Skip to Content
ChatChoosing the right model

Choosing the right AI model

Anuma gives you access to a wide range of leading AI models  across every major provider — all through a single interface with one unified memory. Different models excel at different tasks, so choosing the right one can make a big difference.

The exact lineup changes often as new models ship and older ones are retired. The model picker in the app is always the source of truth for what’s available right now — the lists below are a current snapshot.

Snapshot last updated: July 2026.

Available models

Closed source models

These run on the model provider’s own infrastructure. Learn more about closed source models .

ProviderModels
OpenAIChatGPT 5.6 (Sol, Terra, Luna), ChatGPT 5.5
AnthropicClaude Fable 5, Claude Opus 4.8, Claude Sonnet 5
GoogleGemini 3.1 Pro, Gemini 3.5 Flash
xAIGrok 4.5, Grok 4.3, Grok 4.1 Reasoning, Grok 4.1 Non-Reasoning

Open source & private models

Open‑weight models that run on Anuma’s private infrastructure, so you can go fully private any time. Learn more about open source models .

ProviderModels
QwenQwen 3.7 Plus, Qwen 3.6 Plus, Qwen 3 235B
KimiKimi 2.6, Kimi K2.7 Code
MiniMaxMiniMax 2.7, MiniMax M3, MiniMax M2.5, MiniMax M2.1
GLM / ZhipuGLM 5.2
InclusionAILing 2.6 Flash

Image models

ProviderModels
Nano BananaNano Banana 2, Nano Banana Pro, Nano Banana Flash
FluxFlux 2 Dev, Flux 1 Schnell
OpenAIGPT Image 2
xAIGrok Imagine

Control which families appear

The model picker respects your Model privacy setting in Settings → Models — pick Open source only (max privacy), Closed-source only (max performance), or All models. See Open Source vs Closed Source Models for the full breakdown.

Anuma Settings → Models showing the Model privacy options: Open source only (Max privacy), Closed-source only (Max performance), and All models

How to select a model

Step 1: Open the model selector

Tap the model name at the top of any chat to open the model picker. On the web it opens as a dropdown; on mobile it opens as a full-height sheet.

Model privacy options in the web app

Step 2: Browse by provider

Models are grouped by provider. Scroll through or use search to find a specific model.

Step 3: Select your model

Most models are available on every plan. Most premium models unlock with Starter; a small set of flagship models (currently Claude Fable 5) is Pro-only. Tap a model to select it for your conversation.

Which model should I use?

  • General chat and Q&AAuto Model or ChatGPT 5.6
  • Long documents and analysis — Claude Opus 4.8
  • Coding and debugging — ChatGPT 5.5 or Claude Sonnet 5
  • Creative writing — Claude or Gemini
  • Maximum privacy — Qwen, Kimi, GLM, MiniMax, or Ling 2.6 Flash
  • Fast responses — Gemini 3.5 Flash, Grok 4.5, or a Flash/Lite model

Good to know

  • All models share your unified Anuma memory. Switch between models without losing context.
  • Different models cost different amounts of credits per message. Premium models cost more.
  • Use Auto Model to let Anuma choose the best model automatically.
  • You can mix models in Council Mode to compare responses side by side.
  • The model list is continuously updated as new models become available — see What’s new for recent additions.

Related articles

Last updated on