Cline CLI 3.0.6 Adds Support for GPT-5.2, GPT-5.4, and GPT-5.4-mini Models
Cline released CLI version 3.0.6 with updated ChatGPT provider model list. The patch adds support for codex variants and three new GPT-5 series models: gpt-5.2, gpt-5.4, and gpt-5.4-mini.
Cline CLI 3.0.6 Adds Support for GPT-5.2, GPT-5.4, and GPT-5.4-mini Models
Cline, an AI-powered coding assistant, released CLI version 3.0.6 on May 17, 2025. The update expands the ChatGPT provider model list to include newly available GPT-5 series models.
What Changed
The patch release makes a single fix to the ChatGPT provider configuration:
- Added support for codex variants
- Added gpt-5.2 subscription model
- Added gpt-5.4 subscription model
- Added gpt-5.4-mini subscription model
The update follows CLI version 3.0.5, released earlier this month. The full changelog is available on GitHub.
Model Availability
The newly added models appear to be subscription-tier offerings from OpenAI, though OpenAI has not publicly announced GPT-5 series models. The inclusion of "codex variants" suggests enhanced code generation capabilities, consistent with Cline's focus as a coding assistant.
The gpt-5.4-mini designation follows OpenAI's naming convention of smaller, more efficient model variants seen with GPT-4-mini and GPT-3.5-turbo.
Installation
Users can update to CLI v3.0.6 through standard package managers or by downloading the release assets directly from the GitHub repository.
What This Means
Cline's rapid addition of GPT-5 model support indicates either private API access or preparation for an imminent OpenAI announcement. The specific model names—gpt-5.2, gpt-5.4, and gpt-5.4-mini—suggest multiple capability tiers, potentially matching the GPT-4, GPT-4-turbo, and GPT-4-mini structure. For developers using Cline, this update positions the tool to leverage next-generation language models as soon as they become generally available, though pricing and performance benchmarks remain unknown until official OpenAI disclosure.
Related Articles
Cline v4.1.22 Adds New AI Providers, Fixes Anthropic Failover and Bedrock Routing Bugs
Cline's v4.1.22 release adds two new model providers, refreshes default models across more than a dozen gateways including a switch to GPT-6.1 Sol, and fixes bugs in Anthropic content-filter handling, Bedrock inference profiles, and reasoning token accounting.
Google ends Pro model access for Gemini AI Plus on November 13, leaving the $4.99 tier with Flash only
Starting November 13, 2026, Google AI Plus subscribers ($4.99/month) can no longer select Pro models in the Gemini app or AI Mode in Search. The tier keeps only Gemini Flash and Flash-Lite, while Gemini 4 Argon goes to AI Pro ($19.99/month) and AI Ultra.
Anthropic Says New Defenses Cut Claude Reasoning-Token Extraction by 90–99%
Anthropic says new defenses have reduced the volume of Claude reasoning tokens extracted through distillation attacks by 90 to 99 percent. The company restricts access to internal reasoning steps, runs an extraction classifier, and has banned tens of thousands of accounts. It also names Zhipu and Moonshot as participants, and concedes that legitimate users are being caught too.
Google removes model picker for free Gemini app users, locking them to 'Auto' routing that defaults to Flash-Lite
Google has removed manual model selection for free Gemini app users, leaving 'Auto' as the only option. Most prompts will go to Flash-Lite, with harder ones routed to Flash or Pro, according to Google. New thinking levels (Low, Medium, High) are also rolling out to subscribers.
Comments
Loading...