Cline v3.85.0 Adds DeepSeek V4, Gemini 3.5 Flash, and GPT-5.5 Support
Cline, the AI coding assistant VS Code extension, released version 3.85.0 on May 25, 2025, adding support for DeepSeek V4 Flash and Pro models, Gemini 3.5 Flash across multiple providers, and GPT-5.5 through SAP AI Core. The update also fixes Vertex AI global endpoint handling for Claude models.
Cline v3.85.0 Adds DeepSeek V4, Gemini 3.5 Flash, and GPT-5.5 Support
Cline released version 3.85.0 on May 25, 2025, expanding its AI coding assistant with support for several new models and provider integrations.
New Model Support
The update adds DeepSeek V4 Flash and Pro models, bringing the latest DeepSeek releases to the VS Code extension. Cline now supports Gemini 3.5 Flash through both Google's Gemini API and Vertex AI providers. The release also adds GPT-5.5 support specifically for SAP AI Core integration.
Poolside's Laguna models now route through next-generation prompts and native tool calling, according to the changelog.
Provider and Infrastructure Updates
The release fixes Vertex AI global endpoint handling for Claude models, addressing routing issues for users of Anthropic's models through Google Cloud. Cline added a new /lg-task URI webhook integration for LG dashboard flows, though specific details of this integration were not disclosed.
Technical Changes
Version 3.85.0 updates two dependencies: diff and protobufjs. The release moves from cli-v3.0.13 to v3.85.0, representing a significant version jump in the numbering scheme.
About Cline
Cline is an autonomous coding agent that runs as a VS Code extension, allowing developers to interact with AI models for code generation, debugging, and terminal command execution. The tool supports multiple AI providers and model options through a unified interface.
What This Means
This update reflects the rapid pace of new model releases across the AI industry, with Cline maintaining compatibility within days of major model launches like DeepSeek V4. The addition of Gemini 3.5 Flash across multiple providers gives developers more routing options for cost optimization. The Vertex AI fix addresses a practical issue for enterprise users running Claude models through Google Cloud infrastructure rather than directly through Anthropic's API.
Related Articles
Google Rolls Out Gemini 3.8 Flash, Third Flash Update in Three Months
Google has released Gemini 3.8 Flash, the third Flash-tier update in three months, arriving just three weeks after Gemini 3.7 Flash. The model is live now in the Gemini app, Google Antigravity, and AI Studio with introductory pricing of $0.75/1M input and $3.75/1M output tokens.
Simon Willison's Pelican Benchmark Shows GPT-6 Astra Outperforming GPT-5.6 Sol at Every Reasoning Level
Developer Simon Willison ran his signature 'pelican riding a bicycle' SVG test on newly-accessed GPT-6 Astra across five reasoning levels, comparing results against GPT-5.6 Sol, Terra, and Luna. Even Astra's lowest reasoning setting reportedly beat every Sol output, though Astra costs roughly twice as much per token.
OpenAI Lists GPT-6 Astra Pro on OpenRouter: Same Model, Higher-Compute Reasoning Mode
GPT-6 Astra Pro, now listed on OpenRouter, is the existing GPT-6 Astra model configured to run with reasoning.mode set to 'pro' for higher-quality output on complex tasks. It carries a 1M-token context window and tiered pricing from $5/$25 to $20/$100 per million input/output tokens depending on the serving tier.
OpenAI's GPT-6 Astra Cuts Hallucinations, But Indirect Prompt Injection Attacks Still Succeed 8.5% of the Time
OpenAI's new GPT-6 Astra model shows major improvements in hallucination rates and jailbreak resistance over predecessor GPT-5.6 Sol, according to OpenAI's system card. However, indirect prompt injection attacks hidden in documents still succeed 8.5% of the time in external testing by Gray Swan, down from 27% but still above rival Claude Opus 5's 4.8% rate.
Comments
Loading...