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. kimi-k2.7

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
GLM 5.2	glm-5.2	Frontier
Kimi K2.7	kimi-k2.7	Frontier
Kimi K2.6	kimi-k2.6	Frontier
MiniMax M3 (1M context)	minimax-m3	Frontier
DeepSeek V4 Flash (1M context)	deepseek-v4-flash	Core
MiMo v2.5 (1M context)	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 Frontier models are the strongest fit: Kimi K2.7 is Moonshot’s flagship agentic and coding model, and GLM 5.2 is a capable frontier coding and reasoning model. Both are in the Frontier Pool.

If you want a cheaper option that still handles large repositories, use DeepSeek V4 Flash from the Core Pool: it pairs high speed with a 1M-token context window, so a big codebase or a long agent conversation fits in a single request. MiMo v2.5 is the other Core Pool model and also has a 1M-token context window.

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.