Choosing chat models
Aethera lets you choose the model for each chat. The selected model controls answer style, reasoning depth, speed, and credit cost.
The model picker is in the chat composer. On a new chat it may briefly show Select model… while the catalog loads, then it falls back to your default model or Aethera’s default.
Model classes
Section titled “Model classes”Aethera groups chat models into three access classes:
Class 1
Standard models are available to Free and paid users. Daily and bonus credits can be spent on Class 1 model work after monthly credits are used.
Class 2
Advanced models are paid-plan models. They use monthly credits and are not eligible for daily or bonus credit spend.
Class 3
Premium models are the highest-cost models in the picker. Use them when quality matters more than speed or cost.
Current active model families
Section titled “Current active model families”The live model catalog includes models from Anthropic, OpenAI, Google, xAI, Qwen, Kimi, Z.ai, DeepSeek, and MiniMax. The active picker currently includes:
| Model | Class | Best for |
|---|---|---|
| Claude Sonnet 4.6 | 2 | high-quality analysis, writing, planning |
| Claude Haiku 4.5 | 1 | fast Anthropic responses |
| Gemini 3.1 Flash Lite | 1 | efficient everyday work |
| Gemini 3 Flash | 1 | default fast general work |
| GLM-5 | 1 | general reasoning and drafting |
| MiniMax M2.5 | 1 | fast low-cost general work |
| Kimi K2.5 / K2.6 | 1 | research-style reasoning and long-form tasks |
| GPT-OSS 120b | 1 | open-model work with no provider cost basis |
| DeepSeek V4 Flash / Pro | 1 | efficient coding and analysis |
| Qwen 3.6 Flash / Plus | 1 | fast general reasoning |
| GPT-5.2 | 2 | advanced OpenAI reasoning |
| Gemini 3.1 Pro | 2 | stronger Google reasoning |
| Grok 4.3 / Grok 4.20 | 2 | xAI reasoning and conversational work |
| Qwen 3.6 Max | 2 | higher-quality Qwen work |
| Claude Opus 4.6 / 4.7 | 3 | premium Anthropic depth |
| GPT-5.4 / GPT-5.5 | 3 | premium OpenAI depth |
Models marked legacy in old conversations may still appear in history, but the picker hides legacy models for new work.
Change models in chat
Section titled “Change models in chat”Open Chat
Section titled “Open Chat”Go to Chat from the sidebar.
Open the model picker
Section titled “Open the model picker”Click the model selector in the composer. It appears near the persona selector and reasoning controls.
Search or browse
Section titled “Search or browse”Use the picker to find a model by name or provider. If the picker is still loading, wait a moment and try again.
Select a model
Section titled “Select a model”Choose the model you want. The next message uses that model. Existing assistant responses do not change.
Default model
Section titled “Default model”To change the model used for new conversations:
- Open Settings → Account.
- Find Defaults.
- Choose a Default model.
- Save changes.
If the selected default model does not support reasoning, the Default thinking level field explains that reasoning is unavailable for that model.
Reasoning controls
Section titled “Reasoning controls”Some models support configurable reasoning. When a model supports it, the composer shows a reasoning control beside the model/persona controls. If the current model does not support reasoning, Aethera disables or hides reasoning choices.
Use higher reasoning when you need careful multi-step analysis, planning, debugging, or synthesis. Use lower reasoning for quick drafts and simple questions.
Cost guidance
Section titled “Cost guidance”Chat model costs are token-based:
- input tokens come from your prompt, conversation context, files, citations, and tool results
- output tokens come from the assistant’s answer and reasoning where applicable
- each active model has its own input and output credit rate
- tool calls and image actions can add separate credit costs
Troubleshooting
Section titled “Troubleshooting”The picker says Select model…
Section titled “The picker says Select model…”The model catalog is still loading. Wait a moment. If it remains empty, refresh the page.
The send button is blocked
Section titled “The send button is blocked”Aethera may still be loading the selected model, you may be out of credits, or the message may not contain any usable input. Check Settings → Usage if you suspect a credit issue.
A model from an old article is missing
Section titled “A model from an old article is missing”Models are periodically retired or moved to legacy status. Legacy models remain supported for old history and cost settlement, but they are hidden from the current picker.