// Cline (open source)
Cline pricing and models
Open-source agent for VS Code and the terminal. Free; bring your own key for any model and pay only for tokens.
All coding toolsPlans checked 2026-10-27
- Free plan
- Yes
- Paid from
- Tokens only
- Own API key
- Yes
- Open source
- Yes
Plans
VS Code extension and CLI.
| Plan | Price | What you get |
|---|---|---|
| Open Source | Free | Free extension and CLI; inference at cost or with your own key |
| Enterpriseteam | Customcustom | SSO, RBAC, centralised billing, SLA |
Strongest models you can plug in
LiveBench coding and long-horizon agentic scores, strongest coder first, with what the same heavy month of agent work would cost paying per token.
| Model | Coding | Long-horizon agentic | Same work via API |
|---|---|---|---|
| Claude Fable 5.1 | 97.7 | 77.9 | $6,540/mo |
| Claude Opus 5.5 | 96.3 | 72.8 | $2,672/mo |
| DeepSeek V4.1 Flash 1017 | 96.0 | 40.9 | $171.36/mo |
| GPT-6.1 Sol | 96.0 | 68.7 | $1,336/mo |
| Claude Sonnet 5.5 | 94.7 | 63.4 | $1,336/mo |
| GPT-6.1 Terra | 94.3 | 48.6 | $668.00/mo |
| GPT-6 Astra | 93.7 | 77.5 | $6,960/mo |
| Claude Haiku 5.5 | 91.4 | 40.0 | $69.60/mo |
Any model you have a key for — you pay the provider directly at cost.
Compare Cline with
Cline FAQ
How much does Cline cost?
Cline has a free plan (free extension and cli; inference at cost or with your own key). Prices from Cline (open source)’s pricing page, checked 2026-10-27.
Which models does Cline use?
Any model you have a key for — you pay the provider directly at cost. The strongest coding model on LiveBench right now is Claude Fable 5.1 (97.7).
Can I use Cline with my own API key?
Yes — usage is then billed per token by the provider instead of by a plan. A heavy coding-agent month (40K tokens in, 4K out, 20K requests, 70% cached) on Claude Fable 5.1 comes to about $6,540 at list price.
Where these numbers come from
- Plans and prices — each vendor's own pricing page, checked 2026-10-27: Cline. Usage allowances change often; check before you buy.
- Model scores — LiveBench coding and long-horizon agentic categories for the models each plan includes, live from the same data as the leaderboard. A tool's own agent loop matters too; these scores rate the model, not the tool.
- “Same work via API” — a heavy coding-agent month (40K tokens in, 4K out, 20K requests, 70% cached input) at OpenRouter list price, for comparing a subscription against paying per token.