Skip to main content
idapt
HomeCodeAI ModelsPricing
Sign inStart free trial
Blog

New Models in idapt: July 2026

ITidapt Team·July 16, 2026

The first issue of a monthly series tracking what joined the catalog. As of mid-July 2026, idapt serves 250+ models from 25 providers; here is what is new and what to do with it.

OpenAI: the GPT-5.6 family

GPT-5.6 Sol is the new flagship generalist, with GPT-5.6 Luna as the fast creative line and GPT-5.6 Terra rounding out the family. Sol slots straight into the frontier tier for hard mixed work; Luna is the interesting one for writers, with a distinct idea-dense drafting style.

xAI: Grok 4.5

Grok 4.5 is xAI's new flagship, and it arrived alongside the build-focused Grok Build line. If your last Grok impression is a version old, it is worth re-running your own prompts against it in a parallel tab.

Also this month

Local-only models got first-class handling end to end (directory, API, routing), so the models your machine serves via Ollama sit properly beside the cloud catalog: see local inference.

How to evaluate a new model in five minutes

  1. Open a chat you already had with your current default.
  2. Re-ask its hardest question with the new model in a parallel tab.
  3. Compare, then check price and context on the model's page.

The rankings track the benchmark picture as scores land, and the best-of roundups re-verify their picks on review dates, so a new arrival that earns a spot shows up there next sweep.

Next issue in August. The models directory is always the live source of truth.

AnnouncementModelsRelease

Found this helpful? Share it:

  • OpenAI: the GPT-5.6 family
  • xAI: Grok 4.5
  • Also this month
  • How to evaluate a new model in five minutes

Continue reading

  • What Shipped in idapt: July 2026

    The July changelog: Skills GA, Tasks boards and My Tasks, faster chat, redesigned cloud computer lifecycle, new comparison surfaces, and more.

  • Introducing idapt Code

    idapt Code turns a normal idapt chat into a coding session on your own machine or an idapt cloud computer, with the model and the tools you already use.

  • How We Rank 250+ Models

    The methodology behind idapt's rankings: named public benchmarks, a rescaled capability index, live telemetry, and the rule against invented composites.

  • Real Receipts: How Model Outputs Are Captured

    Why idapt's model showcases are captured from real production runs with cost and latency attached, and why staged demos are banned from proof surfaces.

Explore idapt

  • Best of: the picks by job

    Data-backed model picks for coding, writing, research, and media.

  • One chat. Every model.

    GPT, Claude, Gemini, Grok, Llama: pick mid-conversation, cheapest-first.

  • Home
  • Pricing
  • AI Models
  • Image models
  • Voice models
  • Video models
  • Rankings
  • New models
  • Model status
  • Multi-Model Chat
  • Agents
  • Computers
  • Drive
  • Automations
  • AI Gateway
  • All features →
  • LLM cost calculator
  • Token counter
  • All free tools →
  • Blog
  • Use cases
  • Comparisons
  • Best of
  • Benchmarks
  • Demos
  • Changelog
  • Help center
  • FAQ
  • Privacy
  • Compare all models
  • Support
  • idapt Code
  • Developers
  • Quickstarts
  • API reference
  • API pricing
  • CLI
  • MCP
  • Downloads
  • Desktop
  • Badges and embeds
© idapt[email protected]TermsPrivacy PolicyLegal noticeReport content
X (Twitter)