- AppYour request
- Flonno gatewayKey and credit
- qwen3.8-27bJSON or text
qwen3.8-27b · OpenAI-compatible
The fast Qwen API.For a fraction.
OpenAI-compatible. Swap one base URL and ship bulk JSON, tagging and coding agents.
No cardPrompts not stored$0.05 / 1M in
from openai import OpenAI
client = OpenAI(
base_url="https://www.flonno.com/v1",
api_key="flo_…",
)
r = client.chat.completions.create(
model="qwen3.8-27b",
response_format={"type": "json_object"},
messages=[{"role": "user",
"content": "Extract name, city from: …"}],
)Response● 115 tok/s · 1.06 s total
Sample response, not a live call.
{ "name": "Ada Lovelace", "city": "London" }115 tok/sOutput speed
$0.05per 1M input tokens
$0.80per 1M output tokens
$1free on signup
Works withOpenAI SDKLiteLLMClineContinueLangChaincURL
Swap one URL. Keep your code.
OpenAI-compatible
One base URL. Your SDK stays.
JSON mode
Ask for an object. Check the keys.
No prompt storage
Prompts and completions are not stored.
Usage dashboard
Credit, requests, and tokens.
Coding agents
base_url = "https://www.flonno.com/v1"
Cline, Continue, OpenCode, and Aider.
$0.05 / $0.80
Input and output, per million tokens, for a new account.
Before the first call.
Does bulk JSON mean a batch API?
No. Each extraction, classification, or tag is one chat completion. This is not a batch product.
How does the $1 free credit work?
Create an account and verify your email to receive $1 free credit. No card is required for that credit.
How fast is it?
The current 24-hour average is 115 tokens per second. It is measured from the first streamed token to the last, with thinking disabled. Real prompts vary. It is a measurement, not a guarantee.
Are prompts stored?
No. Prompts and completions are not stored.