Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.whim.run/llms.txt

Use this file to discover all available pages before exploring further.

​
Providers at a glance

CCR + OpenRouter is not yet available during the alpha period. Claude and Codex are the two supported providers.
Whim runs providers natively inside task containers. During alpha, Claude and Codex are available today. CCR + OpenRouter is wired up in the product and listed below as upcoming.
Claude Subscription (Recommended)Codex SubscriptionCCR + OpenRouter (Coming Soon)
RuntimeNative Claude CLINative Codex CLICloud Code Runtime (CCR)
AuthYour Anthropic subscriptionYour ChatGPT accountManaged by Whim
Recommended modelClaude Opus 4.6 (1M)GPT 5.5Claude Sonnet 4.5
Available modelsClaude familyGPT 5.x family20+ (Claude, GPT, Gemini, Grok, DeepSeek, more)
Setup requiredOAuth tokenChatGPT loginNone when launched
CU costContainer time onlyContainer time onlyContainer time + API tokens
Fast modeYes (all Claude models)Yes (native GPT models)No
Reasoning effortYes (Low/Medium/High/Max)Yes (Low/Medium/High/xhigh)No

​
CCR + OpenRouter

Coming soon. CCR + OpenRouter is currently disabled during alpha, so it is not selectable for workspaces or tasks.
CCR routes models through OpenRouter, a multi-model API gateway. It will offer the widest model range with zero configuration once it launches. Best for: trying different model vendors, using non-Claude/non-GPT models, getting started without managing provider auth. How it works: Whim manages the OpenRouter connection. API token costs are tracked as CU alongside container runtime. When CCR launches, you’ll be able to pick any supported model when creating a task or set a workspace default.

​
Claude Subscription

Use your Anthropic subscription to run the native Claude Code CLI. Token costs go through your subscription and Whim only charges CU for container time. Best for: the primary Whim experience during alpha, native Claude Code behavior, and maximum capability with Opus 4.6.

​
Codex Subscription

Use your ChatGPT account to run the native Codex CLI. Token costs go through your OpenAI subscription and Whim only charges CU for container time. Best for: existing OpenAI subscribers, GPT 5.5, and Codex-tuned GPT models.

​
Choosing a provider

Claude Subscription or Codex Subscription - you only pay CU for container runtime. Token costs go through your existing subscription.
Codex Subscription - native GPT 5.x support, including GPT 5.5 and Codex-tuned GPT models.
CCR + OpenRouter - coming soon. This is where Google, xAI, DeepSeek, MiniMax, Qwen, and Moonshot models will land.

​
Available models

​
Claude (Anthropic)

Available now via Claude Subscription. Selected Claude models also gain CCR support when CCR + OpenRouter launches.
ModelModel IDAvailabilityStrengthsBest for
Claude Opus 4.6claude-opus-4.6Claude now; CCR laterHighest capability, deep reasoningComplex architecture, difficult bugs, nuanced refactors
Claude Opus 4.6 (1M)claude-opus-4.6-1mClaude onlyExtended 1M token contextComplex architecture with large codebases
Claude Sonnet 4.5claude-sonnet-4.5Claude now; CCR laterStrong balance of speed and qualityGeneral-purpose coding, most tasks
Claude Sonnet 4.5 (1M)claude-sonnet-4.5-1mClaude now; CCR laterExtended 1M token contextLarge codebases, cross-file analysis
Claude Haiku 4.5claude-haiku-4.5Claude now; CCR laterFastest Claude modelQuick edits, simple tasks, rapid iteration
Claude Opus 4.6 (1M) is available only through Claude Subscription. It is not exposed through OpenRouter.

​
GPT (OpenAI)

Codex-supported GPT models are available now. OpenRouter-only GPT models will become available when CCR + OpenRouter launches.
ModelModel IDAvailabilityBest for
GPT 5.5gpt-5.5Codex nowLatest GPT tasks via native CLI
GPT 5.4gpt-5.4Codex nowPrevious flagship GPT via Codex
GPT 5.3gpt-5.3OpenRouter when CCR launchesGeneral-purpose GPT coding
GPT 5.3 Codexgpt-5.3-codexCodex now; OpenRouter laterCode-optimized GPT 5.3
GPT 5.3 Codex Spark (Preview)gpt-5.3-codex-sparkCodex now; OpenRouter laterFast, lightweight code tasks
GPT 5.2gpt-5.2OpenRouter when CCR launchesBudget-friendly GPT
GPT 5.2 Codexgpt-5.2-codexCodex now; OpenRouter laterBudget-friendly code-optimized GPT
GPT 5.1 Codex Minigpt-5.1-codex-miniCodex now; OpenRouter laterFastest and cheapest GPT option
GPT OSS 120Bgpt-oss-120bOpenRouter when CCR launchesOpen-source GPT variant

​
Google

Google models are wired up for CCR + OpenRouter and will become selectable when CCR launches.
ModelModel IDAvailabilityStrengthsBest for
Gemini 3 Progemini-3-pro-previewOpenRouter when CCR launchesComplex reasoning, large contextLarge-context analysis and difficult reasoning
Gemini 3 Flashgemini-3-flash-previewOpenRouter when CCR launchesFast, cost-effectiveQuick tasks, rapid iteration
Gemini 2.5 Flashgemini-2.5-flashOpenRouter when CCR launchesFast, cost-effectiveQuick edits, low-latency tasks

​
xAI

xAI models become available when CCR + OpenRouter launches.
ModelModel IDAvailabilityBest for
Grok Code Fastgrok-code-fast-1OpenRouter when CCR launchesRapid code generation

​
DeepSeek

DeepSeek models become available when CCR + OpenRouter launches.
ModelModel IDAvailabilityBest for
DeepSeek V3.2deepseek-v3.2OpenRouter when CCR launchesCost-effective coding

​
MiniMax

MiniMax models become available when CCR + OpenRouter launches.
ModelModel IDAvailabilityBest for
MiniMax M2.5minimax-m2.5OpenRouter when CCR launchesGeneral coding tasks

​
Qwen

Qwen models become available when CCR + OpenRouter launches.
ModelModel IDAvailabilityBest for
Qwen3 Coder Nextqwen3-coder-nextOpenRouter when CCR launchesCode-focused tasks

​
Moonshot

Moonshot models become available when CCR + OpenRouter launches.
ModelModel IDAvailabilityBest for
Kimi K2.5kimi-k2.5OpenRouter when CCR launchesGeneral coding tasks

​
Setting your default model

Defaults determine which model runs when you create new tasks:
  • Workspace default - applies to all members. Set by admins in Settings > Workspace > Defaults.
  • User default - overrides workspace default. Set in Settings > My Defaults.
Each supported provider stores its own default model. When you switch between supported providers, the model switches to that provider’s saved default unless you’ve set a specific override.
CCR + OpenRouter will use the same default-model flow when it launches, but it is not currently selectable during alpha.

​
Per-task override

Override the default model when creating any task by selecting a different model in the composer toolbar. The override only affects that task.
Use per-task overrides for a more capable model on complex work, or a lighter model for simple tasks.

​
CU cost by provider

During alpha, the supported providers are Claude Subscription and Codex Subscription, so CU covers container runtime only (1 CU per 30 minutes). Token costs go through your subscription.
CCR + OpenRouter is coming soon. When it launches, CU will have two components: container runtime and API tokens, with token cost varying by model.

​
Model selection tips

Claude Opus 4.6 (1M) and GPT 5.5 are the current defaults. Switch if you need more speed, lower cost, or a smaller context window.
Claude Opus 4.6, Claude Opus 4.6 (1M), and GPT 5.5 for deep reasoning - complex debugging, large refactors, architectural decisions.
Claude Haiku 4.5 and GPT 5.1 Codex Mini for simple edits, boilerplate, and quick fixes. Gemini 3 Flash and Gemini 2.5 Flash join this lane when CCR launches.
Claude Opus 4.6 (1M) or Claude Sonnet 4.5 (1M) when the agent needs to reason across many files simultaneously.