Users can run Cline Cloud Agents with any AI model, including free trial access using models such as DeepSeek-V4.1-Flash. Cline is also offering ClinePass, a subscription providing approximately 5x discounted access to open-weights models.
Cline has launched Cline Cloud Agents, allowing users to run the AI assistant directly from a browser. Tasks run in a secure cloud sandbox to write code, test implementations, and open pull requests on GitHub repositories.
Cline reported that Mistral Large 4 outperformed Opus 5.5 and GPT-6 Astra on cybersecurity benchmarks, largely because the competing models had approximately 40% of tasks blocked by safety filters.
Cline has added Mistral Large 4 support across its command-line interface and desktop application. The team stated the model enables security-focused workflows previously blocked or unavailable when using GPT or Claude models.
Cline has added Pareto 26.10 Preview, a model that routes queries to multiple frontier and open models, grades the answers, and returns the top result. Cline states it matches Fable's DeepSWE score at $0.24 per task compared to $13.41.
Cline is pausing its free DeepSeek-V4.1-Flash promotion because of abnormally high abuse and says it is investigating how to mitigate the problem.
Cline has added Ling 3.1 Flash and is offering it free until October 13. The mixture-of-experts model has 560 billion total parameters and 25 billion active parameters, and Cline says it is on par with open-weight models such as Kimi K3 and DeepSeek V4 Pro.
Cline now offers GPT-6.1 Sol. On DeepSWE v1.1, Cline says the model matches GPT-6 Astra at roughly one-fifth of the cost.
Cline says it was featured at Meta Connect and that Meta’s Muse Spark 1.3 contributor variant is completely free through Cline provider. No end date or other eligibility limit is stated.
Cline says Sonnet 5.5 beats Opus 5.5 on Terminal-Bench 4.0 while costing half as much. Cline also says it uses fewer tokens than earlier models, cuts cost by up to 30% per task, and generates output 30% faster than its predecessor.
Cline says Ember-1 is available in Cline now, and that quicker thinking is especially noticeable in its new Desktop app.
Cline says the Pixel Canary stealth model has been released and is free in Cline. On Next.js Agent Evals, Cline says it ties GPT-6 Astra and beats Kimi K3.
Gemini 3.8 Flash is free in Cline. Cline says it scores 41 on the Artificial Analysis Intelligence Index, runs at 291 tokens per second, and has a 1 million-token context window.
Cline says the stealth model is free in Cline, with multimodal input and a 1M-token context window. It also describes the model as having fast inference and strong coding capabilities.
Cline links the offer to its Kimi K3 promo at cline.bot/desktop, without stating an end date or eligibility limits.
Parallel tasks each run on a separate branch under ~/.cline/worktrees/<id>. The release also shows a branch’s pull request link, merge status, and CI checks when gh is available, and can assign several tasks to subagents in one session.
Cline said flagship model MiMo-v2.6-Pro is officially out and already available in ClinePass. It also called the model the best-performing open-weights model on the artificial intelligence index.
Cline said Grok 4.7 is live in Cline, with 40% off through 9/27. The company also said the model scores close to GPT 5.6 Sol and Fable 5.1 on DeepSWE, with high TPS and about 8x cheaper cost.
