Cline Pass Pricing: What $9.99/Month Gets You in Models and Limits
Cline Pass costs $9.99/month and bundles Kimi K3.1 Pro, GLM 5.3, DeepSeek V4.1 Flash and more with tiered usage limits for agentic coding.
What is Cline Pass and how much does it cost?
Cline Pass is a $9.99 per month subscription from the Cline team that bundles access to a rotating lineup of strong open models, including Kimi K3.1 Pro, GLM 5.3, GLM 5.3 Flash, DeepSeek V4.1 Flash, MiniMax M3.1 Flash, and QN3 Max. Cline negotiated volume pricing directly with the labs behind these models, then passed that down as a flat monthly fee instead of per-token billing. Usage is capped with 5-hour, weekly, and monthly limits rather than a hard token ceiling, which makes it a practical fit for agentic workflows that burn through a lot of context.
TL;DR
- Cline Pass costs $9.99 a month and gives access to a bundle of open models rather than a single provider’s lineup.
- Kimi K3.1 Pro is now the default model on the plan, with GLM 5.3, GLM 5.3 Flash, DeepSeek V4.1 Flash, MiniMax M3.1 Flash, and QN3 Max also included.
- Instead of metering by token, Cline Pass applies 5-hour, weekly, and monthly usage limits that are generous relative to the price.
- The plan is well suited to token-heavy agentic workflows like multi-agent design reviews, where several fresh sub agents each read a full document and codebase from scratch.
- Because the plan includes multiple model families, you can mix models by task, using a stronger model for long reasoning and faster, cheaper models for lighter review passes.
- Cline Pass works through the VS Code extension or the CLI, and the same credentials can be used via an API key with Cline’s API base URL in other agent harnesses.
- Cline is also usable inside multi-agent orchestration setups where one session acts as a coordinator and spins out isolated worker sessions running Cline Pass models in parallel.
Plans first. Then code.
Remy writes the spec, manages the build, and ships the app.
What models are included in Cline Pass?
The lineup centers on open models rather than closed frontier models from the big three labs. As of the current rollout, Cline Pass includes:
- Kimi K3.1 Pro, now the default model on the plan, described as strong for long, careful conversations and for drafting detailed documents.
- GLM 5.3 and GLM 5.3 Flash, with the full GLM 5.3 positioned as a solid choice for reading and critiquing actual code.
- DeepSeek V4.1 Flash, a fast option suited to lighter review tasks.
- MiniMax M3.1 Flash, another fast model in the same tier as DeepSeek’s flash variant.
- QN3 Max, rounding out the set.
This is a notably different approach from a single-model subscription. Instead of locking you into one lab’s roadmap, Cline Pass functions more like a model marketplace with one bill. For developers who already juggle multiple model APIs for different tasks (long context reasoning versus fast, cheap review passes) having them all under one flat-rate plan removes the friction of managing separate accounts and separate pricing.
How do the usage limits work?
Cline Pass doesn’t bill per token the way raw API access does. Instead, it applies limits across three windows: a 5-hour rolling limit, a weekly limit, and a monthly limit. The exact numeric caps weren’t detailed in available coverage, but the structure is designed around how agentic coding sessions actually behave: bursts of heavy activity (a long design review, for instance) followed by quieter stretches.
This tiered structure matters more than it might first appear. Pure per-token pricing punishes workflows that intentionally re-read large files or spin up several sub agents in parallel, since every read adds to the bill. A flat monthly fee with soft usage windows means a developer can run an expensive, multi-pass workflow (like a full agentic design review with five or six reviewer passes) without doing mental math on cost before every step.
Why does Cline Pass pair well with multi-agent review workflows?
Agentic coding patterns that use multiple fresh sub agents, sometimes called “elephant and goldfish” patterns after a workflow popularized in a Google-published open source project, are inherently token-hungry. In that pattern, one long-running agent (“the elephant”) holds full project context and drafts a design document, while several short-lived “goldfish” sub agents with zero memory of the conversation review that document from scratch, each through a different lens: architecture risk, comprehension gaps, cost and scaling concerns, implementation readiness, and so on.
Every goldfish reviewer has to read the design document and referenced code files independently. Run that five or six times per review round, and then run review rounds again after revisions, and the token cost adds up quickly on a standard metered plan. On a $20 flat-rate plan from a single lab, that kind of workflow can burn through limits fast. Cline Pass’s flat $9.99 fee combined with its usage windows makes repeated, heavy review cycles far less costly to experiment with.
Remy doesn't write the code. It manages the agents who do.
Remy runs the project. The specialists do the work. You work with the PM, not the implementers.
There’s also a structural benefit beyond price: because Cline Pass bundles several distinct model families rather than variants of one model, you can assign different models to different reviewer roles. A long-context model good at careful reasoning can act as the elephant drafting the document. A model known for strong code comprehension can run the harder, more adversarial review passes. Faster, lighter models can handle simpler comprehension checks. Since a goldfish review is supposed to avoid sharing the elephant’s blind spots, using genuinely different models for different roles reinforces that independence in a way that a single-model-family plan can’t.
Is Cline Pass worth it compared to a single-lab subscription?
For developers running heavy, exploratory, or multi-agent coding workflows, Cline Pass is priced well below typical single-provider subscriptions while covering several capable open models. It won’t replace frontier closed models for every task, since Kimi, GLM, DeepSeek, MiniMax, and QN3 Max are open models with their own strengths and limits rather than drop-in replacements for the top proprietary systems. But for the specific category of “agent needs to read a lot of files, from a lot of fresh contexts, repeatedly” the economics favor a flat-fee, usage-windowed plan over per-token billing.
The trade-off is flexibility versus predictability. A metered API gives you precise cost control per call but can spike unexpectedly on heavy sessions. Cline Pass trades that precision for a flat monthly cost and soft usage ceilings, which is generally the better deal if your workflow regularly involves bursts of multi-agent activity rather than occasional single-shot requests.
How do you set up and use Cline Pass?
Cline Pass is accessible through the Cline extension for VS Code or through Cline’s CLI, installable via npm. During onboarding, you select Cline Pass as your plan. If you’ve already configured it in VS Code, the CLI picks up the same credentials automatically. For use in other agent harnesses or custom tooling, Cline supports generating an API key tied to your Cline account, which can then be pointed at Cline’s API base URL like any other OpenAI-compatible endpoint.
Cline also integrates into multi-agent orchestration setups where one session acts as a coordinating “architect” and dispatches isolated worker sessions for subtasks. In that kind of setup, the main session can serve as the long-context elephant while each worker, running a Cline Pass model, acts as an independent, read-only goldfish reviewer. Because each worker starts with no shared memory of the main conversation, the review stays genuinely fresh rather than just being another message in the same context window.
Frequently Asked Questions
How much does Cline Pass cost per month?
Cline Pass costs $9.99 per month as a flat subscription fee, rather than charging per token or per API call.
Which models are included in Cline Pass?
The plan currently includes Kimi K3.1 Pro (the default model), GLM 5.3, GLM 5.3 Flash, DeepSeek V4.1 Flash, MiniMax M3.1 Flash, and QN3 Max.
Does Cline Pass use token limits or usage windows?
It uses tiered usage limits across three time windows: a 5-hour limit, a weekly limit, and a monthly limit, instead of billing by individual token usage.
Why would a multi-agent coding workflow need a plan like this?
Workflows that spin up several independent sub agents to review the same document or codebase, each starting with no shared context, consume a lot of tokens quickly. A flat-rate plan with generous usage windows avoids the cost anxiety of running these reviews repeatedly on a metered API.
Can Cline Pass be used outside the Cline extension?
Seven tools to build an app. Or just Remy.
Editor, preview, AI agents, deploy — all in one tab. Nothing to install.
Yes. You can generate an API key from your Cline account and use it with Cline’s API base URL in other tools, in addition to using it directly through the VS Code extension or CLI.
