# Models and accounts > Accounts, the model picker, fallback chains, model options, agent profiles and usage in the terminal app. Which providers exist, how each signs in and how fallback works: [providers](https://zidane.si/docs/providers.md). ## Settings › Authentication Settings › Authentication lists each provider and its credential source: the credentials file, OAuth or an environment variable. A provider can hold several OAuth accounts. The footer model chip names the one in use. | Key | Does | | - | - | | `Enter` | Switch to the provider | | `Enter` on `+ add / re-configure` | Open the [sign-in wizard](https://zidane.si/docs/tui.md#sign-in) | | `Tab` | Show a provider's accounts | | `Ctrl`+`E` | Rename an account | | `Ctrl`+`X` twice | Remove a credential | ## Pick a model `Ctrl`+`M` opens the model picker with every signed-in provider's models. Type to search by provider, name or capability. *Terminal: The model picker: the selected model is first in the chain.* ```text ┌ New session ─────────── ▢ ─ ~/acme-api 0 user messages 0 turns ctrl+shift+x session ┐ │ │ │ │ │ ┌─ models (tried in order) ────────────────────────────────────────────────────────┐ │ │ │ │ │ │ │ ┌────────────────────────────────────────────────────────────────────────────┐ │ │ │ │ │ search models by name, provider or capability │ │ │ │ │ └────────────────────────────────────────────────────────────────────────────┘ │ │ │ │ │ │ │ │ ▶ Opus 5.5 claude-opus-5-5 Anthropic ctx 1.00M reasoning vision 1 │ │ │ │ GPT-6.1 Sol gpt-6.1-sol OpenAI ctx 272.0k reasoning vision 2 │ │ │ │ Fable 5.1 claude-fable-5-1 Anthropic ctx 1.00M reasoning vision │ │ │ │ Haiku 4.5 claude-haiku-4-5 Anthropic ctx 200.0k reasoning vision │ │ │ │ Sonnet 5.5 claude-sonnet-5-5 Anthropic ctx 1.00M reasoning vision │ │ │ │ GPT-4 Turbo gpt-4-turbo OpenAI ctx 128.0k vision │ │ │ │ GPT-4o gpt-4o OpenAI ctx 128.0k vision │ │ │ │ GPT-4o mini gpt-4o-mini OpenAI ctx 128.0k vision │ │ │ │ GPT-5.3 Chat gpt-5.3-chat-latest OpenAI ctx 128.0k vision │ │ │ │ GPT-5.3 Codex gpt-5.3-codex OpenAI ctx 400.0k reasoning vision │ │ │ │ GPT-5.3 Codex Spark gpt-5.3-code OpenAI ctx 128.0k reasoning vision │ │ │ │ GPT-5.4 mini gpt-5.4-mini OpenAI ctx 400.0k reasoning vision │ │ │ │ GPT-5.4 nano gpt-5.4-nano OpenAI ctx 400.0k reasoning vision │ │ │ │ GPT-5.5 gpt-5.5 OpenAI ctx 272.0k reasoning vision │ │ │ │ │ │ └──│ ↑↓ navigate ↵ use as primary ⇥ add/remove fallback ctrl+shift+↑↓ reorder │──┘ ┌──│ esc apply ctrl+o 36 older 2 selected 24 of 60 models │s ┐ │ A│ │ │ └──└──────────────────────────────────────────────────────────────────────────────────┘──┘ shift+tab Build ctrl+m/l Opus 5.5 +1 medium ctrl+shift+x session ctrl+o settings ctx 0 / 1.00M (0%) ``` | Key | Does | | - | - | | `Enter` | Use the highlighted model as the primary | | `Tab` | Add or remove it as a fallback | | `Ctrl`+`Shift`+`↑` `↓` | Move it up or down the chain | | `Ctrl`+`O` | Show or hide older models (on an empty search) | | `Esc` | Apply the chain and close (or close, when nothing changed) | An id the catalog does not list shows a "use anyway" row. The hint row counts selected and matching models. ## Build a fallback chain The picker lists the chain in order, and zidane tries the first model first. Add fallbacks with `Tab` and order them with `Ctrl`+`Shift`+`↑` `↓`. A chain takes one account per provider, and forks keep it. A fallback serving a run shows in the footer in the warning color. When a run moves on and back: [model fallback](https://zidane.si/docs/providers.md#model-fallback). ## Set model options `Ctrl`+`L` opens the current model's options, when it has any: its reasoning effort levels, then toggles such as fast mode. `↑` `↓` move, `Enter` or `Space` picks. *Terminal: Model options: reasoning effort, with medium selected.* ```text ┌ New session ─────────── ▢ ─ ~/acme-api 0 user messages 0 turns ctrl+shift+x session ┐ │ │ │ │ │ │ │ │ │ │ │ │ │ │ │ ┌─ model options ──────────────────────────────────────────────┐ │ │ │ │ │ │ │ reasoning effort │ │ │ │ off │ │ │ │ minimal │ │ │ │ low │ │ │ │ ▶ medium ✓ │ │ │ │ high │ │ │ │ xhigh │ │ │ │ max │ │ │ │ adaptive │ │ │ │ │ │ │ │ ↑↓ navigate ↵ select esc close │ │ │ │ │ │ │ └──────────────────────────────────────────────────────────────┘ │ │ │ └────────────────────────────────────────────────────────────────────────────────────────┘ ┌──────────────────────── ↵ send shift+↵ newline ↑↓ history ? search ctrl+s messages ┐ │ Ask zidane… │ └────────────────────────────────────────────────────────────────────────────────────────┘ shift+tab Build ctrl+m/l Opus 5.5 +1 medium ctrl+shift+x session ctrl+o settings ctx 0 / 1.00M (0%) ``` The footer shows the effort and options next to the model: `ctrl+m/l Opus 4.6 medium`. Effort levels: [thinking](https://zidane.si/docs/agents.md#thinking). ## Switch the agent profile `Shift`+`Tab` cycles profiles when you have more than one. The footer shows the current one in its color. | Profile | Tools | | - | - | | Build (default) | All | | Plan | Read-only | | Codemode | Build, with tool calls written as one short script. Needs Settings › Agent › Codemode. | Build and Plan share one agent, so a switch between them keeps the prompt cache: a gate refuses the tools Plan lacks, and a note tells the model about the switch. Plan on a Codemode session works the same way. Other switches rebuild the agent, and the provider reads the conversation again ([profiles](https://zidane.si/docs/extensions.md#agent-profiles)). The model, effort and agent pickers mark an option that would re-read a long conversation, for example `re-reads ~452k tokens`. A switch that keeps the cache shows nothing. Markdown agents in `.agents/agents/` or `.zidane/agents/` are [sub-agents](https://zidane.si/docs/sub-agents.md) the main agent starts, not part of this cycle. ## Usage `Ctrl`+`P` opens the usage panel: rate-limit windows and credits for each OAuth subscription, then GitHub API limits. `Ctrl`+`R` refreshes, `Esc` closes. Settings › Agent › Check usage stops the fetches. Settings › UI › Usage indicator hides the chip. The windows: [plan usage](https://zidane.si/docs/providers.md#plan-usage). Model settings and defaults: [Settings](https://zidane.si/docs/tui-settings.md#models). One-off runs take `--provider`, `--model` and `--thinking`: [`zidane run`](https://zidane.si/docs/cli.md#zidane-run).