Cut your Cline API bill with flat-rate models

Cline is a coding agent, and coding agents burn tokens: they read files, keep large context, retry, and send many requests per task. On per-token providers that makes the bill scale with how hard the agent works. CheapestInference exposes an OpenAI-compatible Chat Completions endpoint at https://api.cheapestinference.com/v1, so you can point Cline at it and, during your reserved time blocks, run it with no per-token billing — the cost is a flat monthly subscription instead.

Setup (2 minutes)

1. Subscribe to a pool and copy your subscriber key (sk-...) from the dashboard.

2. In VS Code, open Cline’s settings (the ⚙️ icon in the Cline panel) and set the API Provider to OpenAI Compatible.

3. Fill in the three fields:

   • Base URL: https://api.cheapestinference.com/v1
   • API Key: your subscriber key (sk-...)
   • Model: a model id from the table below, e.g. glm-5.3

4. Save. Cline now sends every request to your pool. Switch models any time by changing the Model field — no new key.

Which model id to use

You want	Set Model to	Pool
Kimi K3	kimi-k3	Flagship
GLM 5.3	glm-5.3	Frontier
MiniMax M3	minimax-m3	Frontier
DeepSeek V4.1 Flash	deepseek-v4.1-flash	Core
MiMo v2.5	mimo-v2.5	Core

A subscription covers every model in its pool, so you can switch models by changing the Model field — no new key, no new plan.

Which model for Cline

For agentic coding — planning edits, calling tools, iterating across files — the strongest fits are Kimi K3 (Flagship Pool), Moonshot’s flagship agentic and coding model, and GLM 5.3 (Frontier Pool), a capable frontier coding and reasoning model.

If you want a cheaper option that still handles large repositories, use DeepSeek V4.1 Flash from the Core Pool: it pairs high speed with the lowest price and handles big codebases and long agent conversations well. MiMo v2.5 is the other Core Pool model.

Pick by pool and price on the pools page; you can change the Model field whenever a task calls for a different one.

Why flat-rate for a coding agent

A coding agent’s token count is unpredictable: the same feature might take one clean pass or a dozen read-edit-retry cycles, each one re-sending context. Under per-token billing that variance lands directly on your invoice. With a CheapestInference subscription the price is fixed per pool per month, so a heavy Cline session and a light one cost the same. See current pool pricing on the pools page.

Notes

• Unlimited during your blocks: within your reserved time blocks there are no token caps, so an agent that reads and retries a lot does not cost more. Outside your blocks, requests are rejected until the next block starts — see Unlimited Subscriptions.
• Concurrency: a subscription is sized for one active session at a time. Cline runs one task at a time, which fits this model well.
• Other tools: the same base URL and key work in any client that speaks the OpenAI API. If your tool speaks the Anthropic API instead, use https://api.cheapestinference.com/anthropic — see the Claude Code guide.