Skip to main content
October 8, 2026 DinoAI’s model lineup now covers eight providers. Every model is in the model picker for the copilot and agent sessions, and each bills at its own DinoAI credit rate.
  • New models:
    • Anthropic: Sonnet 5.5 and Opus 5.5.
    • OpenAI: GPT-6.1 Sol and GPT-6 Luna, OpenAI’s fastest model in the picker.
    • Google: Gemini 3.8 Flash.
    • xAI: Grok 4.7 (Preview).
    • Moonshot AI: Kimi K3.
    • Qwen: Qwen3.8 Max.
    • DeepSeek: DeepSeek V4.1 Flash (Max effort).
    • Meta: Muse Spark 1.3 (xHigh effort).
  • New default: new copilot sessions start on GPT-5.6 Sol when you haven’t picked a model.
  • Retired: Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 3.6 Flash, and Gemini 3.7 Flash move to Gemini 3.8 Flash, and Grok 4.6 moves to Grok 4.7.
Agents get eight new model families: Balanced (Claude 5.5), Deep (Opus 5.5), OpenAI (GPT-6), OpenAI Deep (GPT-6), DeepSeek, Kimi, Muse Spark, and Qwen. Fast now runs on Gemini 3.8 Flash and Grok on Grok 4.7. Pick a family in the agent builder’s Model section, set model_family in the agent’s YAML, or pass modelFamily when you trigger a run. See Supported models. Shipped in Paradime v6.18.0.