AI Providers

Foxl supports multiple AI providers, and connecting one is the setup step that matters: Foxl is free and the model access is yours to supply.

Pick one of three

The Foxl relay

The relay at relay.foxl.ai still does auth, cross-device sync, the desktop tunnel, Channels, push and shared folders. What it does not do right now is serve models, so there is no relay model to fall back on and no Foxl credits to spend on one.

OAuth Providers (Subscription Login)

Use your existing Claude, Gemini, or ChatGPT subscriptions directly in Foxl - no API key needed. Foxl reads OAuth credentials created by each vendor's login flow.

Gemini CLI (Google AI)

Use your Google AI subscription or API key.

1. Install: npm install -g @google/gemini-cli
2. Authenticate: gemini auth login or set GEMINI_API_KEY
3. Select Gemini CLI in Settings > Model & provider

Models: Gemini 3.1 Pro, Gemini 3 Pro, Gemini 3.5 Flash and Gemini 3.1 Flash Lite, as the CLI serves them, plus Gemini 2.5 Pro and Gemini 2.5 Flash behind Show older model versions - the 2.5 pair is still the CLI's own built-in default but is two generations back. Credentials from ~/.gemini/settings.json or environment variable.

Foxl exposes the concrete model ids rather than the CLI's auto-gemini-* routing sentinels: Foxl records which model ran so a turn's cost is attributable, and a sentinel would make that impossible.

Claude Code (Anthropic Pro/Max)

Use your Claude Pro or Claude Max subscription. Foxl calls api.anthropic.com directly with your Claude Code OAuth token - no CLI subprocess.

1. Run the official login once inside Claude Code: claude /login (or claude setup-token)
2. Select Claude Code (OAuth) in Settings > Model & provider, then pick a model from the selector

Models: Opus 5 (claude-code/claude-opus-5), Fable 5.1, Fable 5, Opus 4.8, Opus 4.7 (1M context each), plus Sonnet 5 and Sonnet 4.6 (200K on the subscription pool). Fable 5.1 is the one exception to the sentence below: it is not in the subscription pool, and a Pro token without Extra-usage credits gets 429 "Usage credits are required for this model." - see Models. They run in compatibility mode so requests route through your Claude Pro/Max subscription instead of pay-as-you-go "Extra usage". The legacy claude-code/opus and claude-code/sonnet aliases now map to Opus 5 and Sonnet 5. Tokens auto-refresh in the background.

OpenAI (ChatGPT Plus/Pro)

Use your ChatGPT Plus or Pro subscription - Foxl calls OpenAI's Codex Responses API directly with your OAuth token. No local CLI subprocess or proxy server needed.

1. Run the official login once: npx @openai/codex login (creates ~/.codex/auth.json)
2. Select OpenAI (OAuth) in Settings > Model & provider

Models: GPT-6 Astra, GPT-5.6 Sol / Terra / Luna, GPT-5.5, plus GPT-5.4 Mini behind Show older model versions. GPT-5.4 is not on this transport - OpenAI stopped serving it to ChatGPT accounts (measured: 400 "The 'gpt-5.4' model is not supported when using Codex with a ChatGPT account.") and it was removed from the picker in v0.7.5; reach it through Amazon Bedrock instead. Every one of them is 272K context (278,528) on this transport - that is the Codex CLI's own figure for each slug it serves, not the 1M window Bedrock offers the GPT-5.6 generation. The live catalog is fetched from Codex per account, so your actual selection may differ slightly based on what ChatGPT rolls out to your tier. Tokens auto-refresh in the background via the OAuth refresh flow.

GPT-6 Astra (launched September 4, 2026) always reasons - it accepts low through max and refuses a none level, so with thinking switched off Foxl sends low. It has no Amazon Bedrock model id yet, so a ChatGPT subscription or an OpenAI API key is the only way to reach it. See Models.

Image generation is available through the generate_image tool (powered by gpt-image-2), which uses the same OAuth credentials. See Agent Tools - Media for details.

Bring Your Own Key (BYOK)

Add your own API keys on the desktop and Foxl calls the provider directly from your machine. The web app and the phone use the same key through your desktop over the relay.

Anthropic

Direct access to Claude models via the Anthropic API.

1. Go to Settings > Model & provider
2. Select Anthropic
3. Enter your API key from console.anthropic.com
4. Select a model (Claude Opus 5, Fable 5, Opus 4.8, Sonnet 5, Haiku 4.5; Opus 4.7, Opus 4.6 and Sonnet 4.6 appear once Show older model versions is on). Foxl lists Fable 5.1 under Amazon Bedrock only, below.

Prompt caching is on for this path since v0.6.25, so the unchanging front of each request (the system prompt and the tool definitions) is billed at the cache-read rate rather than sent again at full price every turn.

OpenAI

Access the OpenAI API catalog - GPT-5.6 Sol, Terra and Luna, and GPT-5.5. GPT-5.4, GPT-4.1, GPT-4.1 Mini, o3, o4-mini and GPT-4o are the older generation and appear once Show older model versions is on.

1. Go to Settings > Model & provider
2. Select OpenAI
3. Enter your API key from platform.openai.com
4. Select a model

Google (Gemini)

Access Gemini models via Google AI.

1. Go to Settings > Model & provider
2. Select Google AI
3. Enter your API key from aistudio.google.com
4. Select a Gemini model

Ollama (Local Models)

Run AI models entirely on your machine with zero cost and full privacy.

1. Install Ollama from ollama.com
2. Pull a model: ollama pull llama3 or ollama pull mistral
3. In Foxl Settings > Model & provider, select Ollama
4. Foxl auto-detects running Ollama models

Amazon Bedrock

For users with their own AWS account and Bedrock access.

1. Configure AWS credentials (~/.aws/credentials or environment variables)
2. In Settings > Model & provider, select Amazon Bedrock
3. Ensure the models you want are enabled in your Amazon Bedrock console

One provider covers everything your AWS account can serve: Claude, GLM 5 and Kimi K2.5 alongside GPT-5.x, Grok 4.6 and Gemma 4 31B. Bedrock serves those two sets over different APIs internally, but they are the same account and the same credential, so they are one entry in the provider list and one model dropdown.

Claude Fable 5.1 is on this list as of v0.6.27. It is the same class as Fable 5 at the same price per token, with cache reads at a quarter of Fable 5's - most of the bill on long agent runs - and Foxl offers it through Amazon Bedrock only, so it needs your AWS account rather than an Anthropic key.

OpenAI-compatible vendors

Nineteen more providers speak the OpenAI API shape and are listed as their own entries: OpenRouter, DeepSeek, Groq, Together AI, Mistral AI, Fireworks AI, Z.ai (GLM), Kimi (Moonshot AI), Qwen (Alibaba), MiniMax, Perplexity, xAI (Grok), Cerebras, SambaNova, Cohere, AI21 Labs, Hugging Face, and a local vLLM or LM Studio server. Pick one under Settings > Model & provider, paste its key (a local server needs none), and the model picker fills with the vendor's own live catalogue - Foxl asks each configured vendor for its list and keeps its hand-picked favourites at the front, so an OpenRouter key sees all of OpenRouter rather than six models. Z.ai, Kimi and Qwen also offer a regional endpoint (China mainland, the GLM Coding Plan, US) in the same pane.

Provider options. Each vendor's card carries the controls it supports, and they apply to every request Foxl sends it - chat, scheduled runs and Notes:

• Maximum reply length (tokens) - some providers (OpenRouter among them) reserve this whole amount against your balance before answering and refuse when it cannot cover it. Lower it if you see "requires more credits, or fewer max_tokens"; raise it for long reports.
• Endpoint - a regional host, or a local server on another port.
• Only free models - offer just the models the vendor serves at no charge, everywhere a model is picked.
• Prefer (the cheapest, the fastest, the quickest to start), with Allow fallbacks, Require full parameter support and Refuse providers that train on your data - for resellers that route one model through several upstreams. Sorting only re-orders; the three switches remove options, and if none is left the vendor answers "No endpoints found", which looks like the model vanished.
• Account > Check - asks the vendor what this key has spent and what remains, so a refusal for lack of credit is visible before it happens.

Provider Health Check

The Settings > Model & provider pane shows, for the selected provider, whether a key is saved (or that it is auto-configured, as Ollama and the subscription logins are) and a Connected badge once Foxl has reached it. A provider that cannot be reached reports the error it returned.

Model Switching

You can switch between models and providers at any time using the model selector in the chat input area. Your selection persists across conversations.

Superseded models are hidden from every picker until you turn on Show older model versions in Settings > Model & provider. The ones it hides today: Opus 4.7, Opus 4.6, Sonnet 4.6 (on Bedrock, an Anthropic key and the Claude Code subscription alike), GPT-5.4 and GPT-5.4 Mini, GPT-4.1, GPT-4.1 Mini, o3, o4-mini, GPT-4o, and the Gemini CLI's Gemini 2.5 Pro / Gemini 2.5 Flash. Hiding is presentation only - a hidden model keeps its pricing and its tier eligibility, and a saved selection, a scheduled task or an API caller pinned to one keeps working.

Gemini 2.0 Flash is not on that list because it is gone, not hidden: Google no longer publishes a price for any 2.0 model, and a model with no price is metered at $0.00, so it was removed in September 2026. A saved selection of it still resolves and still bills nothing; pick a 2.5 model instead.

Automatic fallback

Settings > Model & provider > Automatic fallback lists up to three models to try, in order, when the one you picked refuses a request it cannot retry - a rate limit, an overload, an outage. It engages only after the normal retries are exhausted, so a healthy primary is always used first, and the list is drawn from every provider you have set up, because when a vendor is down its other models are down too. Off unless you turn it on, since falling back changes which vendor sees the conversation and what the turn costs. It applies to background runs as well - a 3am schedule or a Slack mention no longer dies at a rate limit.

Cost Comparison

The Foxl relay is deliberately absent from that table: it does not serve models right now. See Cost & model access.