New Frontier Models in v1.3.6: OpenAI, Anthropic, Google

We’re excited to ship v1.3.6, a release focused on bringing you the latest frontier models from all three major providers, squashing long-standing bugs in the model selector, and — perhaps most importantly — unifying how models are defined across the entire stack.

🚀 Newest Frontier Models

The AI landscape moves fast. This release adds day-one support for the newest flagship models from OpenAI, Anthropic, and Google:

OpenAI — GPT-5.4

OpenAI’s latest and most capable model lands in the plugin as GPT-5.4, alongside its Pro variant. The full OpenAI lineup now spans from the ultra-efficient GPT-5 Nano all the way up to the new frontier:

• GPT-5.4 — Newest Frontier
• GPT-5.4 Pro — Extended thinking & higher limits
• GPT-5.2 Pro / GPT-5.2 / GPT-5.1 / GPT-5
• GPT-5 Mini (Fast) / GPT-5 Nano (Lowest Cost)

Anthropic — Claude Opus 4.6 & Sonnet 4.6

Anthropic continues its rapid iteration on the Claude family. We now support the brand-new Claude Opus 4.6 as the newest frontier model, with Claude Sonnet 4.6 as our recommended default for the best balance of quality and speed:

• Claude Opus 4.6 — Newest Frontier
• Claude Sonnet 4.6 — Recommended
• Claude Haiku 4.5 — Fast
• Claude Sonnet 4.5 / Claude Opus 4.5

Google — Gemini 3.1 Pro Preview

Google’s Gemini family gets a big update with the Gemini 3.1 Pro Preview leading the pack. The lineup now includes the new Flash 3 preview and Flash-Lite 3.1 tiers for cost-conscious workloads:

• Gemini 3.1 Pro Preview — Newest Frontier
• Gemini 3 Flash Preview
• Gemini 3.1 Flash-Lite
• Gemini 2.5 Pro / Gemini 2.5 Flash / Gemini 2.5 Flash-Lite

We heard your feedback — the model selector had several annoying issues that have been resolved in this release:l.

• Fixed broken model selectors caused by a configuration issue.
• We now maintain a single models.json file that serves as the canonical registry for every supported model. Both the PHP backend and the JavaScript frontend read from this same file:

// models.json (single source of truth)
{
  "openai": [
    { "value": "gpt-5.4", "label": "GPT-5.4 (Newest Frontier)" },
    { "value": "gpt-5.4-pro", "label": "GPT-5.4 Pro" },
    ...
  ],
  "anthropic": [
    { "value": "claude-opus-4-6", "label": "Claude Opus 4.6 (Newest Frontier)" },
    { "value": "claude-sonnet-4-6", "label": "Claude Sonnet 4.6 (Recommended)" },
    ...
  ],
  "gemini": [
    { "value": "gemini-3.1-pro-preview", "label": "Gemini 3.1 Pro Preview (Newest Frontier)" },
    { "value": "gemini-3-flash-preview", "label": "Gemini 3 Flash Preview" },
    ...
  ]
}

What’s Next

We’re continuing to monitor new model releases from all three providers and aim to support them within days of launch. On the roadmap, we’re also looking at adding support for custom/self-hosted model endpoints and a “model comparison” mode that lets you test prompts against multiple models side by side.

As always, thank you for using the plugin and for all the feedback that makes it better.