diff --git a/agent/agent_init.py b/agent/agent_init.py
index 62de3f2c540..c51177a9b8b 100644
--- a/agent/agent_init.py
+++ b/agent/agent_init.py
@@ -1620,6 +1620,12 @@ def init_agent(
     agent.session_cache_write_tokens = 0
     agent.session_reasoning_tokens = 0
     agent.session_estimated_cost_usd = 0.0
+    # Provider-REPORTED cost only (e.g. OpenRouter usage.cost). None means
+    # "nothing reported" — distinct from a real $0.00.
+    agent.session_actual_cost_usd = None
+    # Per-model session usage rows for /usage: {model: {calls, input, output,
+    # cache_read, cache_write, cost_usd|None}}.
+    agent.session_model_usage = {}
     agent.session_cost_status = "unknown"
     agent.session_cost_source = "none"
     
diff --git a/agent/conversation_loop.py b/agent/conversation_loop.py
index 2e4b7ed7073..d0231e994ac 100644
--- a/agent/conversation_loop.py
+++ b/agent/conversation_loop.py
@@ -57,7 +57,11 @@ from agent.process_bootstrap import _install_safe_stdio
 from agent.prompt_caching import apply_anthropic_cache_control
 from agent.retry_utils import jittered_backoff
 from agent.trajectory import has_incomplete_scratchpad
-from agent.usage_pricing import estimate_usage_cost, normalize_usage
+from agent.usage_pricing import (
+    estimate_usage_cost,
+    extract_provider_cost_usd,
+    normalize_usage,
+)
 from hermes_constants import PARTIAL_STREAM_STUB_ID
 from hermes_logging import set_session_context
 from tools.skill_provenance import set_current_write_origin
@@ -1633,6 +1637,37 @@ def run_conversation(
                     agent.session_cost_status = cost_result.status
                     agent.session_cost_source = cost_result.source
 
+                    # ── Real provider-REPORTED cost (never estimated) ──
+                    # OpenRouter usage accounting returns ``usage.cost`` on the
+                    # response when the request carries usage:{include:true}
+                    # (added on OpenRouter routes). When the provider reports
+                    # nothing, this stays None — absent, NOT zero — so cost
+                    # displays hide instead of showing a fabricated $0.00.
+                    reported_cost_usd = extract_provider_cost_usd(response.usage)
+                    if reported_cost_usd is not None:
+                        _prev_actual = getattr(agent, "session_actual_cost_usd", None)
+                        agent.session_actual_cost_usd = (_prev_actual or 0.0) + reported_cost_usd
+                        agent.session_cost_status = "actual"
+                        agent.session_cost_source = "provider_cost_api"
+
+                    # Per-model session breakdown for /usage — counts are always
+                    # real; cost_usd only accumulates provider-reported values
+                    # and stays None when the provider reports nothing.
+                    _model_usage = getattr(agent, "session_model_usage", None)
+                    if _model_usage is None:
+                        _model_usage = agent.session_model_usage = {}
+                    _mrow = _model_usage.setdefault(agent.model, {
+                        "calls": 0, "input": 0, "output": 0,
+                        "cache_read": 0, "cache_write": 0, "cost_usd": None,
+                    })
+                    _mrow["calls"] += 1
+                    _mrow["input"] += canonical_usage.input_tokens
+                    _mrow["output"] += canonical_usage.output_tokens
+                    _mrow["cache_read"] += canonical_usage.cache_read_tokens
+                    _mrow["cache_write"] += canonical_usage.cache_write_tokens
+                    if reported_cost_usd is not None:
+                        _mrow["cost_usd"] = (_mrow["cost_usd"] or 0.0) + reported_cost_usd
+
                     # Persist token counts to session DB for /insights.
                     # Do this for every platform with a session_id so non-CLI
                     # sessions (gateway, cron, delegated runs) cannot lose
@@ -1659,8 +1694,14 @@ def run_conversation(
                                 reasoning_tokens=canonical_usage.reasoning_tokens,
                                 estimated_cost_usd=float(cost_result.amount_usd)
                                 if cost_result.amount_usd is not None else None,
-                                cost_status=cost_result.status,
-                                cost_source=cost_result.source,
+                                # Provider-reported per-call cost delta. NULL
+                                # (not 0) when the provider reported nothing —
+                                # the SQL CASE keeps actual_cost_usd untouched.
+                                actual_cost_usd=reported_cost_usd,
+                                cost_status="actual"
+                                if reported_cost_usd is not None else cost_result.status,
+                                cost_source="provider_cost_api"
+                                if reported_cost_usd is not None else cost_result.source,
                                 billing_provider=agent.provider,
                                 billing_base_url=agent.base_url,
                                 billing_mode="subscription_included"
diff --git a/agent/transports/chat_completions.py b/agent/transports/chat_completions.py
index 0c17e309a8b..3649f21d3eb 100644
--- a/agent/transports/chat_completions.py
+++ b/agent/transports/chat_completions.py
@@ -388,6 +388,13 @@ class ChatCompletionsTransport(ProviderTransport):
         if provider_prefs and is_openrouter:
             extra_body["provider"] = provider_prefs
 
+        # OpenRouter usage accounting — response `usage.cost` carries the REAL
+        # charged cost (credits are 1:1 USD). Parity with the profile path in
+        # plugins/model-providers/openrouter/__init__.py; this branch only runs
+        # when the OpenRouter profile isn't loaded.
+        if is_openrouter:
+            extra_body["usage"] = {"include": True}
+
         # Pareto Code router plugin — model-gated. Same shape as the
         # profile path in plugins/model-providers/openrouter/__init__.py;
         # this branch only runs when the OpenRouter profile isn't loaded.
diff --git a/agent/usage_pricing.py b/agent/usage_pricing.py
index 8d6b85cd0b8..69cc74f3db9 100644
--- a/agent/usage_pricing.py
+++ b/agent/usage_pricing.py
@@ -849,6 +849,73 @@ def estimate_usage_cost(
     )
 
 
+def _finite_nonneg_number(value: Any) -> Optional[float]:
+    """Return ``value`` as a float when it is a real, finite, non-negative
+    number (int/float, not bool); otherwise None."""
+    if isinstance(value, bool) or not isinstance(value, (int, float)):
+        return None
+    try:
+        f = float(value)
+    except (TypeError, ValueError):
+        return None
+    if f != f or f in (float("inf"), float("-inf")) or f < 0:
+        return None
+    return f
+
+
+def extract_provider_cost_usd(response_usage: Any) -> Optional[float]:
+    """Provider-REPORTED cost (USD) from a response ``usage`` object, or None.
+
+    Reads the ``usage.cost`` field that OpenRouter's usage accounting returns
+    (``usage: {"include": true}`` request param; OpenRouter credits are 1:1
+    USD). OpenRouter-compatible aggregators use the same field. This NEVER
+    estimates: when the provider reports nothing, the result is None — callers
+    must treat None as "no cost data", not zero. A reported ``0`` is a real
+    zero (e.g. free-tier models) and is returned as ``0.0``.
+    """
+    if response_usage is None:
+        return None
+    cost = getattr(response_usage, "cost", None)
+    if cost is None and isinstance(response_usage, dict):
+        cost = response_usage.get("cost")
+    return _finite_nonneg_number(cost)
+
+
+def real_session_cost_usd(agent: Any) -> Optional[float]:
+    """Session-cumulative provider-REPORTED cost in USD, or None.
+
+    Combines the two real sources Hermes has — no estimation, ever:
+      - ``agent.session_actual_cost_usd``: per-response ``usage.cost``
+        accumulator (OpenRouter usage accounting).
+      - Nous ``x-nous-credits-*`` header delta via
+        ``agent.get_credits_spent_micros()`` (account-level spend since the
+        session first saw a header; clamped at 0 so a mid-session top-up
+        doesn't render a negative cost).
+
+    Returns None when neither source has reported anything — callers must
+    hide their cost display in that case rather than showing $0.00.
+    """
+    total: Optional[float] = None
+
+    actual = _finite_nonneg_number(getattr(agent, "session_actual_cost_usd", None))
+    if actual is not None:
+        total = actual
+
+    try:
+        spent_micros = agent.get_credits_spent_micros()
+    except Exception:
+        spent_micros = None
+    if spent_micros is not None:
+        try:
+            spent_usd = max(0, int(spent_micros)) / 1_000_000
+        except (TypeError, ValueError):
+            spent_usd = None
+        if spent_usd is not None:
+            total = (total or 0.0) + spent_usd
+
+    return total
+
+
 def has_known_pricing(
     model_name: str,
     provider: Optional[str] = None,
diff --git a/cli.py b/cli.py
index 000778b750f..37861e65dc6 100644
--- a/cli.py
+++ b/cli.py
@@ -10638,14 +10638,13 @@ class HermesCLI:
         compressions = compressor.compression_count
 
         msg_count = len(self.conversation_history)
-        cost_result = estimate_usage_cost(
+        # Cost — provider-REPORTED only (OpenRouter usage.cost accumulator
+        # and/or Nous credits-header delta). No estimation: an unreported
+        # cost shows as "not reported", never a fabricated dollar figure.
+        from agent.usage_pricing import real_session_cost_usd, resolve_billing_route
+        real_cost_usd = real_session_cost_usd(agent)
+        _billing_route = resolve_billing_route(
             agent.model,
-            CanonicalUsage(
-                input_tokens=input_tokens,
-                output_tokens=output_tokens,
-                cache_read_tokens=cache_read_tokens,
-                cache_write_tokens=cache_write_tokens,
-            ),
             provider=getattr(agent, "provider", None),
             base_url=getattr(agent, "base_url", None),
         )
@@ -10665,21 +10664,16 @@ class HermesCLI:
         print(f"  Total tokens:              {total:>10,}")
         print(f"  API calls:                 {calls:>10,}")
         print(f"  Session duration:          {elapsed:>10}")
-        print(f"  Cost status:              {cost_result.status:>10}")
-        print(f"  Cost source:              {cost_result.source:>10}")
-        if cost_result.amount_usd is not None:
-            prefix = "~" if cost_result.status == "estimated" else ""
-            print(f"  Total cost:              {prefix}${float(cost_result.amount_usd):>10.4f}")
-        elif cost_result.status == "included":
-            print(f"  Total cost:              {'included':>10}")
+        if real_cost_usd is not None:
+            print(f"  Cost (provider-reported): ${real_cost_usd:>9.4f}")
+        elif _billing_route.billing_mode == "subscription_included":
+            print(f"  Cost:                    {'included':>11}")
         else:
-            print(f"  Total cost:              {'n/a':>10}")
+            print(f"  Cost:        {'not reported by provider':>23}")
         print(f"  {'─' * 40}")
         print(f"  Current context:  {last_prompt:,} / {ctx_len:,} ({pct:.0f}%)")
         print(f"  Messages:         {msg_count}")
         print(f"  Compressions:     {compressions}")
-        if cost_result.status == "unknown":
-            print(f"  Note:             Pricing unknown for {agent.model}")
 
         # Account limits -- fetched off-thread with a hard timeout so slow
         # provider APIs don't hang the prompt.
diff --git a/gateway/run.py b/gateway/run.py
index 3cef89b96fd..ecb24da1d54 100644
--- a/gateway/run.py
+++ b/gateway/run.py
@@ -13277,25 +13277,24 @@ class GatewayRunner(GatewayKanbanWatchersMixin):
             lines.append(t("gateway.usage.label_total", count=f"{agent.session_total_tokens:,}"))
             lines.append(t("gateway.usage.label_api_calls", count=agent.session_api_calls))
 
-            # Cost estimation
+            # Cost — provider-REPORTED only (OpenRouter usage.cost accumulator
+            # and/or Nous credits-header delta). No estimation: when nothing
+            # was reported the line is omitted entirely, never shown as $0.00.
+            # Subscription-included routes (a billing fact, not a price guess)
+            # still show "included".
             try:
-                from agent.usage_pricing import CanonicalUsage, estimate_usage_cost
-                cost_result = estimate_usage_cost(
-                    agent.model,
-                    CanonicalUsage(
-                        input_tokens=input_tokens,
-                        output_tokens=output_tokens,
-                        cache_read_tokens=cache_read,
-                        cache_write_tokens=cache_write,
-                    ),
-                    provider=getattr(agent, "provider", None),
-                    base_url=getattr(agent, "base_url", None),
-                )
-                if cost_result.amount_usd is not None:
-                    prefix = "~" if cost_result.status == "estimated" else ""
-                    lines.append(t("gateway.usage.label_cost", prefix=prefix, amount=f"{float(cost_result.amount_usd):.4f}"))
-                elif cost_result.status == "included":
-                    lines.append(t("gateway.usage.label_cost_included"))
+                from agent.usage_pricing import real_session_cost_usd, resolve_billing_route
+                real_cost = real_session_cost_usd(agent)
+                if real_cost is not None:
+                    lines.append(t("gateway.usage.label_cost", prefix="", amount=f"{real_cost:.4f}"))
+                else:
+                    route = resolve_billing_route(
+                        agent.model,
+                        provider=getattr(agent, "provider", None),
+                        base_url=getattr(agent, "base_url", None),
+                    )
+                    if route.billing_mode == "subscription_included":
+                        lines.append(t("gateway.usage.label_cost_included"))
             except Exception:
                 pass
 
diff --git a/plugins/model-providers/openrouter/__init__.py b/plugins/model-providers/openrouter/__init__.py
index 1b464b42e82..19ab1545f76 100644
--- a/plugins/model-providers/openrouter/__init__.py
+++ b/plugins/model-providers/openrouter/__init__.py
@@ -49,6 +49,13 @@ class OpenRouterProfile(ProviderProfile):
         if prefs:
             body["provider"] = prefs
 
+        # Usage accounting — makes OpenRouter return the REAL cost it charged
+        # in the response `usage.cost` field (credits are 1:1 USD), instead of
+        # Hermes having to estimate from a pricing table. Captured by
+        # agent.usage_pricing.extract_provider_cost_usd in the conversation
+        # loop. https://openrouter.ai/docs/use-cases/usage-accounting
+        body["usage"] = {"include": True}
+
         # Pareto Code router — model-gated. The plugins block is only
         # meaningful for openrouter/pareto-code; sending it on any other
         # model has no documented effect and would be confusing in logs.
diff --git a/run_agent.py b/run_agent.py
index c6cc1e21581..f95a91a19a4 100644
--- a/run_agent.py
+++ b/run_agent.py
@@ -632,6 +632,9 @@ class AIAgent:
         self.session_reasoning_tokens = 0
         self.session_api_calls = 0
         self.session_estimated_cost_usd = 0.0
+        # Provider-REPORTED cost only — None means "nothing reported".
+        self.session_actual_cost_usd = None
+        self.session_model_usage = {}
         self.session_cost_status = "unknown"
         self.session_cost_source = "none"
         
diff --git a/tests/agent/test_provider_cost_capture.py b/tests/agent/test_provider_cost_capture.py
new file mode 100644
index 00000000000..5399d81a907
--- /dev/null
+++ b/tests/agent/test_provider_cost_capture.py
@@ -0,0 +1,186 @@
+"""Real provider-reported cost capture — never estimated, absent ≠ zero.
+
+Covers the three fixture shapes from the cost-tracking fix:
+  - OpenRouter usage accounting: response ``usage.cost`` present → accumulates.
+  - Nous: ``x-nous-credits-*`` headers present → header delta accumulates.
+  - Provider reports nothing → cost stays None/absent (NOT zero-as-real).
+"""
+
+from types import SimpleNamespace
+
+import pytest
+
+from agent.usage_pricing import extract_provider_cost_usd, real_session_cost_usd
+
+
+# ── extract_provider_cost_usd — the per-response REAL cost reader ────────────
+
+
+class TestExtractProviderCost:
+    def test_openrouter_usage_cost_attr(self):
+        usage = SimpleNamespace(prompt_tokens=10, completion_tokens=5, cost=0.001234)
+        assert extract_provider_cost_usd(usage) == pytest.approx(0.001234)
+
+    def test_dict_shaped_usage(self):
+        assert extract_provider_cost_usd({"cost": 0.5}) == pytest.approx(0.5)
+
+    def test_reported_zero_is_real_zero(self):
+        # Free-tier models really cost $0 — distinct from "not reported".
+        usage = SimpleNamespace(cost=0)
+        assert extract_provider_cost_usd(usage) == 0.0
+
+    def test_absent_cost_is_none_not_zero(self):
+        usage = SimpleNamespace(prompt_tokens=10, completion_tokens=5)
+        assert extract_provider_cost_usd(usage) is None
+        assert extract_provider_cost_usd({"prompt_tokens": 10}) is None
+
+    def test_none_usage_is_none(self):
+        assert extract_provider_cost_usd(None) is None
+
+    def test_garbage_cost_values_are_none(self):
+        for bad in ("0.01", True, float("nan"), float("inf"), -0.5, [], {}):
+            assert extract_provider_cost_usd(SimpleNamespace(cost=bad)) is None, bad
+
+
+# ── real_session_cost_usd — the session accumulator surface ─────────────────
+
+
+class _FakeAgent:
+    def __init__(self, actual=None, credits_micros=None):
+        self.session_actual_cost_usd = actual
+        self._credits_micros = credits_micros
+
+    def get_credits_spent_micros(self):
+        return self._credits_micros
+
+
+class TestRealSessionCost:
+    def test_nothing_reported_is_none(self):
+        assert real_session_cost_usd(_FakeAgent()) is None
+
+    def test_openrouter_accumulator_only(self):
+        assert real_session_cost_usd(_FakeAgent(actual=0.42)) == pytest.approx(0.42)
+
+    def test_nous_credits_delta_only(self):
+        # 123_400 micros = $0.1234
+        assert real_session_cost_usd(
+            _FakeAgent(credits_micros=123_400)
+        ) == pytest.approx(0.1234)
+
+    def test_both_sources_sum(self):
+        assert real_session_cost_usd(
+            _FakeAgent(actual=0.10, credits_micros=200_000)
+        ) == pytest.approx(0.30)
+
+    def test_negative_credits_delta_clamped(self):
+        # A mid-session top-up makes the delta negative — never show negative cost.
+        assert real_session_cost_usd(_FakeAgent(credits_micros=-50_000)) == 0.0
+
+    def test_agent_without_credits_method(self):
+        agent = SimpleNamespace(session_actual_cost_usd=None)
+        assert real_session_cost_usd(agent) is None
+
+    def test_non_numeric_actual_ignored(self):
+        agent = _FakeAgent()
+        agent.session_actual_cost_usd = "0.42"  # corrupted attr → ignore
+        assert real_session_cost_usd(agent) is None
+
+
+# ── Nous header fixture → real accumulator (full _capture_credits path) ─────
+
+
+def _nous_headers(remaining_micros: int) -> dict:
+    return {
+        "x-nous-credits-version": "1",
+        "x-nous-credits-remaining-micros": str(remaining_micros),
+        "x-nous-credits-remaining-usd": f"{remaining_micros / 1_000_000:.2f}",
+        "x-nous-credits-subscription-micros": str(remaining_micros),
+        "x-nous-credits-subscription-usd": f"{remaining_micros / 1_000_000:.2f}",
+        "x-nous-credits-rollover-micros": "0",
+        "x-nous-credits-purchased-micros": "0",
+        "x-nous-credits-purchased-usd": "0.00",
+        "x-nous-credits-denominator-kind": "none",
+        "x-nous-credits-paid-access": "true",
+        "x-nous-credits-as-of-ms": "1717000000000",
+    }
+
+
+def _bare_nous_agent():
+    """Minimal AIAgent shell exercising the real _capture_credits path."""
+    from run_agent import AIAgent
+
+    agent = object.__new__(AIAgent)
+    agent.provider = "nous"
+    agent._credits_state = None
+    agent._credits_session_start_micros = None
+    agent.notice_callback = None
+    agent.notice_clear_callback = None
+    agent.session_actual_cost_usd = None
+    return agent
+
+
+class TestNousHeaderAccumulation:
+    def test_headers_accumulate_into_real_session_cost(self, monkeypatch):
+        monkeypatch.delenv("HERMES_DEV_CREDITS_FIXTURE", raising=False)
+        agent = _bare_nous_agent()
+
+        # First response latches the session-start balance ($10.00).
+        agent._capture_credits(SimpleNamespace(headers=_nous_headers(10_000_000)))
+        assert real_session_cost_usd(agent) == 0.0  # real zero: headers seen, $0 spent
+
+        # Second response: balance dropped by $0.25 → real reported spend.
+        agent._capture_credits(SimpleNamespace(headers=_nous_headers(9_750_000)))
+        assert real_session_cost_usd(agent) == pytest.approx(0.25)
+
+    def test_no_headers_means_no_cost(self, monkeypatch):
+        monkeypatch.delenv("HERMES_DEV_CREDITS_FIXTURE", raising=False)
+        agent = _bare_nous_agent()
+        agent._capture_credits(SimpleNamespace(headers={"content-type": "application/json"}))
+        assert real_session_cost_usd(agent) is None
+
+
+# ── OpenRouter request param — usage accounting must be requested ────────────
+
+
+class TestOpenRouterUsageParam:
+    def test_profile_extra_body_requests_usage_accounting(self):
+        import importlib.util
+        from pathlib import Path
+
+        from providers import get_provider_profile
+
+        profile = get_provider_profile("openrouter")
+        if profile is None:
+            # Force plugin discovery in minimal test envs.
+            plugin = Path(__file__).resolve().parents[2] / "plugins" / "model-providers" / "openrouter" / "__init__.py"
+            spec = importlib.util.spec_from_file_location("_or_plugin", plugin)
+            mod = importlib.util.module_from_spec(spec)
+            spec.loader.exec_module(mod)
+            profile = mod.openrouter
+
+        body = profile.build_extra_body(session_id="s-1")
+        assert body["usage"] == {"include": True}
+
+    def test_legacy_transport_path_requests_usage_accounting(self):
+        from agent.transports.chat_completions import ChatCompletionsTransport
+
+        transport = ChatCompletionsTransport()
+        kwargs = transport.build_kwargs(
+            model="anthropic/claude-sonnet-4.6",
+            messages=[{"role": "user", "content": "hi"}],
+            tools=None,
+            is_openrouter=True,
+        )
+        assert kwargs["extra_body"]["usage"] == {"include": True}
+
+    def test_non_openrouter_does_not_send_usage_param(self):
+        from agent.transports.chat_completions import ChatCompletionsTransport
+
+        transport = ChatCompletionsTransport()
+        kwargs = transport.build_kwargs(
+            model="deepseek-chat",
+            messages=[{"role": "user", "content": "hi"}],
+            tools=None,
+            is_openrouter=False,
+        )
+        assert "usage" not in (kwargs.get("extra_body") or {})
diff --git a/tests/cli/test_cli_status_bar.py b/tests/cli/test_cli_status_bar.py
index 47a78c57044..5631110d1da 100644
--- a/tests/cli/test_cli_status_bar.py
+++ b/tests/cli/test_cli_status_bar.py
@@ -523,7 +523,7 @@ class TestCLIStatusBar:
 
 
 class TestCLIUsageReport:
-    def test_show_usage_includes_estimated_cost(self, capsys):
+    def test_show_usage_reports_real_provider_cost(self, capsys):
         cli_obj = _attach_agent(
             _make_cli(),
             prompt_tokens=10_230,
@@ -535,20 +535,22 @@ class TestCLIUsageReport:
             compressions=1,
         )
         cli_obj.verbose = False
+        # Provider-reported cost (e.g. OpenRouter usage accounting accumulator).
+        cli_obj.agent.session_actual_cost_usd = 0.0640
 
         cli_obj._show_usage()
         output = capsys.readouterr().out
 
         assert "Model:" in output
-        assert "Cost status:" in output
-        assert "Cost source:" in output
-        assert "Total cost:" in output
+        assert "Cost (provider-reported):" in output
         assert "$" in output
         assert "0.064" in output
         assert "Session duration:" in output
         assert "Compressions:" in output
 
-    def test_show_usage_marks_unknown_pricing(self, capsys):
+    def test_show_usage_unreported_cost_is_not_a_dollar_figure(self, capsys):
+        """No estimation: when the provider reports nothing, /usage must NOT
+        fabricate a dollar amount — not even $0.00."""
         cli_obj = _attach_agent(
             _make_cli(model="local/my-custom-model"),
             prompt_tokens=1_000,
@@ -563,13 +565,15 @@ class TestCLIUsageReport:
         cli_obj._show_usage()
         output = capsys.readouterr().out
 
-        assert "Total cost:" in output
-        assert "n/a" in output
-        assert "Pricing unknown for local/my-custom-model" in output
+        assert "not reported by provider" in output
+        assert "Cost (provider-reported):" not in output
+        assert "$0.00" not in output
 
-    def test_zero_priced_provider_models_stay_unknown(self, capsys):
+    def test_show_usage_never_estimates_even_with_known_pricing(self, capsys):
+        """A model with a pricing-table entry must still show NO cost when the
+        provider reported nothing (hard requirement: real cost only)."""
         cli_obj = _attach_agent(
-            _make_cli(model="glm-5"),
+            _make_cli(model="anthropic/claude-sonnet-4-6"),
             prompt_tokens=1_000,
             completion_tokens=500,
             total_tokens=1_500,
@@ -582,9 +586,8 @@ class TestCLIUsageReport:
         cli_obj._show_usage()
         output = capsys.readouterr().out
 
-        assert "Total cost:" in output
-        assert "n/a" in output
-        assert "Pricing unknown for glm-5" in output
+        assert "not reported by provider" in output
+        assert "Cost (provider-reported):" not in output
 
 
 class TestStatusBarWidthSource:
diff --git a/tests/gateway/test_usage_command.py b/tests/gateway/test_usage_command.py
index 2775e72f9d7..bc2f09743e0 100644
--- a/tests/gateway/test_usage_command.py
+++ b/tests/gateway/test_usage_command.py
@@ -21,11 +21,16 @@ def _make_mock_agent(**overrides):
         "session_output_tokens": 10_000,
         "session_cache_read_tokens": 5_000,
         "session_cache_write_tokens": 2_000,
+        # Real provider-reported cost: None = nothing reported (the default).
+        "session_actual_cost_usd": None,
     }
     defaults.update(overrides)
     for k, v in defaults.items():
         setattr(agent, k, v)
 
+    # No Nous credits headers seen unless a test overrides this.
+    agent.get_credits_spent_micros = MagicMock(return_value=None)
+
     # Rate limit state
     rl = MagicMock()
     rl.has_data = True
@@ -72,13 +77,11 @@ class TestUsageCachedAgent:
 
     @pytest.mark.asyncio
     async def test_cached_agent_shows_detailed_usage(self):
-        agent = _make_mock_agent()
+        agent = _make_mock_agent(session_actual_cost_usd=0.1234)
         runner = _make_runner(SK, cached_agent=agent)
         event = MagicMock()
 
-        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"), \
-             patch("agent.usage_pricing.estimate_usage_cost") as mock_cost:
-            mock_cost.return_value = MagicMock(amount_usd=0.1234, status="estimated")
+        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"):
             result = await runner._handle_usage_command(event)
 
         assert "claude-sonnet-4.6" in result
@@ -99,9 +102,7 @@ class TestUsageCachedAgent:
         runner = _make_runner(SK, agent=running, cached_agent=cached)
         event = MagicMock()
 
-        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"), \
-             patch("agent.usage_pricing.estimate_usage_cost") as mock_cost:
-            mock_cost.return_value = MagicMock(amount_usd=None, status="unknown")
+        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"):
             result = await runner._handle_usage_command(event)
 
         assert "80,000" in result   # running agent's total
@@ -117,9 +118,7 @@ class TestUsageCachedAgent:
         runner._running_agents[SK] = _AGENT_PENDING_SENTINEL
         event = MagicMock()
 
-        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"), \
-             patch("agent.usage_pricing.estimate_usage_cost") as mock_cost:
-            mock_cost.return_value = MagicMock(amount_usd=None, status="unknown")
+        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"):
             result = await runner._handle_usage_command(event)
 
         assert "claude-sonnet-4.6" in result
@@ -153,9 +152,7 @@ class TestUsageCachedAgent:
         runner = _make_runner(SK, cached_agent=agent)
         event = MagicMock()
 
-        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"), \
-             patch("agent.usage_pricing.estimate_usage_cost") as mock_cost:
-            mock_cost.return_value = MagicMock(amount_usd=None, status="unknown")
+        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"):
             result = await runner._handle_usage_command(event)
 
         assert "Cache read" not in result
@@ -168,9 +165,7 @@ class TestUsageCachedAgent:
         runner = _make_runner(SK, cached_agent=agent)
         event = MagicMock()
 
-        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"), \
-             patch("agent.usage_pricing.estimate_usage_cost") as mock_cost:
-            mock_cost.return_value = MagicMock(amount_usd=None, status="included")
+        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"):
             result = await runner._handle_usage_command(event)
 
         assert "Cost: included" in result
@@ -199,9 +194,7 @@ class TestUsageAccountSection:
                 "Session: 85% remaining (15% used)",
             ],
         )
-        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"), \
-             patch("agent.usage_pricing.estimate_usage_cost") as mock_cost:
-            mock_cost.return_value = MagicMock(amount_usd=None, status="included")
+        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"):
             result = await runner._handle_usage_command(event)
 
         assert "📊 **Session Token Usage**" in result
@@ -256,3 +249,42 @@ class TestUsageAccountSection:
         assert account_call["kwargs"]["base_url"] == "https://chatgpt.com/backend-api/codex"
         assert "📊 **Session Info**" in result
         assert "📈 **Account limits**" in result
+
+
+class TestUsageRealCostOnly:
+    """Cost lines are provider-REPORTED only — never estimated, never $0.00."""
+
+    @pytest.mark.asyncio
+    async def test_unreported_cost_renders_no_cost_line(self):
+        agent = _make_mock_agent()  # openrouter, nothing reported
+        runner = _make_runner(SK, cached_agent=agent)
+        event = MagicMock()
+
+        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"):
+            result = await runner._handle_usage_command(event)
+
+        assert "Cost:" not in result
+        assert "$0.00" not in result
+
+    @pytest.mark.asyncio
+    async def test_nous_credits_delta_renders_as_cost(self):
+        agent = _make_mock_agent(provider="nous", model="Hermes-4.1-405B")
+        agent.get_credits_spent_micros = MagicMock(return_value=123_400)
+        runner = _make_runner(SK, cached_agent=agent)
+        event = MagicMock()
+
+        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"):
+            result = await runner._handle_usage_command(event)
+
+        assert "$0.1234" in result
+
+    @pytest.mark.asyncio
+    async def test_openrouter_reported_cost_renders(self):
+        agent = _make_mock_agent(session_actual_cost_usd=0.9876)
+        runner = _make_runner(SK, cached_agent=agent)
+        event = MagicMock()
+
+        with patch("agent.rate_limit_tracker.format_rate_limit_compact", return_value="RPM: 50/60"):
+            result = await runner._handle_usage_command(event)
+
+        assert "$0.9876" in result
diff --git a/tests/providers/test_provider_profiles.py b/tests/providers/test_provider_profiles.py
index 438eddddf99..e44df7fdcd9 100644
--- a/tests/providers/test_provider_profiles.py
+++ b/tests/providers/test_provider_profiles.py
@@ -110,7 +110,9 @@ class TestOpenRouterProfile:
     def test_extra_body_no_prefs(self):
         p = get_provider_profile("openrouter")
         body = p.build_extra_body()
-        assert body == {}
+        # Usage accounting is always requested (real provider-reported cost);
+        # nothing else should appear without prefs/session.
+        assert body == {"usage": {"include": True}}
 
     def test_pareto_min_coding_score_emitted_for_pareto_model(self):
         """min_coding_score → plugins block when model is openrouter/pareto-code."""
diff --git a/tui_gateway/server.py b/tui_gateway/server.py
index 2098f3e20e1..d2acb20e477 100644
--- a/tui_gateway/server.py
+++ b/tui_gateway/server.py
@@ -1709,23 +1709,17 @@ def _get_usage(agent) -> dict:
             usage["context_max"] = ctx_max
             usage["context_percent"] = max(0, min(100, round(ctx_used / ctx_max * 100)))
         usage["compressions"] = getattr(comp, "compression_count", 0) or 0
+    # Cost: provider-REPORTED only (OpenRouter usage.cost accumulator and/or
+    # the Nous x-nous-credits-* header delta). Never estimated. When nothing
+    # was reported `cost_usd` is ABSENT (not $0.00) and the TUI hides its
+    # cost segment — that's the intended UX.
     try:
-        from agent.usage_pricing import CanonicalUsage, estimate_usage_cost
+        from agent.usage_pricing import real_session_cost_usd
 
-        cost = estimate_usage_cost(
-            usage["model"],
-            CanonicalUsage(
-                input_tokens=usage["input"],
-                output_tokens=usage["output"],
-                cache_read_tokens=usage["cache_read"],
-                cache_write_tokens=usage["cache_write"],
-            ),
-            provider=getattr(agent, "provider", None),
-            base_url=getattr(agent, "base_url", None),
-        )
-        usage["cost_status"] = cost.status
-        if cost.amount_usd is not None:
-            usage["cost_usd"] = float(cost.amount_usd)
+        real_cost = real_session_cost_usd(agent)
+        if real_cost is not None:
+            usage["cost_usd"] = real_cost
+            usage["cost_status"] = "actual"
     except Exception:
         pass
     # Dev-only live credits-spent readout (L0 usage-aware-credits). Gated on