show cache pricing as well (if supported)

Display live per-million-token pricing from /v1/models when listing
models for OpenRouter or Nous Portal. Prices are shown in a
column-aligned table with decimal points vertically aligned for
easy comparison.

Pricing appears in three places:
- /provider slash command (table with In/Out headers)
- hermes model picker (aligned columns in both TerminalMenu and
  numbered fallback)

Implementation:
- Add fetch_models_with_pricing() in models.py with per-base_url
  module-level cache (one network call per endpoint per session)
- Add _format_price_per_mtok() with fixed 2-decimal formatting
- Add format_model_pricing_table() for terminal table display
- Add get_pricing_for_provider() convenience wrapper
- Update _prompt_model_selection() to accept optional pricing dict
- Wire pricing through _model_flow_openrouter/nous in main.py
- Update test mocks for new pricing parameter

cli.py

@@ -3392,6 +3392,7 @@ class HermesCLI:
         from hermes_cli.models import (
             curated_models_for_provider, list_available_providers,
             normalize_provider, _PROVIDER_LABELS,
+            get_pricing_for_provider, format_model_pricing_table,
         )
         from hermes_cli.auth import resolve_provider as _resolve_provider
 
@@ -3425,7 +3426,13 @@ class HermesCLI:
                 marker = " ← active" if is_active else ""
                 print(f"    [{p['id']}]{marker}")
                 curated = curated_models_for_provider(p["id"])
-                if curated:
+                # Fetch pricing for providers that support it (openrouter, nous)
+                pricing_map = get_pricing_for_provider(p["id"]) if p["id"] in ("openrouter", "nous") else {}
+                if curated and pricing_map:
+                    cur_model = self.model if is_active else ""
+                    for line in format_model_pricing_table(curated, pricing_map, current_model=cur_model):
+                        print(line)
+                elif curated:
                     for mid, desc in curated:
                         current_marker = " ← current" if (is_active and mid == self.model) else ""
                         print(f"      {mid}{current_marker}")

hermes_cli/auth.py

@@ -2143,8 +2143,18 @@ def _reset_config_provider() -> Path:
     return config_path
 
 
-def _prompt_model_selection(model_ids: List[str], current_model: str = "") -> Optional[str]:
-    """Interactive model selection. Puts current_model first with a marker. Returns chosen model ID or None."""
+def _prompt_model_selection(
+    model_ids: List[str],
+    current_model: str = "",
+    pricing: Optional[Dict[str, Dict[str, str]]] = None,
+) -> Optional[str]:
+    """Interactive model selection. Puts current_model first with a marker. Returns chosen model ID or None.
+
+    If *pricing* is provided (``{model_id: {prompt, completion}}``), a compact
+    price indicator is shown next to each model in aligned columns.
+    """
+    from hermes_cli.models import _format_price_per_mtok
+
     # Reorder: current model first, then the rest (deduplicated)
     ordered = []
     if current_model and current_model in model_ids:
@@ -2153,15 +2163,61 @@ def _prompt_model_selection(model_ids: List[str], current_model: str = "") -> Op
         if mid not in ordered:
             ordered.append(mid)
 
-    # Build display labels with marker on current
+    # Column-aligned labels when pricing is available
+    has_pricing = bool(pricing and any(pricing.get(m) for m in ordered))
+    name_col = max((len(m) for m in ordered), default=0) + 2 if has_pricing else 0
+
+    # Pre-compute formatted prices and dynamic column widths
+    _price_cache: dict[str, tuple[str, str, str]] = {}
+    price_col = 3  # minimum width
+    cache_col = 0  # only set if any model has cache pricing
+    has_cache = False
+    if has_pricing:
+        for mid in ordered:
+            p = pricing.get(mid)  # type: ignore[union-attr]
+            if p:
+                inp = _format_price_per_mtok(p.get("prompt", ""))
+                out = _format_price_per_mtok(p.get("completion", ""))
+                cache_read = p.get("input_cache_read", "")
+                cache = _format_price_per_mtok(cache_read) if cache_read else ""
+                if cache:
+                    has_cache = True
+            else:
+                inp, out, cache = "", "", ""
+            _price_cache[mid] = (inp, out, cache)
+            price_col = max(price_col, len(inp), len(out))
+            cache_col = max(cache_col, len(cache))
+        if has_cache:
+            cache_col = max(cache_col, 5)  # minimum: "Cache" header
+
     def _label(mid):
+        if has_pricing:
+            inp, out, cache = _price_cache.get(mid, ("", "", ""))
+            price_part = f" {inp:>{price_col}}  {out:>{price_col}}"
+            if has_cache:
+                price_part += f"  {cache:>{cache_col}}"
+            base = f"{mid:<{name_col}}{price_part}"
+        else:
+            base = mid
         if mid == current_model:
-            return f"{mid}  ← currently in use"
-        return mid
+            base += "  ← currently in use"
+        return base
 
     # Default cursor on the current model (index 0 if it was reordered to top)
     default_idx = 0
 
+    # Build a pricing header hint for the menu title
+    menu_title = "Select default model:"
+    if has_pricing:
+        # Align the header with the model column.
+        # Each choice is "  {label}" (2 spaces) and simple_term_menu prepends
+        # a 3-char cursor region ("-> " or "   "), so content starts at col 5.
+        pad = " " * 5
+        header = f"\n{pad}{'':>{name_col}} {'In':>{price_col}}  {'Out':>{price_col}}"
+        if has_cache:
+            header += f"  {'Cache':>{cache_col}}"
+        menu_title += header + "  /Mtok"
+
     # Try arrow-key menu first, fall back to number input
     try:
         from simple_term_menu import TerminalMenu
@@ -2176,7 +2232,7 @@ def _prompt_model_selection(model_ids: List[str], current_model: str = "") -> Op
             menu_highlight_style=("fg_green",),
             cycle_cursor=True,
             clear_screen=False,
-            title="Select default model:",
+            title=menu_title,
         )
         idx = menu.show()
         if idx is None:
@@ -2192,12 +2248,13 @@ def _prompt_model_selection(model_ids: List[str], current_model: str = "") -> Op
         pass
 
     # Fallback: numbered list
-    print("Select default model:")
+    print(menu_title)
+    num_width = len(str(len(ordered) + 2))
     for i, mid in enumerate(ordered, 1):
-        print(f"  {i}. {_label(mid)}")
+        print(f"  {i:>{num_width}}. {_label(mid)}")
     n = len(ordered)
-    print(f"  {n + 1}. Enter custom model name")
-    print(f"  {n + 2}. Skip (keep current)")
+    print(f"  {n + 1:>{num_width}}. Enter custom model name")
+    print(f"  {n + 2:>{num_width}}. Skip (keep current)")
     print()
 
     while True:

hermes_cli/main.py

@@ -1088,10 +1088,13 @@ def _model_flow_openrouter(config, current_model=""):
         print("API key saved.")
         print()
 
-    from hermes_cli.models import model_ids
+    from hermes_cli.models import model_ids, get_pricing_for_provider
     openrouter_models = model_ids()
 
-    selected = _prompt_model_selection(openrouter_models, current_model=current_model)
+    # Fetch live pricing (non-blocking — returns empty dict on failure)
+    pricing = get_pricing_for_provider("openrouter")
+
+    selected = _prompt_model_selection(openrouter_models, current_model=current_model, pricing=pricing)
     if selected:
         _save_model_choice(selected)
 
@@ -1158,7 +1161,7 @@ def _model_flow_nous(config, current_model="", args=None):
     # Already logged in — use curated model list (same as OpenRouter defaults).
     # The live /models endpoint returns hundreds of models; the curated list
     # shows only agentic models users recognize from OpenRouter.
-    from hermes_cli.models import _PROVIDER_MODELS
+    from hermes_cli.models import _PROVIDER_MODELS, get_pricing_for_provider
     model_ids = _PROVIDER_MODELS.get("nous", [])
     if not model_ids:
         print("No curated models available for Nous Portal.")
@@ -1188,7 +1191,10 @@ def _model_flow_nous(config, current_model="", args=None):
         print(f"Could not verify credentials: {msg}")
         return
 
-    selected = _prompt_model_selection(model_ids, current_model=current_model)
+    # Fetch live pricing (non-blocking — returns empty dict on failure)
+    pricing = get_pricing_for_provider("nous")
+
+    selected = _prompt_model_selection(model_ids, current_model=current_model, pricing=pricing)
     if selected:
         _save_model_choice(selected)
         # Reactivate Nous as the provider and update config

hermes_cli/models.py

@@ -324,6 +324,213 @@ def menu_labels() -> list[str]:
     return labels
 
 
+# ---------------------------------------------------------------------------
+# Pricing helpers — fetch live pricing from OpenRouter-compatible /v1/models
+# ---------------------------------------------------------------------------
+
+# Cache: maps model_id → {"prompt": str, "completion": str} per endpoint
+_pricing_cache: dict[str, dict[str, dict[str, str]]] = {}
+
+
+def _format_price_per_mtok(per_token_str: str) -> str:
+    """Convert a per-token price string to a human-friendly $/Mtok string.
+
+    Always uses 2 decimal places so that prices align vertically when
+    right-justified in a column (the decimal point stays in the same position).
+
+    Examples:
+        "0.000003"   → "$3.00"      (per million tokens)
+        "0.00003"    → "$30.00"
+        "0.00000015" → "$0.15"
+        "0.0000001"  → "$0.10"
+        "0.00018"    → "$180.00"
+        "0"          → "free"
+    """
+    try:
+        val = float(per_token_str)
+    except (TypeError, ValueError):
+        return "?"
+    if val == 0:
+        return "free"
+    per_m = val * 1_000_000
+    return f"${per_m:.2f}"
+
+
+def format_pricing_label(pricing: dict[str, str] | None) -> str:
+    """Build a compact pricing label like 'in $3 · out $15 · cache $0.30/Mtok'.
+
+    Returns empty string when pricing is unavailable.
+    """
+    if not pricing:
+        return ""
+    prompt_price = pricing.get("prompt", "")
+    completion_price = pricing.get("completion", "")
+    if not prompt_price and not completion_price:
+        return ""
+    inp = _format_price_per_mtok(prompt_price)
+    out = _format_price_per_mtok(completion_price)
+    if inp == "free" and out == "free":
+        return "free"
+    cache_read = pricing.get("input_cache_read", "")
+    cache_str = _format_price_per_mtok(cache_read) if cache_read else ""
+    if inp == out and not cache_str:
+        return f"{inp}/Mtok"
+    parts = [f"in {inp}", f"out {out}"]
+    if cache_str and cache_str != "?" and cache_str != inp:
+        parts.append(f"cache {cache_str}")
+    return " · ".join(parts) + "/Mtok"
+
+
+def format_model_pricing_table(
+    models: list[tuple[str, str]],
+    pricing_map: dict[str, dict[str, str]],
+    current_model: str = "",
+    indent: str = "      ",
+) -> list[str]:
+    """Build a column-aligned model+pricing table for terminal display.
+
+    Returns a list of pre-formatted lines ready to print.
+    *models* is ``[(model_id, description), ...]``.
+    """
+    if not models:
+        return []
+
+    # Build rows: (model_id, input_price, output_price, cache_price, is_current)
+    rows: list[tuple[str, str, str, str, bool]] = []
+    has_cache = False
+    for mid, _desc in models:
+        is_cur = mid == current_model
+        p = pricing_map.get(mid)
+        if p:
+            inp = _format_price_per_mtok(p.get("prompt", ""))
+            out = _format_price_per_mtok(p.get("completion", ""))
+            cache_read = p.get("input_cache_read", "")
+            cache = _format_price_per_mtok(cache_read) if cache_read else ""
+            if cache:
+                has_cache = True
+        else:
+            inp, out, cache = "", "", ""
+        rows.append((mid, inp, out, cache, is_cur))
+
+    name_col = max(len(r[0]) for r in rows) + 2
+    # Compute price column widths from the actual data so decimals align
+    price_col = max(
+        max((len(r[1]) for r in rows if r[1]), default=4),
+        max((len(r[2]) for r in rows if r[2]), default=4),
+        3,  # minimum: "In" / "Out" header
+    )
+    cache_col = max(
+        max((len(r[3]) for r in rows if r[3]), default=4),
+        5,  # minimum: "Cache" header
+    ) if has_cache else 0
+    lines: list[str] = []
+
+    # Header
+    if has_cache:
+        lines.append(f"{indent}{'Model':<{name_col}} {'In':>{price_col}}  {'Out':>{price_col}}  {'Cache':>{cache_col}}  /Mtok")
+        lines.append(f"{indent}{'-' * name_col} {'-' * price_col}  {'-' * price_col}  {'-' * cache_col}")
+    else:
+        lines.append(f"{indent}{'Model':<{name_col}} {'In':>{price_col}}  {'Out':>{price_col}}  /Mtok")
+        lines.append(f"{indent}{'-' * name_col} {'-' * price_col}  {'-' * price_col}")
+
+    for mid, inp, out, cache, is_cur in rows:
+        marker = "  ← current" if is_cur else ""
+        if has_cache:
+            lines.append(f"{indent}{mid:<{name_col}} {inp:>{price_col}}  {out:>{price_col}}  {cache:>{cache_col}}{marker}")
+        else:
+            lines.append(f"{indent}{mid:<{name_col}} {inp:>{price_col}}  {out:>{price_col}}{marker}")
+
+    return lines
+
+
+def fetch_models_with_pricing(
+    api_key: str | None = None,
+    base_url: str = "https://openrouter.ai/api",
+    timeout: float = 8.0,
+    *,
+    force_refresh: bool = False,
+) -> dict[str, dict[str, str]]:
+    """Fetch ``/v1/models`` and return ``{model_id: {prompt, completion}}`` pricing.
+
+    Results are cached per *base_url* so repeated calls are free.
+    Works with any OpenRouter-compatible endpoint (OpenRouter, Nous Portal).
+    """
+    cache_key = (base_url or "").rstrip("/")
+    if not force_refresh and cache_key in _pricing_cache:
+        return _pricing_cache[cache_key]
+
+    url = cache_key.rstrip("/") + "/v1/models"
+    headers: dict[str, str] = {"Accept": "application/json"}
+    if api_key:
+        headers["Authorization"] = f"Bearer {api_key}"
+
+    try:
+        req = urllib.request.Request(url, headers=headers)
+        with urllib.request.urlopen(req, timeout=timeout) as resp:
+            payload = json.loads(resp.read().decode())
+    except Exception:
+        _pricing_cache[cache_key] = {}
+        return {}
+
+    result: dict[str, dict[str, str]] = {}
+    for item in payload.get("data", []):
+        mid = item.get("id")
+        pricing = item.get("pricing")
+        if mid and isinstance(pricing, dict):
+            entry: dict[str, str] = {
+                "prompt": str(pricing.get("prompt", "")),
+                "completion": str(pricing.get("completion", "")),
+            }
+            if pricing.get("input_cache_read"):
+                entry["input_cache_read"] = str(pricing["input_cache_read"])
+            if pricing.get("input_cache_write"):
+                entry["input_cache_write"] = str(pricing["input_cache_write"])
+            result[mid] = entry
+
+    _pricing_cache[cache_key] = result
+    return result
+
+
+def _resolve_openrouter_api_key() -> str:
+    """Best-effort OpenRouter API key for pricing fetch."""
+    return os.getenv("OPENROUTER_API_KEY", "").strip()
+
+
+def _resolve_nous_pricing_credentials() -> tuple[str, str]:
+    """Return ``(api_key, base_url)`` for Nous Portal pricing, or empty strings."""
+    try:
+        from hermes_cli.auth import resolve_nous_runtime_credentials
+        creds = resolve_nous_runtime_credentials()
+        if creds:
+            return (creds.get("api_key", ""), creds.get("base_url", ""))
+    except Exception:
+        pass
+    return ("", "")
+
+
+def get_pricing_for_provider(provider: str) -> dict[str, dict[str, str]]:
+    """Return live pricing for providers that support it (openrouter, nous)."""
+    normalized = normalize_provider(provider)
+    if normalized == "openrouter":
+        return fetch_models_with_pricing(
+            api_key=_resolve_openrouter_api_key(),
+            base_url="https://openrouter.ai/api",
+        )
+    if normalized == "nous":
+        api_key, base_url = _resolve_nous_pricing_credentials()
+        if base_url:
+            # Nous base_url typically looks like https://inference-api.nousresearch.com/v1
+            # We need the part before /v1 for our fetch function
+            stripped = base_url.rstrip("/")
+            if stripped.endswith("/v1"):
+                stripped = stripped[:-3]
+            return fetch_models_with_pricing(
+                api_key=api_key,
+                base_url=stripped,
+            )
+    return {}
+
+
 # All provider IDs and aliases that are valid for the provider:model syntax.
 _KNOWN_PROVIDER_NAMES: set[str] = (
     set(_PROVIDER_LABELS.keys())

tests/test_cli_provider_resolution.py

@@ -330,7 +330,7 @@ def test_model_flow_nous_prints_subscription_guidance_without_mutating_explicit_
         "hermes_cli.auth.fetch_nous_models",
         lambda *args, **kwargs: ["claude-opus-4-6"],
     )
-    monkeypatch.setattr("hermes_cli.auth._prompt_model_selection", lambda model_ids, current_model="": "claude-opus-4-6")
+    monkeypatch.setattr("hermes_cli.auth._prompt_model_selection", lambda model_ids, current_model="", pricing=None: "claude-opus-4-6")
     monkeypatch.setattr("hermes_cli.auth._save_model_choice", lambda model: None)
     monkeypatch.setattr("hermes_cli.auth._update_config_for_provider", lambda provider, url: None)
     monkeypatch.setattr(
@@ -368,7 +368,7 @@ def test_model_flow_nous_applies_managed_tts_default_when_unconfigured(monkeypat
         "hermes_cli.auth.fetch_nous_models",
         lambda *args, **kwargs: ["claude-opus-4-6"],
     )
-    monkeypatch.setattr("hermes_cli.auth._prompt_model_selection", lambda model_ids, current_model="": "claude-opus-4-6")
+    monkeypatch.setattr("hermes_cli.auth._prompt_model_selection", lambda model_ids, current_model="", pricing=None: "claude-opus-4-6")
     monkeypatch.setattr("hermes_cli.auth._save_model_choice", lambda model: None)
     monkeypatch.setattr("hermes_cli.auth._update_config_for_provider", lambda provider, url: None)
     monkeypatch.setattr(