feat(cost-model): add GPT, Gemini, Grok prices

tests/pilot/test_cost_model.py

@@ -244,3 +244,39 @@ def test_model_is_within_an_order_of_magnitude_of_the_measurement():
     predicted = cm.tier_usage(modelled, FACTORY, caching=False).total_input
     measured = run["input"]
     assert 0.4 < predicted / measured < 2.5, (predicted, measured)
+
+
+# ---------------------------------------------------------------------------
+# PRICES — the multi-provider table (GPT / Gemini / Grok)
+# ---------------------------------------------------------------------------
+
+
+NEW_KEYS = ("gpt-5", "gpt-5-mini", "gemini-2.5-pro",
+            "gemini-2.5-flash", "grok-4.5", "grok-4.3")
+
+
+def test_prices_contains_new_providers():
+    for k in NEW_KEYS:
+        assert k in cm.PRICES, k
+
+
+def test_cost_matches_published_gpt5():
+    # $1.25 in / $10.00 out / cached $0.125; cache_write = input
+    u = cm.Usage(uncached_input=1_000_000, cached_input=1_000_000,
+                 cache_writes=1_000_000, output=1_000_000)
+    assert abs(cm.cost(u, cm.PRICES["gpt-5"]) - (1.25 + 0.125 + 1.25 + 10.00)) < 1e-9
+
+
+def test_cost_matches_published_gemini_flash():
+    # $0.30 in / $2.50 out / cached $0.03; cache_write = input
+    u = cm.Usage(uncached_input=2_000_000, cached_input=0,
+                 cache_writes=0, output=500_000)
+    expected = 2.00 * 0.30 + 0.50 * 2.50  # $0.60 + $1.25
+    assert abs(cm.cost(u, cm.PRICES["gemini-2.5-flash"]) - expected) < 1e-9
+
+
+def test_cost_matches_published_grok45():
+    # $2.00 in / $6.00 out / cached $0.30; cache_write = input
+    u = cm.Usage(uncached_input=1_000_000, cached_input=1_000_000,
+                 cache_writes=1_000_000, output=1_000_000)
+    assert abs(cm.cost(u, cm.PRICES["grok-4.5"]) - (2.00 + 0.30 + 2.00 + 6.00)) < 1e-9