Power Hermes, OpenCode, OpenClaw, Aider, and other high-volume agents without counting tokens or managing GPUs. Unlimited token usage, transparent concurrency, and no overage charges. Now live as Stream.
Available through the Camel Stream API platform.
Why flat rate
Stop engineering around the token bill. #
Agent workloads read files, call tools, retry, and carry long histories. Their cost is difficult to predict because their work is difficult to predict.
No token meter
Use the model without a monthly token allowance or surprise overage line item.
Capacity you can understand
One active generation on the founding plan. Extra requests queue instead of increasing your bill.
No GPU operations
We handle model weights, serving, recovery, routing, and cache management.
Common deployment patterns
Put unlimited DeepSeek to work. #
Use the flat-rate API as your primary inference layer, an overflow path, or backup capacity.
Power your free tier
Offer useful AI features to every user without attaching an open-ended per-token cost to adoption.
Keep users going past limits
Route requests to DeepSeek after premium-model credits run out, so users can keep working while you protect margins.
Run high-volume agents
Power request-heavy coding agents and autonomous tools like Hermes and OpenClaw without metering every loop.
Back up your main provider
Add a fallback route for outages or degraded service, keeping critical AI workflows available when your primary provider is not.
Coding agent compatibility
One DeepSeek API for Hermes, OpenCode, OpenClaw, Aider, and more. #
If your coding agent accepts a custom OpenAI-compatible endpoint, it can use Stream without changing the rest of your workflow.
Hermes
Keep tool calls, file operations, retries, and long agent sessions moving without metering every loop.
Read the setup guideCustom provider
OpenCode
Add Stream as an OpenAI-compatible provider and select DeepSeek V4 Flash from the model picker.
Read the setup guideCustom provider
OpenClaw
Use a custom model provider for always-on automations, coding workflows, and high-volume agent tasks.
Read the setup guideOpenAI-compatible
Aider
Point Aider at the Stream base URL and run repository-scale coding sessions against a predictable bill.
Read the setup guideDrop-in by design
Keep your client. Change the endpoint. #
The API follows the OpenAI format, including streaming, tool calling, and structured output.
from openai import OpenAI # Change the base URL and key.client = OpenAI( base_url="https://api.camelai.com/v1", api_key="$CAMELAI_API_KEY") response = client.chat.completions.create( model="deepseek-v4-flash", messages=messages, tools=tools, stream=True)
Unlimited, said clearly
No token cap. A real capacity boundary. #
Flat-rate inference only works when capacity is understandable. We are putting the boundary in the product instead of hiding it in fair-use language.
Unlimited tokens
No monthly token allowance and no per-token overages.
One active generation
Additional requests queue on the founding plan.
256K context
Long agent sessions without an ambiguous million-token promise.
24/7 access
Not a reserved daily time block. Generate whenever you need to.
Founding plan
For developers who want a predictable DeepSeek bill and can work within one active generation at a time.
Billed monthly. Cancel anytime. Need more concurrency? Contact us.
What's included
Frequently asked questions
Before you sign up. #
Build without watching the meter. #
Unlimited DeepSeek V4 Flash (0731) at one fixed monthly price. Sign up and start generating in minutes.
Questions first? Contact us.