "ANTHROPIC_AUTH_TOKEN": "tc-your-key", "ANTHROPIC_MODEL": "glm-5.3", "ANTHROPIC_SMALL_FAST_MODEL": "glm-5.3" } }Check it
Run claude and ask it, for example, to explain the project structure. If you get an answer, you are connected.
How to roll back
Remove the variables or the env block and Claude Code goes back to your previous account.
unset ANTHROPIC_BASE_URL ANTHROPIC_AUTH_TOKEN ANTHROPIC_MODEL ANTHROPIC_SMALL_FAST_MODELCommon errors and fixes
- Claude Code asks you to log in to Anthropic
- The variables were not picked up: make sure they are set in the same terminal window, or add them to the env block of ~/.claude/settings.json and restart claude.
- Connection error to the address
- Claude Code needs the address without /v1: https://tenzo-cloud.com. The /v1 address is for OpenAI-compatible clients.
- 401 invalid_api_key, “key not found”
- Make sure the whole key is copied with no spaces or quotes and is enabled in the dashboard. Expired keys also return 401.
- 403 no_access, “no access to this model”
- There is no active subscription for this model, or the key does not allow this model or your IP. Check Plans and the key restrictions in the dashboard.
- 404 model_not_found
- The model id is wrong. Use an id from the model list, for example qwen-3.8-max or glm-5.3.
- 429 concurrency_limit
- All your streams are busy or you exceeded 120 requests a minute. Retry in a few seconds or buy more streams, they stack.
- 503 model_unavailable
- The model is under maintenance. Each model’s status is on the status page; switch models with one line.
Pricing
One subscription covers this tool, the chat and your own scripts.
Qwen 3.8 Max
Operational1 stream 4+ streams, each 3 days $2.73₸1,150 $2.10₸880 7 days $5.33₸2,280 $4.10₸1,750 30 days $14.30₸6,180 $11₸4,750 GLM 5.3
Coming soon1 stream 4+ streams, each 3 days $2.86₸1,240 $2.20₸950 7 days $5.72₸2,470 $4.40₸1,900 30 days $15.73₸6,830 $12.10₸5,250
Price per stream. Volume discount: 2–3 streams pay 88%, 4 or more pay 77% of the single-stream price. Streams and periods stack. Prices sync from the dashboard automatically.
FAQ
Which model should I use in Claude Code?
GLM 5.3 for agentic coding, Qwen 3.8 Max for large repositories and screenshots. Change it in ANTHROPIC_MODEL; see the Models page for the current status.
Do I need Claude Pro or Max?
No. Claude Code is a free tool, and Tenzo Cloud provides the models behind it on its own subscription.
How much does it cost and is there a token limit?
A subscription to a model at a fixed price per stream for 3, 7 or 30 days. Tokens are not counted; only concurrent requests and 120 requests a minute per account are limited. The first 3 hours are free, no card.
Do I need a VPN?
No. The API, site and chat work directly from Kazakhstan, Russia and the CIS.
Are my requests stored?
No. Prompts and answers sent through the API are not saved, neither in the database nor in logs. The journal keeps only time, model, status and token count.
See also
- ModelsGLM 5.3 API: a model for code and agents with no token billGLM 5.3 over an OpenAI-compatible API: a model for code and multi-step agents, 200K token context, works in Claude Code and Cursor. A fixed price per stream, no VPN.Learn more
- ComparisonsTenzo Cloud or Claude Max: unlimited-token streams versus usage windowsTenzo Cloud or the Claude Max subscription: usage limits versus streams with no token caps, API included, access from Kazakhstan and Russia, prices in tenge. Verifiable facts only, October 2026.Learn more
- BlogHow to connect Claude Code to Qwen and GLM, step by stepA step-by-step guide to running Claude Code on Qwen 3.8 Max and GLM 5.3 in compatible mode: environment variables, settings.json, choosing a model and common errors.Learn more
- IntegrationsCodex CLI with a custom provider: an agent without a token billHow to add Tenzo Cloud to Codex CLI as a separate provider in config.toml: GLM 5.3 and Qwen 3.8 Max with no token limits, no VPN. Guide, rollback and common errors.Learn more
Try it on your own work
Three free hours with every model, no card and no VPN. Connect Cursor, Claude Code or your own code in a minute.