API for developers
An LLM API for developers: OpenAI-compatible with no token limits
You write code, not token budgets. Tenzo Cloud speaks the OpenAI protocol: change the address and key, and your SDKs, plugins and agents keep working with a monthly price known upfront.
What is inside
- OpenAI-format Chat Completions with streaming
- A compatible mode for Claude Code
- Keys restricted by IP, models, expiry and streams
- OpenAI-format errors with clear codes
- A public model status page
Two lines to the first answer
from openai import OpenAI
client = OpenAI(base_url="https://tenzo-cloud.com/v1", api_key="tc-your-key")
stream = client.chat.completions.create(
model="qwen-3.8-max",
messages=[{"role": "user", "content": "Hello!"}],
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="")Limits
| Parameter | Value |
|---|---|
| Tokens | Unlimited |
| Concurrent requests | As many as streams bought |
| New requests per minute | Up to 120 per account |
| API prompt retention | None |
Models
- Qwen 3.8 MaxOperationalBest for: large codebases and documentsContext: 256K tokensReads screenshots and diagrams
- GLM 5.3Coming soonBest for: code and agentsContext: 200K tokensText and code only
- DeepSeek V4 ProComing soonBest for: reasoning and reviewsContext: 128K tokensText and code only
- GLM 5.3 FlashComing soonBest for: fast, high-volume tasksContext: 128K tokensReads screenshots and diagrams
- DeepSeek V4.1 FlashComing soonBest for: fast, high-volume tasksContext: 128K tokensReads screenshots and diagrams
Pricing
A fixed price per stream for the chosen period. No token bill and no auto-renewal.
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 DeepSeek V4 Pro
Coming soon1 stream 4+ streams, each 3 days $2.21₸950 $1.70₸730 7 days $4.55₸1,950 $3.50₸1,500 30 days $12.74₸5,530 $9.80₸4,250 GLM 5.3 Flash
Coming soon1 stream 4+ streams, each 3 days $2.47₸1,040 $1.90₸800 7 days $4.81₸2,080 $3.70₸1,600 30 days $13.91₸6,020 $10.70₸4,630 DeepSeek V4.1 Flash
Coming soon1 stream 4+ streams, each 3 days $2.47₸1,040 $1.90₸800 7 days $4.81₸2,080 $3.70₸1,600 30 days $13.91₸6,020 $10.70₸4,630
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
Is the API compatible with the OpenAI SDK?
Yes. The official openai libraries for Python and Node.js work as is; only base_url and the key change.
Is there a trial?
3 hours with every model, 1 stream, no card. Once per account.
What do errors look like?
OpenAI format: an error object with message, type and code, such as invalid_api_key, no_access, concurrency_limit.
See also
- IntegrationsLLM API in Python: the official openai library, two linesHow to call Qwen 3.8 Max and GLM 5.3 from Python with the official openai library: streaming, a key in an environment variable, error handling. No token limits, no VPN.Learn more
- IntegrationsLLM API in Node.js: the official openai SDK without rewriting codeHow to connect Qwen 3.8 Max and GLM 5.3 in Node.js and TypeScript with the official openai SDK: streaming, a key in the environment, common errors. No token limits, no VPN.Learn more
- ComparisonsTenzo Cloud or the OpenAI API: a subscription versus a token billHow Tenzo Cloud differs from the OpenAI API: a fixed price per stream instead of per-token billing, no VPN from Kazakhstan and Russia, prices in tenge or rubles, prompts not stored.Learn more
- ComparisonsTenzo Cloud or OpenRouter: a per-token aggregator versus a subscriptionTenzo Cloud or OpenRouter: a per-token model aggregator versus a model subscription at a fixed price per stream. Prices in tenge or rubles, prompt retention, access from the CIS. October 2026.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.