Foxl Docs

Models

AI models available in Foxl

Foxl supports models from multiple providers. Use Foxl relay credits, your own API keys (BYOK), or your Claude Pro/Max subscription (SSO).

Foxl Relay Models

Included with your Foxl plan. No setup needed — just sign in and chat.

ModelProviderContextBest For
Claude Opus 4.6Bedrock200K tokensComplex reasoning, coding, analysis
Claude Opus 4.6 (1M)Bedrock1M tokensVery long documents, large codebases
Claude Sonnet 4.6Bedrock200K tokensBalanced speed and quality
Claude Sonnet 4.6 (1M)Bedrock1M tokensLong context with good speed
Claude Haiku 4.5Bedrock200K tokensFast responses, simple tasks
GLM 5Bedrock (Z.AI)200K tokensAgentic coding, long-horizon tasks

CLI Provider Models

Use your existing subscriptions. Desktop only — see Providers for setup.

Claude Code (Claude Pro/Max)

ModelContextBest For
Opus 4.6 (SSO)200K tokensComplex reasoning, same as relay Opus
Sonnet 4.6 (SSO)200K tokensBalanced speed and quality
Haiku 4.5 (SSO)200K tokensFast responses, simple tasks

Gemini CLI (Google)

ModelContextBest For
Gemini 2.5 Pro1M tokensLong documents, deep analysis
Gemini 2.5 Flash1M tokensFast, cost-effective

Codex CLI (OpenAI)

ModelContextBest For
o3200K tokensAdvanced reasoning
o4 Mini200K tokensFast reasoning, cost-effective
GPT 4.11M tokensGeneral purpose, long context

BYOK Models

Bring your own API key to access models from any provider. See AI Providers for setup.

ModelProviderContextAPI Key From
Claude Opus 4.6Anthropic200K tokensconsole.anthropic.com
Claude Sonnet 4.6Anthropic200K tokensconsole.anthropic.com
Claude Haiku 4.5Anthropic200K tokensconsole.anthropic.com
GPT-4.1OpenAI1M tokensplatform.openai.com
GPT-4.1 MiniOpenAI1M tokensplatform.openai.com
o3OpenAI200K tokensplatform.openai.com
Gemini 2.5 ProGoogle1M tokensaistudio.google.com
Gemini 2.5 FlashGoogle1M tokensaistudio.google.com
Llama 3, Mistral, etc.OllamaVariesFree — ollama.com

Adaptive Thinking

Claude Opus 4.6 and Sonnet 4.6 support adaptive thinking — Claude dynamically decides when and how much to think based on the complexity of your request. No manual budget setting needed.

  • Simple questions: Claude responds directly without thinking overhead
  • Complex problems: Claude automatically engages deep reasoning
  • Agentic workflows: Claude can think between tool calls (interleaved thinking)

Adaptive thinking (type: "adaptive") is the recommended mode for Opus 4.6 and Sonnet 4.6. Haiku 4.5 uses type: "enabled" with a budget_tokens parameter instead.

Haiku 4.5 also supports extended thinking with type: "enabled" and budget_tokens.

You can toggle thinking on/off in the model selector.

Thinking and Cost

Thinking consumes output tokens. When thinking is enabled, the model may use 2-10x more output tokens depending on task complexity. This directly increases credit cost:

  • Simple question without thinking: ~0.01 credits (Sonnet)
  • Same question with thinking: ~0.05-0.15 credits (Sonnet)
  • Complex reasoning with thinking: ~0.30-1.0 credits (Opus)

For cost-sensitive usage, disable thinking for simple tasks. For complex coding, analysis, or multi-step reasoning, thinking significantly improves quality and is worth the extra cost. See Credits for detailed per-token pricing.

Model Selection

Desktop App

Click the model name in the chat input area to switch models. Your selection persists across conversations.

Web App

Click the model selector dropdown to choose a different model. The selection is saved in your browser.

Bring Your Own Key (Desktop Only)

In the desktop app, you can use your own API keys instead of Foxl credits:

  1. Go to Settings
  2. Select a provider (Anthropic, OpenAI, Google, etc.)
  3. Enter your API key
  4. Select a model from that provider

When using your own keys, no Foxl credits are consumed.

Claude Code SSO

You can also use your Claude Pro/Max subscription directly — no API key needed.

  1. Install Claude Code: npm install -g @anthropic-ai/claude-code
  2. Run claude auth login to authenticate
  3. Select Claude Code (SSO) in Settings > Providers

Foxl auto-detects your credentials. See AI Providers for details on all supported providers.

On this page