PRICING
Flat price
$5 a month is the whole bill. There is no token allowance behind it and no overage line waiting at the end of the month.
STREAM BY CAMELAI
Inference,
without a meter.
One subscription, one visible queue, and unlimited DeepSeek V4 Flash tokens for $5 a month. Nothing is counted against you.
How it works
Three steps. No invoice surprises.
01
Subscribe
Create an account at stream.camelai.com and start the founding plan. Your API key is issued immediately — there's no approval step.
02
Point your client
Stream speaks the OpenAI API format. Swap the base URL and model name in the SDK you already use and keep the rest of your code.
03
Generate
Send as much work as you want. One request generates at a time, the rest wait in a visible queue, and the bill stays $5.
api.camelai.com/v1
model deepseek-v4-flash
stream true
tools enabled
Tokens
38.4M
This month
$5.00
Overages
$0.00
streaming response · 84 tok/squeue
What Stream is
One subscription. One queue. No meter.
CAPACITY
A queue you can see
Capacity on Stream is a queue, not a fee. Send more than one request and the extras wait their turn instead of raising your bill.
COMPATIBILITY
The format you already use
Streaming, tool calling, and structured output through the OpenAI API shape. Your SDK, your framework, your existing code.
The model
Serving DeepSeek V4 Flash.
Stream runs one model today, chosen for coding agents and high-volume applications, on a fleet we operate ourselves. Running the hardware is what makes a flat price possible — and it means more models can join Stream without changing how you pay.
256K context
Room for long agent sessions and full codebases in one request.
Self-hosted fleet
No GPU setup, no capacity planning, no ops on your side.
Streaming and tools
Server-sent events, tool calls, and structured output on every request.
Founding plan
$5/ month
Unlimited tokens One active generation 256K context No overages
Get started Billed monthly. Cancel anytime. Questions or need more concurrency? Contact us.
Frequently asked questions