Cline with a cheaper API: UberLLM as an OpenAI Compatible provider
In Cline’s settings choose API Provider "OpenAI Compatible", enter Base URL https://api.uberllm.dev/v1 (with /v1) and your UberLLM key, then pick a Model ID from the list. Set the context window under Model Configuration.
In VS Code, open the Cline panel and click the gear icon.
Set API Provider to OpenAI Compatible.
Fill in:
Base URL: https://api.uberllm.dev/v1
OpenAI Compatible API Key: your ull_… key
Model ID: pick moonshotai/kimi-k3 from the list. If it is not shown, choose Use custom model ID… and type it.
Open Model Configuration and set Context Window Size and Max Output Tokens to the numbers on the model's page (uberllm.dev/models). Turn on Supports Images only for models that take pictures.
Close settings and start a task.
Type the /v1. Current Cline versions use the Base URL exactly as entered and no longer add /v1 for you.
Plan and Act on different models
Cline can use one model to plan and another to act. A strong model for Plan (moonshotai/kimi-k3) and a cheap one for Act (deepseek/deepseek-v4.1-flash) cuts the bill on long tasks, since acting is where most tokens go. Set it under Cline's Plan/Act settings, using the same provider for both.
Prices in Cline's cost counter
Model Configuration has Input Price / 1M tokens and Output Price / 1M tokens. Cline only uses them to show a cost estimate per task. Copy them from the table below if you want that estimate close; your real charge is always in Dashboard → Activity.
Troubleshooting
Model list empty, or every request 404s: the Base URL is missing /v1. It must be exactly https://api.uberllm.dev/v1.
401: the key is wrong or has a trailing space.
The model stops using tools, or Cline says a required parameter is missing: pick a model from the first table; small models drift out of Cline's tool format.
Context window exceeded: Cline did not know the model's size. Set Context Window Size in Model Configuration.
402 insufficient credits: add credit on the credits page. For a hard ceiling, set a spend limit on the key.
Prices at the last hourly build, no fee added · every model →
FAQ
What base URL does Cline need for UberLLM?
https://api.uberllm.dev/v1, typed in full with /v1, under API Provider "OpenAI Compatible". Cline uses the Base URL exactly as entered.
Which UberLLM models work best with Cline?
Models with reliable tool calls and long context, such as the Claude, GLM, Kimi, DeepSeek and Qwen Coder models listed on the guide with their live prices.