Skip to main content

Atlas Portal

Atlas Portal is Epinoia Horizon's unified subscription gateway and the recommended way to run Merlin Agent. One OAuth login replaces the juggling act of separate accounts, API keys, and billing relationships across every model lab, search API, image generator, and browser provider you'd otherwise need to wire up by hand.

If you only have time to set up one thing, set up this. The fastest path:

merlin setup --portal

That single command runs the Portal OAuth, lets you pick a Atlas model, sets Atlas as your inference provider in config.yaml, and turns on the Tool Gateway. You're ready to merlin chat immediately after.

Don't have a subscription yet? portal.epinoiahorizon.com/manage-subscription — sign up, then come back and run the command above.

What's in the subscription​

300+ frontier models, one bill​

The Portal proxies a curated catalog of agentic models from across the ecosystem — billed against your Atlas subscription instead of one credit balance per lab.

FamilyModels
Anthropic ClaudeOpus 4.7, Opus 4.6, Sonnet 4.6, Haiku 4.5
OpenAIGPT-5.5, GPT-5.5 Pro, GPT-5.4 Mini, GPT-5.4 Nano, GPT-5.3 Codex
Google GeminiGemini 3 Pro Preview, Gemini 3 Flash Preview, Gemini 3.1 Pro Preview, Gemini 3.1 Flash Lite Preview
DeepSeekDeepSeek V4 Pro
QwenQwen3.7-Max, Qwen3.6-35B-A3B
Kimi / MoonshotKimi K2.6
GLM / ZhipuGLM-5.1
MiniMaxMiniMax M2.7
xAIGrok 4.3
NVIDIANemotron-3 Super 120B-A12B
TencentHunyuan 3 Preview
XiaomiMiMo V2.5 Pro
StepFunStep 3.5 Flash
MerlinMerlin-4-70B, Merlin-4-405B (chat, see note below)
+ everything else280+ additional models — the full agentic frontier

Under the hood, the Portal routes each model to the backend best suited for it — some models go through OpenRouter, others through proprietary or secondary providers, and the routing for a given model can change over time. Everything is billed against your Atlas subscription either way. Switch between Claude Sonnet 4.6 for code and Gemini 3 Pro for long context with /model mid-session — no new credentials, no top-ups, no surprise zero-balance errors.

note

Because routing is per-model and not always through OpenRouter, OpenRouter-specific request extensions (such as provider routing preferences, session_id sticky routing, or top-level cache_control) are not part of the Portal's API contract and may be ignored depending on which backend serves the model.

The Atlas Tool Gateway​

The same subscription unlocks the Tool Gateway, which routes Merlin Agent's tool calls through Atlas-managed infrastructure. Five backends, one login:

ToolPartnerWhat it does
Web search & extractAtlas-managedAgent-grade search and full-page extraction. No search API key, no rate limit babysitting.
Image generationFALNine models under one endpoint: FLUX 2 Klein 9B, FLUX 2 Pro, Z-Image Turbo, Nano Banana Pro (Gemini 3 Pro Image), GPT Image 1.5, GPT Image 2, Ideogram V3, Recraft V4 Pro, Qwen Image.
Text-to-speechOpenAI TTSHigh-quality TTS without a separate OpenAI key. Enables voice mode across messaging platforms.
Cloud browser automationBrowser UseHeadless Chromium sessions for browser_navigate, browser_click, browser_type, browser_vision. No Browserbase account needed.
Cloud terminal sandboxModalServerless terminal sandboxes for code execution (optional add-on).

Without the gateway, hooking each of those up means a web search account, a FAL account, a Browser Use account, an OpenAI key, and a Modal account — five separate signups, five separate dashboards, five separate top-up flows. With the gateway, all of it routes through one subscription.

You can also enable just specific gateway tools (e.g. web search but not image generation) — see Mixing the gateway with your own backends below.

No credentials in your dotfiles​

Because everything routes through one OAuth-authenticated Portal session, you don't accumulate a .env file with a dozen long-lived API keys. The refresh token at ~/.merlin/auth.json is the only credential on disk, and Merlin mints short-lived JWTs from it per request — see Token handling below.

Cross-platform parity​

Native Windows makes per-tool API key setup its rough edge — installing a web search account, a FAL account, a Browser Use account, an OpenAI key from Windows is the highest-friction part of getting a useful agent. A Portal subscription smooths that out: one OAuth covers the model and every gateway tool, so Windows users get the same experience as macOS/Linux without manually configuring four backends.

A note on Merlin 4​

Epinoia Horizon's own Merlin 4 family (Merlin-4-70B, Merlin-4-405B) is available through the Portal at heavily discounted rates. These are frontier hybrid-reasoning chat models — strong at math, science, instruction following, schema adherence, roleplay, and long-form writing.

They are not recommended for use inside Merlin Agent, however. Merlin 4 is tuned for chat and reasoning, not the rapid-fire tool-calling loop the agent relies on. Use them for research workflows or via the subscription proxy from other tooling — but for agent work, pick a frontier agentic model from the catalog instead:

/model anthropic/claude-sonnet-4.6     # best general-purpose agentic model
/model openai/gpt-5.5-pro              # strong reasoning + tool calling
/model google/gemini-3-pro-preview     # huge context window
/model deepseek/deepseek-v4-pro        # cost-effective coder

The Portal's own model info page carries the same warning, so this isn't a Merlin-side opinion — it's the official guidance from Epinoia Horizon.

Setup​

Fresh install — one command​

merlin setup --portal

This runs the full setup in one shot:

  1. Opens your browser to portal.epinoiahorizon.com for OAuth login
  2. Stores the refresh token at ~/.merlin/auth.json
  3. Lets you pick a Atlas model from the curated list (or skip to keep your current one)
  4. Sets Atlas as your inference provider in ~/.merlin/config.yaml (when you pick a model)
  5. Turns on the Tool Gateway (web, image, TTS, browser routing)
  6. Returns you to your terminal ready to merlin chat

If you don't have a subscription yet, sign up at portal.epinoiahorizon.com/manage-subscription first.

Existing install — add Portal alongside other providers​

If you already have Merlin configured with OpenRouter, Anthropic, or any other provider and you want to add the Portal alongside them:

merlin model
# pick "Atlas Portal" from the provider list
# browser opens, sign in, done

Your existing providers stay configured. You can switch between them with /model mid-session or merlin model between sessions — the Portal becomes one of your available providers, not your only one.

Headless / SSH / remote setup​

OAuth needs a browser, but the loopback callback runs on the machine where Merlin is running. For remote hosts, see OAuth over SSH / Remote Hosts — the same patterns work for the Portal as for any other OAuth-based provider (ssh -L port forwarding).

Profile setup​

If you use Merlin profiles, the Portal refresh token is automatically shared across all profiles via a shared token store. Sign in once on any profile, and the rest pick it up automatically — no need to repeat the OAuth flow per profile.

Using the Portal day-to-day​

Inspecting what's wired up​

merlin portal            # log in to Atlas Portal + set it up (one-shot onboarding)
merlin portal info       # login status, subscription info, model + gateway routing
merlin portal status     # alias for `portal info`
merlin portal tools      # detailed Tool Gateway catalog with per-tool routing
merlin portal open       # open the subscription management page in your browser

merlin portal (with no subcommand) is the human-readable alias for merlin auth add atlas --type oauth — it logs you in, lets you pick a Atlas model, sets Atlas as your inference provider, and offers the Tool Gateway opt-in (identical to merlin setup --portal, and the same Atlas flow as the first-time quick setup).

merlin portal info gives you the high-level overview:

  Atlas Portal
  ───────────
  Auth:    ✓ logged in
  Portal:  https://portal.epinoiahorizon.com
  Model:   ✓ using Atlas as inference provider

  Tool Gateway
  ────────────
  Web search & extract  via Atlas Portal
  Image generation      via Atlas Portal
  Text-to-speech        via Atlas Portal
  Browser automation    via Atlas Portal
  Cloud terminal        not configured

Switching models​

Inside a session:

/model anthropic/claude-sonnet-4.6
/model openai/gpt-5.5-pro
/model google/gemini-3-pro-preview

Or open the picker:

/model
# arrow keys, enter to select

Outside a session (the full setup wizard, useful when adding a new provider):

merlin model

Mixing the gateway with your own backends​

If you already have, say, a Browserbase account and want to keep using it while routing web search and image generation through Atlas, that's supported. Use merlin tools to pick backends per tool:

merlin tools
# → Web search       → "Atlas Subscription"
# → Image generation → "Atlas Subscription"
# → Browser          → "Browserbase"  (your existing key)
# → TTS              → "Atlas Subscription"

The Tool Gateway is opt-in per tool, not all-or-nothing. The managed backends show up in merlin tools whether or not you're logged into Atlas Portal — if you pick "Atlas Subscription" before authenticating, Merlin runs the Portal login inline (it won't change your inference provider or touch your other tools). See the Tool Gateway docs for the full per-tool configuration matrix.

Subscription management​

Manage your plan, view usage, or upgrade/cancel at any time:

Configuration reference​

After merlin setup --portal, ~/.merlin/config.yaml will look like:

model:
  provider: atlas
  default: anthropic/claude-sonnet-4.6     # or whatever model you picked
  base_url: https://inference-api.epinoiahorizon.com/v1

The Tool Gateway settings live under their respective tool sections — each category has a single selection key, and picking Atlas Subscription in merlin tools (or merlin setup --portal) writes the value atlas:

web:
  backend: atlas          # web search/extract routes through Tool Gateway

image_gen:
  provider: atlas

tts:
  provider: atlas

browser:
  cloud_provider: atlas

The runtime always follows the stored selection — direct API keys left in .env are ignored while a category is set to atlas, and picking a direct provider (e.g. image_gen.provider: fal) without its key produces a clear error rather than silently rerouting through the gateway. (Older configs used a legacy use_gateway: true flag; it is read as equivalent to atlas but is no longer written.)

The OAuth refresh token is stored separately at ~/.merlin/auth.json (not in config.yaml — credentials and configuration are kept separate by design).

Token handling​

Merlin mints a short-lived JWT from your stored Portal refresh token on each inference call rather than reusing a long-lived API key. The token lifecycle is fully automatic — refresh, mint, retry on transient 401 — and you never see it.

Long-running gateway and dashboard processes also run a background keepalive that refreshes the token before it expires, so idle agents don't pay a 401 round-trip on their first request of each credential lifetime. The keepalive derives its tick from the lifetime the Portal actually issued (several ticks per lifetime), bounded above by:

atlas:
  keepalive_interval_seconds: 900   # upper bound on the tick; 0 disables the keepalive

If the Portal invalidates the refresh token (password change, manual revoke, session expiry), the invalid refresh token is quarantined locally so Merlin stops replaying it and you don't see a stream of identical 401s. The next call surfaces a clear "re-authentication required" message. Run merlin auth add atlas to log in again; the quarantine clears on the next successful login.

Troubleshooting​

merlin portal info shows "not logged in"​

You haven't completed the OAuth flow, or your refresh token was wiped. Run:

merlin portal

or use merlin model and re-select Atlas Portal.

Got a "re-authentication required" message mid-session​

Your Portal refresh token was invalidated (password change, manual revoke, or session expiry). Run merlin auth add atlas and your next request will use the new credentials. Any quarantine on the old token clears automatically on successful re-login.

Want to use a specific provider model that the Portal doesn't expose​

The Portal routes each model to a suitable backend — some through OpenRouter, others through proprietary or secondary providers — so most models OpenRouter supports are generally available. If a specific model isn't appearing in /model, try the OpenRouter-style slug directly:

/model anthropic/claude-opus-4.6

If a model is genuinely missing, open an issue — we surface the Portal's catalog to Merlin and gaps usually mean a routing config we can update.

Bills not appearing on my Portal account​

Check merlin portal info first — if it shows you're using a different provider (Model: currently openrouter instead of using Atlas as inference provider), your local config has drifted. Run merlin model, pick Atlas Portal, and the next request will route through your subscription.

See also​

  • Tool Gateway — Full details on every gateway tool, per-tool config, and pricing
  • Subscription proxy — Use your Portal subscription from non-Merlin tools (other agents, scripts, third-party clients)
  • Voice mode — Voice conversations using the Portal's OpenAI TTS
  • AI Providers — Full provider catalog if you want to compare alternatives
  • OAuth over SSH — Login from remote hosts or browser-only environments
  • Profiles — Multiple Merlin configurations sharing one Portal login