diff --git a/tests/e2e/CLAUDE.md b/tests/e2e/CLAUDE.md
index a3e5696ef9d..54c143c11d9 100644
--- a/tests/e2e/CLAUDE.md
+++ b/tests/e2e/CLAUDE.md
@@ -21,7 +21,7 @@ Each subdirectory under `tests/e2e/` is one suite, scoped to an endpoint family
 - `load/` - performance-category tests, kept OUT of the main suite: throughput/load SLO tests are a different testing category from functional e2e (variance-driven, historically flaky) and live outside this suite until re-implemented as their own pipeline (LIT-5163); do not add a live load test that runs in the default collection. What lives here: the weekly session-anomaly test (`test_weekly_session_anomaly_e2e.py`, Claude Code-shaped multi-turn sessions against real providers with ceilings on error rate, cache read/write, turn time, and spend; marked `weekly` and deselected unless `E2E_WEEKLY_ANOMALY` is set, driven by `.github/workflows/weekly_load_anomaly.yml`), the Redis chaos test (`test_redis_chaos_e2e.py`, locust load against mock deployments split round robin over `/chat/completions` and `/v1/messages`, one endpoint per simulated user, with `CLIENT PAUSE ALL` on the proxy's Redis mid-run to simulate it being down outright, asserting zero failed requests on every endpoint, budgeting RSS and CPU-per-request as ratios against the same run's healthy phase, and holding p50/p90/p99 latency and log-bytes-per-request to flat ceilings (a ratio cannot bound those two: an open breaker skips Redis instead of waiting on it, so the chaos phase can measure cheaper than baseline while still being far slower than a user should see); needs a proxy booted from `gateway/redis_chaos_ci_config.yml` on the same host with `E2E_PROXY_PID` and `E2E_PROXY_LOG` set, marked `redis_chaos`, deselected unless `E2E_REDIS_CHAOS` is set and excluded from the per-PR selector like the rest of `load/`, driven by `.github/workflows/test-e2e-redis-chaos.yml` and by the Buildkite `e2e-redis-chaos` step in project-releaser, which runs the proxy, Postgres and Valkey co-located with pytest in one pod and sets the opt-in), and markerless harness unit tests for the locust, process-usage, and session-anomaly aggregation logic
 - `other/` - the holding-pen suite for the `other.*` registry cluster with no home of its own yet: the master-key auth gate, JWT auth (access tokens issued by a real Keycloak realm, `idp.py` plus `idp_realm.json`, whose JWKS the proxy's `JWT_PUBLIC_KEY_URL` points at; see CONTRIBUTING.md for the start command and config block), and the process-lifecycle health probes (liveness, public readiness, authenticated readiness diagnostics). Promote a cluster out once it is large/stable enough for its own suite
 - `gateway/` - proxy configuration only (`litellm-config.yml`); no tests
-- `cost_calculation/` - cost accounting against a dedicated proxy whose whole model cost map is the test-owned `tests/e2e/cost_map.json` (loaded via `LITELLM_MODEL_COST_MAP_URL`), with provider calls answered by the scripted-provider sidecar in `scripted_provider.py`; every cost-map entry is a deployment and the cases plus asserted goldens are data in `cases.json` (each exact-spend case carries a literal `expected` cell per map key; `cost_matrix.matrix_data_errors()` runs at collection time so a key absent from the cost map fails the suite's collection loudly), deselected unless `E2E_COST_MAP_STACK` is set, driven by the Buildkite `e2e-cost-calculation` step in project-releaser, which runs a proxy booted from `gateway/cost_calculation_ci_config.yml`, Postgres and the scripted provider co-located with pytest in one pod and sets the opt-in
+- `cost_calculation/` - cost accounting against a dedicated proxy whose whole model cost map is the test-owned `tests/e2e/cost_map.json` (loaded via `LITELLM_MODEL_COST_MAP_URL`), with provider calls answered by the scripted-provider sidecar in `scripted_provider.py`; every cost-map entry is a deployment and the cases plus asserted goldens are data in `cases.json` (each `pricing` case owns (model, cost key) pairs via `owns`/`fallback_for` so every rate key present on each map entry has exactly one owning case, and each carries a literal `expected` cell per map key; `transport` cases list `models` and exercise token counting only; `cost_matrix.matrix_data_errors()` runs at collection time so a key absent from the cost map, an unowned or double-owned (model, rate key) pair, an `owns` key absent on all of the case's models, or a `fallback_for` key present on a case model fails the suite's collection loudly), deselected unless `E2E_COST_MAP_STACK` is set, driven by the Buildkite `e2e-cost-calculation` step in project-releaser, which runs a proxy booted from `gateway/cost_calculation_ci_config.yml` with `MODEL_COST_MAP_MIN_MODEL_COUNT=1` and `MODEL_COST_MAP_MAX_SHRINK_RATIO=0` (the 21-entry test map trips the fetched-cost-map integrity check at the defaults), Postgres and the scripted provider co-located with pytest in one pod and sets the opt-in
 - `claude_code/` - the Claude Code compatibility matrix: drives the real `claude` CLI (and HTTP probes) against a proxy for each feature x provider cell, reporting tagged-union outcomes via the `compat_result` fixture; ships its own driver/builder/publisher plus `_*_unit_tests/` trees. The HTTP probes ride the shared transport (`ProxyClient.count_tokens` / `ProxyClient.messages`); the CLI-driving path stays bespoke
 - `ui/` - the Admin UI browser suite: Playwright in TypeScript, driving the dashboard served by a live proxy on port 4000 (seeded postgres + mock LLM upstream; see its `run_e2e.sh`). It is a self-contained npm package with its own lockfile and does not use the Python harness, pytest markers, or the shared transport; the Python rules in this file (typed models, `Result` unions, basedpyright zero-error gate) do not apply inside it. Its only Python file, `fixtures/mock_llm_server/server.py`, is excluded from the e2e basedpyright gate via the root `pyrightconfig.json`
 
diff --git a/tests/e2e/cost_calculation/cases.json b/tests/e2e/cost_calculation/cases.json
index cda7bc6e67a..d2cdd40aa94 100644
--- a/tests/e2e/cost_calculation/cases.json
+++ b/tests/e2e/cost_calculation/cases.json
@@ -1,468 +1,1837 @@
 {
   "deployments": [
-    {"map_key": "azure/gpt-5.4-mini", "litellm_model": "azure/cc-pinned-deployment", "base_model": "azure/gpt-5.4-mini"}
+    {
+      "map_key": "azure/gpt-5.4-mini",
+      "litellm_model": "azure/cc-pinned-deployment",
+      "base_model": "azure/gpt-5.4-mini"
+    }
   ],
   "cases": [
     {
-      "name": "basic",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
+      "name": "input_text",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
+      "owns": [
+        "input_cost_per_token",
+        "output_cost_per_token"
+      ],
+      "fallback_for": [],
       "expected": {
-        "anthropic.claude-sonnet-5-v1:0": {"spend": 0.034, "input_cost": 0.0204, "output_cost": 0.0136, "prompt_tokens": 120, "completion_tokens": 40},
-        "azure/gpt-5.4-mini": {"spend": 0.032, "input_cost": 0.0192, "output_cost": 0.0128, "prompt_tokens": 120, "completion_tokens": 40},
-        "azure/gpt-5.6": {"spend": 0.03, "input_cost": 0.018, "output_cost": 0.012, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-haiku-4-5": {"spend": 0.014, "input_cost": 0.0084, "output_cost": 0.0056, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-opus-5": {"spend": 0.01, "input_cost": 0.006, "output_cost": 0.004, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-sonnet-5": {"spend": 0.012, "input_cost": 0.0072, "output_cost": 0.0048, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.028, "input_cost": 0.0168, "output_cost": 0.0112, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/kimi-k3": {"spend": 0.024, "input_cost": 0.0144, "output_cost": 0.0096, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.026, "input_cost": 0.0156, "output_cost": 0.0104, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.1-pro-preview": {"spend": 0.042, "input_cost": 0.0252, "output_cost": 0.0168, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.8-flash": {"spend": 0.04, "input_cost": 0.024, "output_cost": 0.016, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.018, "input_cost": 0.0108, "output_cost": 0.0072, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.8-flash": {"spend": 0.016, "input_cost": 0.0096, "output_cost": 0.0064, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.3-codex": {"spend": 0.006, "input_cost": 0.0036, "output_cost": 0.0024, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.4-mini": {"spend": 0.008, "input_cost": 0.0048, "output_cost": 0.0032, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.5-pro": {"spend": 0.004, "input_cost": 0.0024, "output_cost": 0.0016, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.6": {"spend": 0.002, "input_cost": 0.0012, "output_cost": 0.0008, "prompt_tokens": 120, "completion_tokens": 40},
-        "meta.llama4-maverick-17b-instruct-v1:0": {"spend": 0.038, "input_cost": 0.0228, "output_cost": 0.0152, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.02, "input_cost": 0.012, "output_cost": 0.008, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.022, "input_cost": 0.0132, "output_cost": 0.0088, "prompt_tokens": 120, "completion_tokens": 40},
-        "us.anthropic.claude-opus-5-v1:0": {"spend": 0.036, "input_cost": 0.0216, "output_cost": 0.0144, "prompt_tokens": 120, "completion_tokens": 40}
+        "gpt-5.6": {
+          "spend": 0.008988,
+          "input_cost": 0.00322,
+          "output_cost": 0.005768,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.0017976,
+          "input_cost": 0.000644,
+          "output_cost": 0.0011536,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.0092448,
+          "input_cost": 0.003312,
+          "output_cost": 0.0059328,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.00184896,
+          "input_cost": 0.0006624,
+          "output_cost": 0.00118656,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.007704,
+          "input_cost": 0.00276,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.07704,
+          "input_cost": 0.0276,
+          "output_cost": 0.04944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-opus-5": {
+          "spend": 0.0195,
+          "input_cost": 0.0092,
+          "output_cost": 0.0103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-sonnet-5": {
+          "spend": 0.0117,
+          "input_cost": 0.00552,
+          "output_cost": 0.00618,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.0039,
+          "input_cost": 0.00184,
+          "output_cost": 0.00206,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.02145,
+          "input_cost": 0.01012,
+          "output_cost": 0.01133,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "spend": 0.01287,
+          "input_cost": 0.006072,
+          "output_cost": 0.006798,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "meta.llama4-maverick-17b-instruct-v1:0": {
+          "spend": 0.00084124,
+          "input_cost": 0.0004416,
+          "output_cost": 0.00039964,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.008624,
+          "input_cost": 0.00368,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.002156,
+          "input_cost": 0.00092,
+          "output_cost": 0.001236,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.0090552,
+          "input_cost": 0.003864,
+          "output_cost": 0.0051912,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.00224224,
+          "input_cost": 0.0009568,
+          "output_cost": 0.00128544,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/moonshotai/Kimi-K3": {
+          "spend": 0.0035374,
+          "input_cost": 0.002116,
+          "output_cost": 0.0014214,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/zai-org/GLM-5.3": {
+          "spend": 0.0019184,
+          "input_cost": 0.001012,
+          "output_cost": 0.0009064,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/kimi-k3": {
+          "spend": 0.002134,
+          "input_cost": 0.001104,
+          "output_cost": 0.00103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
+          "spend": 0.0005232,
+          "input_cost": 0.000276,
+          "output_cost": 0.0002472,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/qwen3p8-max": {
+          "spend": 0.0031392,
+          "input_cost": 0.001656,
+          "output_cost": 0.0014832,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
       }
     },
     {
       "name": "cache_read",
-      "usage": {"fresh_input_tokens": 100, "cache_read_tokens": 50, "output_tokens": 30},
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 640,
+        "cache_read_tokens": 12288,
+        "output_tokens": 380
+      },
+      "owns": [
+        "cache_read_input_token_cost"
+      ],
+      "fallback_for": [],
       "expected": {
-        "anthropic.claude-sonnet-5-v1:0": {"spend": 0.02805, "input_cost": 0.01785, "output_cost": 0.0102, "prompt_tokens": 150, "completion_tokens": 30},
-        "azure/gpt-5.4-mini": {"spend": 0.0264, "input_cost": 0.0168, "output_cost": 0.0096, "prompt_tokens": 150, "completion_tokens": 30},
-        "azure/gpt-5.6": {"spend": 0.02475, "input_cost": 0.01575, "output_cost": 0.009, "prompt_tokens": 150, "completion_tokens": 30},
-        "claude-haiku-4-5": {"spend": 0.01155, "input_cost": 0.00735, "output_cost": 0.0042, "prompt_tokens": 150, "completion_tokens": 30},
-        "claude-opus-5": {"spend": 0.00825, "input_cost": 0.00525, "output_cost": 0.003, "prompt_tokens": 150, "completion_tokens": 30},
-        "claude-sonnet-5": {"spend": 0.0099, "input_cost": 0.0063, "output_cost": 0.0036, "prompt_tokens": 150, "completion_tokens": 30},
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.0231, "input_cost": 0.0147, "output_cost": 0.0084, "prompt_tokens": 150, "completion_tokens": 30},
-        "fireworks_ai/kimi-k3": {"spend": 0.0198, "input_cost": 0.0126, "output_cost": 0.0072, "prompt_tokens": 150, "completion_tokens": 30},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.02145, "input_cost": 0.01365, "output_cost": 0.0078, "prompt_tokens": 150, "completion_tokens": 30},
-        "gemini-3.1-pro-preview": {"spend": 0.03465, "input_cost": 0.02205, "output_cost": 0.0126, "prompt_tokens": 150, "completion_tokens": 30},
-        "gemini-3.8-flash": {"spend": 0.033, "input_cost": 0.021, "output_cost": 0.012, "prompt_tokens": 150, "completion_tokens": 30},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.01485, "input_cost": 0.00945, "output_cost": 0.0054, "prompt_tokens": 150, "completion_tokens": 30},
-        "gemini/gemini-3.8-flash": {"spend": 0.0132, "input_cost": 0.0084, "output_cost": 0.0048, "prompt_tokens": 150, "completion_tokens": 30},
-        "gpt-5.3-codex": {"spend": 0.00495, "input_cost": 0.00315, "output_cost": 0.0018, "prompt_tokens": 150, "completion_tokens": 30},
-        "gpt-5.4-mini": {"spend": 0.0066, "input_cost": 0.0042, "output_cost": 0.0024, "prompt_tokens": 150, "completion_tokens": 30},
-        "gpt-5.5-pro": {"spend": 0.0033, "input_cost": 0.0021, "output_cost": 0.0012, "prompt_tokens": 150, "completion_tokens": 30},
-        "gpt-5.6": {"spend": 0.00165, "input_cost": 0.00105, "output_cost": 0.0006, "prompt_tokens": 150, "completion_tokens": 30},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.0165, "input_cost": 0.0105, "output_cost": 0.006, "prompt_tokens": 150, "completion_tokens": 30},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.01815, "input_cost": 0.01155, "output_cost": 0.0066, "prompt_tokens": 150, "completion_tokens": 30},
-        "us.anthropic.claude-opus-5-v1:0": {"spend": 0.0297, "input_cost": 0.0189, "output_cost": 0.0108, "prompt_tokens": 150, "completion_tokens": 30}
+        "gpt-5.6": {
+          "spend": 0.0085904,
+          "input_cost": 0.0032704,
+          "output_cost": 0.00532,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.00171808,
+          "input_cost": 0.00065408,
+          "output_cost": 0.001064,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.00883584,
+          "input_cost": 0.00336384,
+          "output_cost": 0.005472,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.001767168,
+          "input_cost": 0.000672768,
+          "output_cost": 0.0010944,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.0073632,
+          "input_cost": 0.0028032,
+          "output_cost": 0.00456,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.073632,
+          "input_cost": 0.028032,
+          "output_cost": 0.0456,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "claude-opus-5": {
+          "spend": 0.018844,
+          "input_cost": 0.009344,
+          "output_cost": 0.0095,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "claude-sonnet-5": {
+          "spend": 0.0113064,
+          "input_cost": 0.0056064,
+          "output_cost": 0.0057,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.0037688,
+          "input_cost": 0.0018688,
+          "output_cost": 0.0019,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.0207284,
+          "input_cost": 0.0102784,
+          "output_cost": 0.01045,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "spend": 0.01243704,
+          "input_cost": 0.00616704,
+          "output_cost": 0.00627,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.0082976,
+          "input_cost": 0.0037376,
+          "output_cost": 0.00456,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.0020744,
+          "input_cost": 0.0009344,
+          "output_cost": 0.00114,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.00871248,
+          "input_cost": 0.00392448,
+          "output_cost": 0.004788,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.002157376,
+          "input_cost": 0.000971776,
+          "output_cost": 0.0011856,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "fireworks_ai/accounts/fireworks/models/kimi-k3": {
+          "spend": 0.00207128,
+          "input_cost": 0.00112128,
+          "output_cost": 0.00095,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "fireworks_ai/accounts/fireworks/models/qwen3p8-max": {
+          "spend": 0.00304992,
+          "input_cost": 0.00168192,
+          "output_cost": 0.001368,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        }
       }
     },
     {
       "name": "cache_write_5m",
-      "usage": {"fresh_input_tokens": 90, "cache_write_5m_tokens": 60, "output_tokens": 30},
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 512,
+        "cache_write_5m_tokens": 9216,
+        "output_tokens": 350
+      },
+      "owns": [
+        "cache_creation_input_token_cost"
+      ],
+      "fallback_for": [],
       "expected": {
-        "anthropic.claude-sonnet-5-v1:0": {"spend": 0.0561, "input_cost": 0.0459, "output_cost": 0.0102, "prompt_tokens": 150, "completion_tokens": 30},
-        "azure/gpt-5.4-mini": {"spend": 0.0528, "input_cost": 0.0432, "output_cost": 0.0096, "prompt_tokens": 150, "completion_tokens": 30},
-        "azure/gpt-5.6": {"spend": 0.0495, "input_cost": 0.0405, "output_cost": 0.009, "prompt_tokens": 150, "completion_tokens": 30},
-        "claude-haiku-4-5": {"spend": 0.0231, "input_cost": 0.0189, "output_cost": 0.0042, "prompt_tokens": 150, "completion_tokens": 30},
-        "claude-opus-5": {"spend": 0.0165, "input_cost": 0.0135, "output_cost": 0.003, "prompt_tokens": 150, "completion_tokens": 30},
-        "claude-sonnet-5": {"spend": 0.0198, "input_cost": 0.0162, "output_cost": 0.0036, "prompt_tokens": 150, "completion_tokens": 30},
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.0408, "input_cost": 0.0324, "output_cost": 0.0084, "prompt_tokens": 150, "completion_tokens": 30},
-        "fireworks_ai/kimi-k3": {"spend": 0.0378, "input_cost": 0.0306, "output_cost": 0.0072, "prompt_tokens": 150, "completion_tokens": 30},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.0393, "input_cost": 0.0315, "output_cost": 0.0078, "prompt_tokens": 150, "completion_tokens": 30},
-        "gpt-5.4-mini": {"spend": 0.0132, "input_cost": 0.0108, "output_cost": 0.0024, "prompt_tokens": 150, "completion_tokens": 30},
-        "gpt-5.6": {"spend": 0.0033, "input_cost": 0.0027, "output_cost": 0.0006, "prompt_tokens": 150, "completion_tokens": 30},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.033, "input_cost": 0.027, "output_cost": 0.006, "prompt_tokens": 150, "completion_tokens": 30},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.0363, "input_cost": 0.0297, "output_cost": 0.0066, "prompt_tokens": 150, "completion_tokens": 30},
-        "us.anthropic.claude-opus-5-v1:0": {"spend": 0.0594, "input_cost": 0.0486, "output_cost": 0.0108, "prompt_tokens": 150, "completion_tokens": 30}
+        "claude-opus-5": {
+          "spend": 0.06891,
+          "input_cost": 0.06016,
+          "output_cost": 0.00875,
+          "prompt_tokens": 9728,
+          "completion_tokens": 350
+        },
+        "claude-sonnet-5": {
+          "spend": 0.041346,
+          "input_cost": 0.036096,
+          "output_cost": 0.00525,
+          "prompt_tokens": 9728,
+          "completion_tokens": 350
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.013782,
+          "input_cost": 0.012032,
+          "output_cost": 0.00175,
+          "prompt_tokens": 9728,
+          "completion_tokens": 350
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.075801,
+          "input_cost": 0.066176,
+          "output_cost": 0.009625,
+          "prompt_tokens": 9728,
+          "completion_tokens": 350
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "spend": 0.0454806,
+          "input_cost": 0.0397056,
+          "output_cost": 0.005775,
+          "prompt_tokens": 9728,
+          "completion_tokens": 350
+        }
       }
     },
     {
       "name": "cache_write_1h",
-      "usage": {"fresh_input_tokens": 90, "cache_write_5m_tokens": 20, "cache_write_1h_tokens": 40, "output_tokens": 30},
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 512,
+        "cache_write_5m_tokens": 2048,
+        "cache_write_1h_tokens": 7168,
+        "output_tokens": 350
+      },
+      "owns": [
+        "cache_creation_input_token_cost_above_1hr"
+      ],
+      "fallback_for": [],
       "expected": {
-        "anthropic.claude-sonnet-5-v1:0": {"spend": 0.0629, "input_cost": 0.0527, "output_cost": 0.0102, "prompt_tokens": 150, "completion_tokens": 30},
-        "azure/gpt-5.4-mini": {"spend": 0.0592, "input_cost": 0.0496, "output_cost": 0.0096, "prompt_tokens": 150, "completion_tokens": 30},
-        "azure/gpt-5.6": {"spend": 0.0555, "input_cost": 0.0465, "output_cost": 0.009, "prompt_tokens": 150, "completion_tokens": 30},
-        "claude-haiku-4-5": {"spend": 0.0259, "input_cost": 0.0217, "output_cost": 0.0042, "prompt_tokens": 150, "completion_tokens": 30},
-        "claude-opus-5": {"spend": 0.0185, "input_cost": 0.0155, "output_cost": 0.003, "prompt_tokens": 150, "completion_tokens": 30},
-        "claude-sonnet-5": {"spend": 0.0222, "input_cost": 0.0186, "output_cost": 0.0036, "prompt_tokens": 150, "completion_tokens": 30},
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.0452, "input_cost": 0.0368, "output_cost": 0.0084, "prompt_tokens": 150, "completion_tokens": 30},
-        "fireworks_ai/kimi-k3": {"spend": 0.0422, "input_cost": 0.035, "output_cost": 0.0072, "prompt_tokens": 150, "completion_tokens": 30},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.0437, "input_cost": 0.0359, "output_cost": 0.0078, "prompt_tokens": 150, "completion_tokens": 30},
-        "gpt-5.4-mini": {"spend": 0.0148, "input_cost": 0.0124, "output_cost": 0.0024, "prompt_tokens": 150, "completion_tokens": 30},
-        "gpt-5.6": {"spend": 0.0037, "input_cost": 0.0031, "output_cost": 0.0006, "prompt_tokens": 150, "completion_tokens": 30},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.037, "input_cost": 0.031, "output_cost": 0.006, "prompt_tokens": 150, "completion_tokens": 30},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.0407, "input_cost": 0.0341, "output_cost": 0.0066, "prompt_tokens": 150, "completion_tokens": 30},
-        "us.anthropic.claude-opus-5-v1:0": {"spend": 0.0666, "input_cost": 0.0558, "output_cost": 0.0108, "prompt_tokens": 150, "completion_tokens": 30}
+        "claude-opus-5": {
+          "spend": 0.09579,
+          "input_cost": 0.08704,
+          "output_cost": 0.00875,
+          "prompt_tokens": 9728,
+          "completion_tokens": 350
+        },
+        "claude-sonnet-5": {
+          "spend": 0.057474,
+          "input_cost": 0.052224,
+          "output_cost": 0.00525,
+          "prompt_tokens": 9728,
+          "completion_tokens": 350
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.019158,
+          "input_cost": 0.017408,
+          "output_cost": 0.00175,
+          "prompt_tokens": 9728,
+          "completion_tokens": 350
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.105369,
+          "input_cost": 0.095744,
+          "output_cost": 0.009625,
+          "prompt_tokens": 9728,
+          "completion_tokens": 350
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "spend": 0.0632214,
+          "input_cost": 0.0574464,
+          "output_cost": 0.005775,
+          "prompt_tokens": 9728,
+          "completion_tokens": 350
+        }
+      }
+    },
+    {
+      "name": "audio_input",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 96,
+        "audio_input_tokens": 1450,
+        "output_tokens": 210
+      },
+      "owns": [
+        "input_cost_per_audio_token"
+      ],
+      "fallback_for": [],
+      "audio_input": true,
+      "expected": {
+        "gpt-5.6": {
+          "spend": 0.061108,
+          "input_cost": 0.058168,
+          "output_cost": 0.00294,
+          "prompt_tokens": 1546,
+          "completion_tokens": 210
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.0151216,
+          "input_cost": 0.0145336,
+          "output_cost": 0.000588,
+          "prompt_tokens": 1546,
+          "completion_tokens": 210
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.0626468,
+          "input_cost": 0.0596228,
+          "output_cost": 0.003024,
+          "prompt_tokens": 1546,
+          "completion_tokens": 210
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.01586436,
+          "input_cost": 0.01525956,
+          "output_cost": 0.0006048,
+          "prompt_tokens": 1546,
+          "completion_tokens": 210
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.006482,
+          "input_cost": 0.003962,
+          "output_cost": 0.00252,
+          "prompt_tokens": 1546,
+          "completion_tokens": 210
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.002128,
+          "input_cost": 0.001498,
+          "output_cost": 0.00063,
+          "prompt_tokens": 1546,
+          "completion_tokens": 210
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.0067626,
+          "input_cost": 0.0041166,
+          "output_cost": 0.002646,
+          "prompt_tokens": 1546,
+          "completion_tokens": 210
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.00221312,
+          "input_cost": 0.00155792,
+          "output_cost": 0.0006552,
+          "prompt_tokens": 1546,
+          "completion_tokens": 210
+        }
+      }
+    },
+    {
+      "name": "audio_output",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 220,
+        "output_tokens": 180,
+        "audio_output_tokens": 1120
+      },
+      "owns": [
+        "output_cost_per_audio_token"
+      ],
+      "fallback_for": [],
+      "audio_output": true,
+      "expected": {
+        "gpt-5.6": {
+          "spend": 0.092505,
+          "input_cost": 0.000385,
+          "output_cost": 0.09212,
+          "prompt_tokens": 220,
+          "completion_tokens": 1300
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.022981,
+          "input_cost": 7.7e-05,
+          "output_cost": 0.022904,
+          "prompt_tokens": 220,
+          "completion_tokens": 1300
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.094828,
+          "input_cost": 0.000396,
+          "output_cost": 0.094432,
+          "prompt_tokens": 220,
+          "completion_tokens": 1300
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.0241176,
+          "input_cost": 7.92e-05,
+          "output_cost": 0.0240384,
+          "prompt_tokens": 220,
+          "completion_tokens": 1300
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.00737,
+          "input_cost": 0.00011,
+          "output_cost": 0.00726,
+          "prompt_tokens": 220,
+          "completion_tokens": 1300
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.0076648,
+          "input_cost": 0.0001144,
+          "output_cost": 0.0075504,
+          "prompt_tokens": 220,
+          "completion_tokens": 1300
+        }
+      }
+    },
+    {
+      "name": "image_input",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 310,
+        "image_input_tokens": 1806,
+        "output_tokens": 240
+      },
+      "owns": [
+        "input_cost_per_image_token"
+      ],
+      "fallback_for": [],
+      "image_input": true,
+      "expected": {
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.0074732,
+          "input_cost": 0.0045932,
+          "output_cost": 0.00288,
+          "prompt_tokens": 2116,
+          "completion_tokens": 240
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.0018683,
+          "input_cost": 0.0011483,
+          "output_cost": 0.00072,
+          "prompt_tokens": 2116,
+          "completion_tokens": 240
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.0078288,
+          "input_cost": 0.0048048,
+          "output_cost": 0.003024,
+          "prompt_tokens": 2116,
+          "completion_tokens": 240
+        }
+      }
+    },
+    {
+      "name": "video_input",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 140,
+        "video_input_tokens": 7920,
+        "output_tokens": 300
+      },
+      "owns": [
+        "input_cost_per_video_token"
+      ],
+      "fallback_for": [],
+      "video_input": true,
+      "expected": {
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.022888,
+          "input_cost": 0.019288,
+          "output_cost": 0.0036,
+          "prompt_tokens": 8060,
+          "completion_tokens": 300
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.005722,
+          "input_cost": 0.004822,
+          "output_cost": 0.0009,
+          "prompt_tokens": 8060,
+          "completion_tokens": 300
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.0059192,
+          "input_cost": 0.0049832,
+          "output_cost": 0.000936,
+          "prompt_tokens": 8060,
+          "completion_tokens": 300
+        }
       }
     },
     {
       "name": "reasoning",
-      "usage": {"fresh_input_tokens": 100, "output_tokens": 30, "reasoning_tokens": 70},
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1240,
+        "output_tokens": 560,
+        "reasoning_tokens": 3480
+      },
+      "owns": [
+        "output_cost_per_reasoning_token"
+      ],
+      "fallback_for": [],
+      "reasoning": true,
       "expected": {
-        "azure/gpt-5.4-mini": {"spend": 0.0816, "input_cost": 0.016, "output_cost": 0.0656, "prompt_tokens": 100, "completion_tokens": 100},
-        "azure/gpt-5.6": {"spend": 0.0765, "input_cost": 0.015, "output_cost": 0.0615, "prompt_tokens": 100, "completion_tokens": 100},
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.0609, "input_cost": 0.014, "output_cost": 0.0469, "prompt_tokens": 100, "completion_tokens": 100},
-        "fireworks_ai/kimi-k3": {"spend": 0.0577, "input_cost": 0.012, "output_cost": 0.0457, "prompt_tokens": 100, "completion_tokens": 100},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.0593, "input_cost": 0.013, "output_cost": 0.0463, "prompt_tokens": 100, "completion_tokens": 100},
-        "gemini-3.1-pro-preview": {"spend": 0.1071, "input_cost": 0.021, "output_cost": 0.0861, "prompt_tokens": 100, "completion_tokens": 100},
-        "gemini-3.8-flash": {"spend": 0.102, "input_cost": 0.02, "output_cost": 0.082, "prompt_tokens": 100, "completion_tokens": 100},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.0459, "input_cost": 0.009, "output_cost": 0.0369, "prompt_tokens": 100, "completion_tokens": 100},
-        "gemini/gemini-3.8-flash": {"spend": 0.0408, "input_cost": 0.008, "output_cost": 0.0328, "prompt_tokens": 100, "completion_tokens": 100},
-        "gpt-5.3-codex": {"spend": 0.0153, "input_cost": 0.003, "output_cost": 0.0123, "prompt_tokens": 100, "completion_tokens": 100},
-        "gpt-5.4-mini": {"spend": 0.0204, "input_cost": 0.004, "output_cost": 0.0164, "prompt_tokens": 100, "completion_tokens": 100},
-        "gpt-5.5-pro": {"spend": 0.0102, "input_cost": 0.002, "output_cost": 0.0082, "prompt_tokens": 100, "completion_tokens": 100},
-        "gpt-5.6": {"spend": 0.0051, "input_cost": 0.001, "output_cost": 0.0041, "prompt_tokens": 100, "completion_tokens": 100},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.051, "input_cost": 0.01, "output_cost": 0.041, "prompt_tokens": 100, "completion_tokens": 100},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.0561, "input_cost": 0.011, "output_cost": 0.0451, "prompt_tokens": 100, "completion_tokens": 100}
+        "gpt-5.6": {
+          "spend": 0.06569,
+          "input_cost": 0.00217,
+          "output_cost": 0.06352,
+          "prompt_tokens": 1240,
+          "completion_tokens": 4040
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.013138,
+          "input_cost": 0.000434,
+          "output_cost": 0.012704,
+          "prompt_tokens": 1240,
+          "completion_tokens": 4040
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.067716,
+          "input_cost": 0.002232,
+          "output_cost": 0.065484,
+          "prompt_tokens": 1240,
+          "completion_tokens": 4040
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.0135432,
+          "input_cost": 0.0004464,
+          "output_cost": 0.0130968,
+          "prompt_tokens": 1240,
+          "completion_tokens": 4040
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.05382,
+          "input_cost": 0.00186,
+          "output_cost": 0.05196,
+          "prompt_tokens": 1240,
+          "completion_tokens": 4040
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.5382,
+          "input_cost": 0.0186,
+          "output_cost": 0.5196,
+          "prompt_tokens": 1240,
+          "completion_tokens": 4040
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.05444,
+          "input_cost": 0.00248,
+          "output_cost": 0.05196,
+          "prompt_tokens": 1240,
+          "completion_tokens": 4040
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.01448,
+          "input_cost": 0.00062,
+          "output_cost": 0.01386,
+          "prompt_tokens": 1240,
+          "completion_tokens": 4040
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.05664,
+          "input_cost": 0.002604,
+          "output_cost": 0.054036,
+          "prompt_tokens": 1240,
+          "completion_tokens": 4040
+        }
       }
     },
     {
-      "name": "audio",
-      "usage": {"fresh_input_tokens": 100, "audio_input_tokens": 25, "output_tokens": 30, "audio_output_tokens": 15},
+      "name": "tiered_input_above_200k",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 204800,
+        "output_tokens": 620
+      },
+      "owns": [
+        "input_cost_per_token_above_200k_tokens",
+        "output_cost_per_token_above_200k_tokens"
+      ],
+      "fallback_for": [],
       "expected": {
-        "azure/gpt-5.4-mini": {"spend": 0.0664, "input_cost": 0.04, "output_cost": 0.0264, "prompt_tokens": 125, "completion_tokens": 45},
-        "azure/gpt-5.6": {"spend": 0.06225, "input_cost": 0.0375, "output_cost": 0.02475, "prompt_tokens": 125, "completion_tokens": 45},
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.05045, "input_cost": 0.0305, "output_cost": 0.01995, "prompt_tokens": 125, "completion_tokens": 45},
-        "fireworks_ai/kimi-k3": {"spend": 0.04725, "input_cost": 0.0285, "output_cost": 0.01875, "prompt_tokens": 125, "completion_tokens": 45},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.04885, "input_cost": 0.0295, "output_cost": 0.01935, "prompt_tokens": 125, "completion_tokens": 45},
-        "gemini-3.1-pro-preview": {"spend": 0.08715, "input_cost": 0.0525, "output_cost": 0.03465, "prompt_tokens": 125, "completion_tokens": 45},
-        "gemini-3.8-flash": {"spend": 0.083, "input_cost": 0.05, "output_cost": 0.033, "prompt_tokens": 125, "completion_tokens": 45},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.03735, "input_cost": 0.0225, "output_cost": 0.01485, "prompt_tokens": 125, "completion_tokens": 45},
-        "gemini/gemini-3.8-flash": {"spend": 0.0332, "input_cost": 0.02, "output_cost": 0.0132, "prompt_tokens": 125, "completion_tokens": 45},
-        "gpt-5.4-mini": {"spend": 0.0166, "input_cost": 0.01, "output_cost": 0.0066, "prompt_tokens": 125, "completion_tokens": 45},
-        "gpt-5.6": {"spend": 0.00415, "input_cost": 0.0025, "output_cost": 0.00165, "prompt_tokens": 125, "completion_tokens": 45},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.0415, "input_cost": 0.025, "output_cost": 0.0165, "prompt_tokens": 125, "completion_tokens": 45},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.04565, "input_cost": 0.0275, "output_cost": 0.01815, "prompt_tokens": 125, "completion_tokens": 45}
+        "claude-opus-5": {
+          "spend": 2.07125,
+          "input_cost": 2.048,
+          "output_cost": 0.02325,
+          "prompt_tokens": 204800,
+          "completion_tokens": 620
+        },
+        "claude-sonnet-5": {
+          "spend": 1.24275,
+          "input_cost": 1.2288,
+          "output_cost": 0.01395,
+          "prompt_tokens": 204800,
+          "completion_tokens": 620
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 2.278375,
+          "input_cost": 2.2528,
+          "output_cost": 0.025575,
+          "prompt_tokens": 204800,
+          "completion_tokens": 620
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.83036,
+          "input_cost": 0.8192,
+          "output_cost": 0.01116,
+          "prompt_tokens": 204800,
+          "completion_tokens": 620
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.871878,
+          "input_cost": 0.86016,
+          "output_cost": 0.011718,
+          "prompt_tokens": 204800,
+          "completion_tokens": 620
+        }
       }
     },
     {
-      "name": "tiered",
-      "usage": {"fresh_input_tokens": 200001, "output_tokens": 30},
+      "name": "tiered_cache_read_above_200k",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 4096,
+        "cache_read_tokens": 201728,
+        "output_tokens": 480
+      },
+      "owns": [
+        "cache_read_input_token_cost_above_200k_tokens"
+      ],
+      "fallback_for": [],
       "expected": {
-        "azure/gpt-5.4-mini": {"spend": 256.04448, "input_cost": 256.00128, "output_cost": 0.0432, "prompt_tokens": 200001, "completion_tokens": 30},
-        "azure/gpt-5.6": {"spend": 240.0417, "input_cost": 240.0012, "output_cost": 0.0405, "prompt_tokens": 200001, "completion_tokens": 30},
-        "gemini-3.1-pro-preview": {"spend": 336.05838, "input_cost": 336.00168, "output_cost": 0.0567, "prompt_tokens": 200001, "completion_tokens": 30},
-        "gemini-3.8-flash": {"spend": 320.0556, "input_cost": 320.0016, "output_cost": 0.054, "prompt_tokens": 200001, "completion_tokens": 30},
-        "gemini/gemini-3.1-pro-preview": {"spend": 144.02502, "input_cost": 144.00072, "output_cost": 0.0243, "prompt_tokens": 200001, "completion_tokens": 30},
-        "gemini/gemini-3.8-flash": {"spend": 128.02224, "input_cost": 128.00064, "output_cost": 0.0216, "prompt_tokens": 200001, "completion_tokens": 30},
-        "gpt-5.3-codex": {"spend": 48.00834, "input_cost": 48.00024, "output_cost": 0.0081, "prompt_tokens": 200001, "completion_tokens": 30},
-        "gpt-5.4-mini": {"spend": 64.01112, "input_cost": 64.00032, "output_cost": 0.0108, "prompt_tokens": 200001, "completion_tokens": 30},
-        "gpt-5.5-pro": {"spend": 32.00556, "input_cost": 32.00016, "output_cost": 0.0054, "prompt_tokens": 200001, "completion_tokens": 30},
-        "gpt-5.6": {"spend": 16.00278, "input_cost": 16.00008, "output_cost": 0.0027, "prompt_tokens": 200001, "completion_tokens": 30},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 160.0278, "input_cost": 160.0008, "output_cost": 0.027, "prompt_tokens": 200001, "completion_tokens": 30},
-        "together_ai/zai-org/GLM-5.3": {"spend": 176.03058, "input_cost": 176.00088, "output_cost": 0.0297, "prompt_tokens": 200001, "completion_tokens": 30}
+        "claude-opus-5": {
+          "spend": 0.260688,
+          "input_cost": 0.242688,
+          "output_cost": 0.018,
+          "prompt_tokens": 205824,
+          "completion_tokens": 480
+        },
+        "claude-sonnet-5": {
+          "spend": 0.1564128,
+          "input_cost": 0.1456128,
+          "output_cost": 0.0108,
+          "prompt_tokens": 205824,
+          "completion_tokens": 480
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.2867568,
+          "input_cost": 0.2669568,
+          "output_cost": 0.0198,
+          "prompt_tokens": 205824,
+          "completion_tokens": 480
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.1057152,
+          "input_cost": 0.0970752,
+          "output_cost": 0.00864,
+          "prompt_tokens": 205824,
+          "completion_tokens": 480
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.11100096,
+          "input_cost": 0.10192896,
+          "output_cost": 0.009072,
+          "prompt_tokens": 205824,
+          "completion_tokens": 480
+        }
+      }
+    },
+    {
+      "name": "tiered_cache_write_above_200k",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 4096,
+        "cache_write_5m_tokens": 200704,
+        "output_tokens": 480
+      },
+      "owns": [
+        "cache_creation_input_token_cost_above_200k_tokens"
+      ],
+      "fallback_for": [],
+      "expected": {
+        "claude-opus-5": {
+          "spend": 2.56776,
+          "input_cost": 2.54976,
+          "output_cost": 0.018,
+          "prompt_tokens": 204800,
+          "completion_tokens": 480
+        },
+        "claude-sonnet-5": {
+          "spend": 1.540656,
+          "input_cost": 1.529856,
+          "output_cost": 0.0108,
+          "prompt_tokens": 204800,
+          "completion_tokens": 480
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 2.824536,
+          "input_cost": 2.804736,
+          "output_cost": 0.0198,
+          "prompt_tokens": 204800,
+          "completion_tokens": 480
+        }
       }
     },
     {
       "name": "service_tier_flex",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
+      "owns": [
+        "input_cost_per_token_flex",
+        "output_cost_per_token_flex"
+      ],
+      "fallback_for": [],
       "service_tier": "flex",
       "expected": {
-        "azure/gpt-5.4-mini": {"spend": 0.0448, "input_cost": 0.0288, "output_cost": 0.016, "prompt_tokens": 120, "completion_tokens": 40},
-        "azure/gpt-5.6": {"spend": 0.042, "input_cost": 0.027, "output_cost": 0.015, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.1-pro-preview": {"spend": 0.0588, "input_cost": 0.0378, "output_cost": 0.021, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.8-flash": {"spend": 0.056, "input_cost": 0.036, "output_cost": 0.02, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.0252, "input_cost": 0.0162, "output_cost": 0.009, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.8-flash": {"spend": 0.0224, "input_cost": 0.0144, "output_cost": 0.008, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.3-codex": {"spend": 0.0084, "input_cost": 0.0054, "output_cost": 0.003, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.4-mini": {"spend": 0.0112, "input_cost": 0.0072, "output_cost": 0.004, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.5-pro": {"spend": 0.0056, "input_cost": 0.0036, "output_cost": 0.002, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.6": {"spend": 0.0028, "input_cost": 0.0018, "output_cost": 0.001, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.028, "input_cost": 0.018, "output_cost": 0.01, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.0308, "input_cost": 0.0198, "output_cost": 0.011, "prompt_tokens": 120, "completion_tokens": 40}
+        "gpt-5.6": {
+          "spend": 0.004494,
+          "input_cost": 0.00161,
+          "output_cost": 0.002884,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.0008988,
+          "input_cost": 0.000322,
+          "output_cost": 0.0005768,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.0046224,
+          "input_cost": 0.001656,
+          "output_cost": 0.0029664,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.00092448,
+          "input_cost": 0.0003312,
+          "output_cost": 0.00059328,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.003852,
+          "input_cost": 0.00138,
+          "output_cost": 0.002472,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.03852,
+          "input_cost": 0.0138,
+          "output_cost": 0.02472,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.010725,
+          "input_cost": 0.00506,
+          "output_cost": 0.005665,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "spend": 0.006435,
+          "input_cost": 0.003036,
+          "output_cost": 0.003399,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.004312,
+          "input_cost": 0.00184,
+          "output_cost": 0.002472,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.001078,
+          "input_cost": 0.00046,
+          "output_cost": 0.000618,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.0045276,
+          "input_cost": 0.001932,
+          "output_cost": 0.0025956,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.00112112,
+          "input_cost": 0.0004784,
+          "output_cost": 0.00064272,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
       }
     },
     {
       "name": "service_tier_priority",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
+      "owns": [
+        "input_cost_per_token_priority",
+        "output_cost_per_token_priority"
+      ],
+      "fallback_for": [],
       "service_tier": "priority",
       "expected": {
-        "azure/gpt-5.4-mini": {"spend": 0.04992, "input_cost": 0.03264, "output_cost": 0.01728, "prompt_tokens": 120, "completion_tokens": 40},
-        "azure/gpt-5.6": {"spend": 0.0468, "input_cost": 0.0306, "output_cost": 0.0162, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.1-pro-preview": {"spend": 0.06552, "input_cost": 0.04284, "output_cost": 0.02268, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.8-flash": {"spend": 0.0624, "input_cost": 0.0408, "output_cost": 0.0216, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.02808, "input_cost": 0.01836, "output_cost": 0.00972, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.8-flash": {"spend": 0.02496, "input_cost": 0.01632, "output_cost": 0.00864, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.3-codex": {"spend": 0.00936, "input_cost": 0.00612, "output_cost": 0.00324, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.4-mini": {"spend": 0.01248, "input_cost": 0.00816, "output_cost": 0.00432, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.5-pro": {"spend": 0.00624, "input_cost": 0.00408, "output_cost": 0.00216, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.6": {"spend": 0.00312, "input_cost": 0.00204, "output_cost": 0.00108, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.0312, "input_cost": 0.0204, "output_cost": 0.0108, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.03432, "input_cost": 0.02244, "output_cost": 0.01188, "prompt_tokens": 120, "completion_tokens": 40}
+        "gpt-5.6": {
+          "spend": 0.017976,
+          "input_cost": 0.00644,
+          "output_cost": 0.011536,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.0035952,
+          "input_cost": 0.001288,
+          "output_cost": 0.0023072,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.0184896,
+          "input_cost": 0.006624,
+          "output_cost": 0.0118656,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.00369792,
+          "input_cost": 0.0013248,
+          "output_cost": 0.00237312,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.015408,
+          "input_cost": 0.00552,
+          "output_cost": 0.009888,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.15408,
+          "input_cost": 0.0552,
+          "output_cost": 0.09888,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-opus-5": {
+          "spend": 0.024375,
+          "input_cost": 0.0115,
+          "output_cost": 0.012875,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-sonnet-5": {
+          "spend": 0.014625,
+          "input_cost": 0.0069,
+          "output_cost": 0.007725,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.004875,
+          "input_cost": 0.0023,
+          "output_cost": 0.002575,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.0268125,
+          "input_cost": 0.01265,
+          "output_cost": 0.0141625,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "spend": 0.0160875,
+          "input_cost": 0.00759,
+          "output_cost": 0.0084975,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.01078,
+          "input_cost": 0.0046,
+          "output_cost": 0.00618,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.002695,
+          "input_cost": 0.00115,
+          "output_cost": 0.001545,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.011319,
+          "input_cost": 0.00483,
+          "output_cost": 0.006489,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.0028028,
+          "input_cost": 0.001196,
+          "output_cost": 0.0016068,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
       }
     },
     {
-      "name": "web_search",
-      "usage": {"fresh_input_tokens": 100, "output_tokens": 30, "web_search_calls": 3},
+      "name": "anthropic_fast_mode",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
+      "owns": [
+        "provider_specific_entry.fast"
+      ],
+      "fallback_for": [],
+      "speed": "fast",
       "expected": {
-        "claude-haiku-4-5": {"spend": 0.0712, "input_cost": 0.007, "output_cost": 0.0042, "prompt_tokens": 100, "completion_tokens": 30},
-        "claude-opus-5": {"spend": 0.068, "input_cost": 0.005, "output_cost": 0.003, "prompt_tokens": 100, "completion_tokens": 30},
-        "claude-sonnet-5": {"spend": 0.0696, "input_cost": 0.006, "output_cost": 0.0036, "prompt_tokens": 100, "completion_tokens": 30},
-        "gemini-3.1-pro-preview": {"spend": 0.0936, "input_cost": 0.021, "output_cost": 0.0126, "prompt_tokens": 100, "completion_tokens": 30},
-        "gemini-3.8-flash": {"spend": 0.092, "input_cost": 0.02, "output_cost": 0.012, "prompt_tokens": 100, "completion_tokens": 30},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.0744, "input_cost": 0.009, "output_cost": 0.0054, "prompt_tokens": 100, "completion_tokens": 30},
-        "gemini/gemini-3.8-flash": {"spend": 0.0728, "input_cost": 0.008, "output_cost": 0.0048, "prompt_tokens": 100, "completion_tokens": 30},
-        "gpt-5.3-codex": {"spend": 0.0648, "input_cost": 0.003, "output_cost": 0.0018, "prompt_tokens": 100, "completion_tokens": 30},
-        "gpt-5.5-pro": {"spend": 0.0632, "input_cost": 0.002, "output_cost": 0.0012, "prompt_tokens": 100, "completion_tokens": 30}
+        "claude-opus-5": {
+          "spend": 0.117,
+          "input_cost": 0.0552,
+          "output_cost": 0.0618,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
       }
     },
     {
-      "name": "web_search_single",
-      "usage": {"fresh_input_tokens": 100, "output_tokens": 30, "web_search_calls": 1},
+      "name": "anthropic_us_inference",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
+      "owns": [
+        "provider_specific_entry.us"
+      ],
+      "fallback_for": [],
+      "inference_geo": "us",
       "expected": {
-        "azure/gpt-5.4-mini": {"spend": 0.0456, "input_cost": 0.016, "output_cost": 0.0096, "prompt_tokens": 100, "completion_tokens": 30},
-        "azure/gpt-5.6": {"spend": 0.044, "input_cost": 0.015, "output_cost": 0.009, "prompt_tokens": 100, "completion_tokens": 30},
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.0424, "input_cost": 0.014, "output_cost": 0.0084, "prompt_tokens": 100, "completion_tokens": 30},
-        "fireworks_ai/kimi-k3": {"spend": 0.0392, "input_cost": 0.012, "output_cost": 0.0072, "prompt_tokens": 100, "completion_tokens": 30},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.0408, "input_cost": 0.013, "output_cost": 0.0078, "prompt_tokens": 100, "completion_tokens": 30},
-        "gpt-5.4-mini": {"spend": 0.0264, "input_cost": 0.004, "output_cost": 0.0024, "prompt_tokens": 100, "completion_tokens": 30},
-        "gpt-5.6": {"spend": 0.0216, "input_cost": 0.001, "output_cost": 0.0006, "prompt_tokens": 100, "completion_tokens": 30},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.036, "input_cost": 0.01, "output_cost": 0.006, "prompt_tokens": 100, "completion_tokens": 30},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.0376, "input_cost": 0.011, "output_cost": 0.0066, "prompt_tokens": 100, "completion_tokens": 30}
+        "claude-opus-5": {
+          "spend": 0.02145,
+          "input_cost": 0.01012,
+          "output_cost": 0.01133,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-sonnet-5": {
+          "spend": 0.01287,
+          "input_cost": 0.006072,
+          "output_cost": 0.006798,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.00429,
+          "input_cost": 0.002024,
+          "output_cost": 0.002266,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
+      }
+    },
+    {
+      "name": "web_search_medium",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412,
+        "web_search_calls": 3
+      },
+      "owns": [
+        "search_context_cost_per_query.search_context_size_medium",
+        "web_search_billing_unit"
+      ],
+      "fallback_for": [],
+      "web_search": "medium",
+      "expected": {
+        "gpt-5.6": {
+          "spend": 0.021488,
+          "input_cost": 0.00322,
+          "output_cost": 0.005768,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.0142976,
+          "input_cost": 0.000644,
+          "output_cost": 0.0011536,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.0217448,
+          "input_cost": 0.003312,
+          "output_cost": 0.0059328,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.01434896,
+          "input_cost": 0.0006624,
+          "output_cost": 0.00118656,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.045204,
+          "input_cost": 0.00276,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.11454,
+          "input_cost": 0.0276,
+          "output_cost": 0.04944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-opus-5": {
+          "spend": 0.0495,
+          "input_cost": 0.0092,
+          "output_cost": 0.0103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-sonnet-5": {
+          "spend": 0.0417,
+          "input_cost": 0.00552,
+          "output_cost": 0.00618,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.0339,
+          "input_cost": 0.00184,
+          "output_cost": 0.00206,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.113624,
+          "input_cost": 0.00368,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.1140552,
+          "input_cost": 0.003864,
+          "output_cost": 0.0051912,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
+      }
+    },
+    {
+      "name": "web_search_low",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412,
+        "web_search_calls": 1
+      },
+      "owns": [
+        "search_context_cost_per_query.search_context_size_low"
+      ],
+      "fallback_for": [],
+      "web_search": "low",
+      "expected": {
+        "gpt-5.6": {
+          "spend": 0.018988,
+          "input_cost": 0.00322,
+          "output_cost": 0.005768,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.0117976,
+          "input_cost": 0.000644,
+          "output_cost": 0.0011536,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.0192448,
+          "input_cost": 0.003312,
+          "output_cost": 0.0059328,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.01184896,
+          "input_cost": 0.0006624,
+          "output_cost": 0.00118656,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.017704,
+          "input_cost": 0.00276,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.08704,
+          "input_cost": 0.0276,
+          "output_cost": 0.04944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
+      }
+    },
+    {
+      "name": "web_search_high",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412,
+        "web_search_calls": 1
+      },
+      "owns": [
+        "search_context_cost_per_query.search_context_size_high"
+      ],
+      "fallback_for": [],
+      "web_search": "high",
+      "expected": {
+        "gpt-5.6": {
+          "spend": 0.023988,
+          "input_cost": 0.00322,
+          "output_cost": 0.005768,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.0167976,
+          "input_cost": 0.000644,
+          "output_cost": 0.0011536,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.0242448,
+          "input_cost": 0.003312,
+          "output_cost": 0.0059328,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.01684896,
+          "input_cost": 0.0006624,
+          "output_cost": 0.00118656,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.022704,
+          "input_cost": 0.00276,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.09204,
+          "input_cost": 0.0276,
+          "output_cost": 0.04944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
+      }
+    },
+    {
+      "name": "web_search_per_prompt",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412,
+        "web_search_calls": 3
+      },
+      "owns": [
+        "search_context_cost_per_query.search_context_size_medium",
+        "web_search_billing_unit"
+      ],
+      "fallback_for": [],
+      "web_search": "medium",
+      "expected": {
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.037156,
+          "input_cost": 0.00092,
+          "output_cost": 0.001236,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.03724224,
+          "input_cost": 0.0009568,
+          "output_cost": 0.00128544,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
+      }
+    },
+    {
+      "name": "google_maps_grounding",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412,
+        "google_maps_calls": 1
+      },
+      "owns": [
+        "google_maps_grounding_cost_per_query"
+      ],
+      "fallback_for": [],
+      "google_maps": true,
+      "expected": {
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.033624,
+          "input_cost": 0.00368,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.027156,
+          "input_cost": 0.00092,
+          "output_cost": 0.001236,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.0340552,
+          "input_cost": 0.003864,
+          "output_cost": 0.0051912,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.02724224,
+          "input_cost": 0.0009568,
+          "output_cost": 0.00128544,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
+      }
+    },
+    {
+      "name": "file_search",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412,
+        "file_search_calls": 1
+      },
+      "owns": [
+        "file_search_cost_per_1k_calls"
+      ],
+      "fallback_for": [],
+      "file_search": true,
+      "expected": {
+        "gpt-5.3-codex": {
+          "spend": 0.010204,
+          "input_cost": 0.00276,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.07954,
+          "input_cost": 0.0276,
+          "output_cost": 0.04944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
+      }
+    },
+    {
+      "name": "fallback_cache_read_at_input_rate",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 640,
+        "cache_read_tokens": 12288,
+        "output_tokens": 380
+      },
+      "owns": [],
+      "fallback_for": [
+        "cache_read_input_token_cost"
+      ],
+      "expected": {
+        "meta.llama4-maverick-17b-instruct-v1:0": {
+          "spend": 0.00347132,
+          "input_cost": 0.00310272,
+          "output_cost": 0.0003686,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        },
+        "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
+          "spend": 0.0021672,
+          "input_cost": 0.0019392,
+          "output_cost": 0.000228,
+          "prompt_tokens": 12928,
+          "completion_tokens": 380
+        }
+      }
+    },
+    {
+      "name": "fallback_cache_write_at_input_rate",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 512,
+        "cache_write_5m_tokens": 9216,
+        "output_tokens": 350
+      },
+      "owns": [],
+      "fallback_for": [
+        "cache_creation_input_token_cost"
+      ],
+      "expected": {
+        "meta.llama4-maverick-17b-instruct-v1:0": {
+          "spend": 0.00267422,
+          "input_cost": 0.00233472,
+          "output_cost": 0.0003395,
+          "prompt_tokens": 9728,
+          "completion_tokens": 350
+        }
+      }
+    },
+    {
+      "name": "fallback_reasoning_at_output_rate",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 1240,
+        "output_tokens": 560,
+        "reasoning_tokens": 3480
+      },
+      "owns": [],
+      "fallback_for": [
+        "output_cost_per_reasoning_token"
+      ],
+      "reasoning": true,
+      "expected": {
+        "gemini-3.8-flash": {
+          "spend": 0.0132496,
+          "input_cost": 0.0006448,
+          "output_cost": 0.0126048,
+          "prompt_tokens": 1240,
+          "completion_tokens": 4040
+        }
+      }
+    },
+    {
+      "name": "fallback_image_tokens_at_input_rate",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 310,
+        "image_input_tokens": 1806,
+        "output_tokens": 240
+      },
+      "owns": [],
+      "fallback_for": [
+        "input_cost_per_image_token"
+      ],
+      "image_input": true,
+      "expected": {
+        "gemini-3.8-flash": {
+          "spend": 0.00184912,
+          "input_cost": 0.00110032,
+          "output_cost": 0.0007488,
+          "prompt_tokens": 2116,
+          "completion_tokens": 240
+        }
+      }
+    },
+    {
+      "name": "fallback_video_tokens_at_input_rate",
+      "family": "pricing",
+      "usage": {
+        "fresh_input_tokens": 140,
+        "video_input_tokens": 7920,
+        "output_tokens": 300
+      },
+      "owns": [],
+      "fallback_for": [
+        "input_cost_per_video_token"
+      ],
+      "video_input": true,
+      "expected": {
+        "gemini-3.1-pro": {
+          "spend": 0.020706,
+          "input_cost": 0.016926,
+          "output_cost": 0.00378,
+          "prompt_tokens": 8060,
+          "completion_tokens": 300
+        }
       }
     },
     {
       "name": "stream",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
       "stream": true,
       "expected": {
-        "anthropic.claude-sonnet-5-v1:0": {"spend": 0.034, "input_cost": 0.0204, "output_cost": 0.0136, "prompt_tokens": 120, "completion_tokens": 40},
-        "azure/gpt-5.4-mini": {"spend": 0.032, "input_cost": 0.0192, "output_cost": 0.0128, "prompt_tokens": 120, "completion_tokens": 40},
-        "azure/gpt-5.6": {"spend": 0.03, "input_cost": 0.018, "output_cost": 0.012, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-haiku-4-5": {"spend": 0.014, "input_cost": 0.0084, "output_cost": 0.0056, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-opus-5": {"spend": 0.01, "input_cost": 0.006, "output_cost": 0.004, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-sonnet-5": {"spend": 0.012, "input_cost": 0.0072, "output_cost": 0.0048, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.028, "input_cost": 0.0168, "output_cost": 0.0112, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/kimi-k3": {"spend": 0.024, "input_cost": 0.0144, "output_cost": 0.0096, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.026, "input_cost": 0.0156, "output_cost": 0.0104, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.1-pro-preview": {"spend": 0.042, "input_cost": 0.0252, "output_cost": 0.0168, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.8-flash": {"spend": 0.04, "input_cost": 0.024, "output_cost": 0.016, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.018, "input_cost": 0.0108, "output_cost": 0.0072, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.8-flash": {"spend": 0.016, "input_cost": 0.0096, "output_cost": 0.0064, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.3-codex": {"spend": 0.006, "input_cost": 0.0036, "output_cost": 0.0024, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.4-mini": {"spend": 0.008, "input_cost": 0.0048, "output_cost": 0.0032, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.5-pro": {"spend": 0.004, "input_cost": 0.0024, "output_cost": 0.0016, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.6": {"spend": 0.002, "input_cost": 0.0012, "output_cost": 0.0008, "prompt_tokens": 120, "completion_tokens": 40},
-        "meta.llama4-maverick-17b-instruct-v1:0": {"spend": 0.038, "input_cost": 0.0228, "output_cost": 0.0152, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.02, "input_cost": 0.012, "output_cost": 0.008, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.022, "input_cost": 0.0132, "output_cost": 0.0088, "prompt_tokens": 120, "completion_tokens": 40},
-        "us.anthropic.claude-opus-5-v1:0": {"spend": 0.036, "input_cost": 0.0216, "output_cost": 0.0144, "prompt_tokens": 120, "completion_tokens": 40}
+        "gpt-5.6": {
+          "spend": 0.008988,
+          "input_cost": 0.00322,
+          "output_cost": 0.005768,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.0017976,
+          "input_cost": 0.000644,
+          "output_cost": 0.0011536,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.0092448,
+          "input_cost": 0.003312,
+          "output_cost": 0.0059328,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.00184896,
+          "input_cost": 0.0006624,
+          "output_cost": 0.00118656,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.007704,
+          "input_cost": 0.00276,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.07704,
+          "input_cost": 0.0276,
+          "output_cost": 0.04944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-opus-5": {
+          "spend": 0.0195,
+          "input_cost": 0.0092,
+          "output_cost": 0.0103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-sonnet-5": {
+          "spend": 0.0117,
+          "input_cost": 0.00552,
+          "output_cost": 0.00618,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.0039,
+          "input_cost": 0.00184,
+          "output_cost": 0.00206,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.02145,
+          "input_cost": 0.01012,
+          "output_cost": 0.01133,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "spend": 0.01287,
+          "input_cost": 0.006072,
+          "output_cost": 0.006798,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "meta.llama4-maverick-17b-instruct-v1:0": {
+          "spend": 0.00084124,
+          "input_cost": 0.0004416,
+          "output_cost": 0.00039964,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.008624,
+          "input_cost": 0.00368,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.002156,
+          "input_cost": 0.00092,
+          "output_cost": 0.001236,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.0090552,
+          "input_cost": 0.003864,
+          "output_cost": 0.0051912,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.00224224,
+          "input_cost": 0.0009568,
+          "output_cost": 0.00128544,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/moonshotai/Kimi-K3": {
+          "spend": 0.0035374,
+          "input_cost": 0.002116,
+          "output_cost": 0.0014214,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/zai-org/GLM-5.3": {
+          "spend": 0.0019184,
+          "input_cost": 0.001012,
+          "output_cost": 0.0009064,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/kimi-k3": {
+          "spend": 0.002134,
+          "input_cost": 0.001104,
+          "output_cost": 0.00103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
+          "spend": 0.0005232,
+          "input_cost": 0.000276,
+          "output_cost": 0.0002472,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/qwen3p8-max": {
+          "spend": 0.0031392,
+          "input_cost": 0.001656,
+          "output_cost": 0.0014832,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
       }
     },
     {
       "name": "stream_no_usage",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
       "stream": true,
       "stream_usage": "absent",
       "exact_spend": false,
       "models": [
-        "anthropic.claude-sonnet-5-v1:0",
-        "azure/gpt-5.4-mini",
+        "gpt-5.6",
+        "gpt-5.4-mini",
         "azure/gpt-5.6",
-        "claude-haiku-4-5",
+        "azure/gpt-5.4-mini",
+        "gpt-5.3-codex",
+        "gpt-5.5-pro",
         "claude-opus-5",
         "claude-sonnet-5",
-        "fireworks_ai/deepseek-v4p1-flash",
-        "fireworks_ai/kimi-k3",
-        "fireworks_ai/qwen3p8-max",
-        "gemini-3.1-pro-preview",
-        "gemini-3.8-flash",
-        "gemini/gemini-3.1-pro-preview",
-        "gemini/gemini-3.8-flash",
-        "gpt-5.3-codex",
-        "gpt-5.4-mini",
-        "gpt-5.5-pro",
-        "gpt-5.6",
+        "claude-haiku-4-5",
+        "us.anthropic.claude-opus-5-v1:0",
+        "anthropic.claude-sonnet-5-v1:0",
         "meta.llama4-maverick-17b-instruct-v1:0",
+        "gemini/gemini-3.1-pro",
+        "gemini/gemini-3.8-flash",
+        "gemini-3.1-pro",
+        "gemini-3.8-flash",
         "together_ai/moonshotai/Kimi-K3",
         "together_ai/zai-org/GLM-5.3",
-        "us.anthropic.claude-opus-5-v1:0"
+        "fireworks_ai/accounts/fireworks/models/kimi-k3",
+        "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash",
+        "fireworks_ai/accounts/fireworks/models/qwen3p8-max"
       ]
     },
-    {
-      "name": "response_model_override",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
-      "response_model_override": true,
-      "expected": {
-        "azure/gpt-5.4-mini": {"spend": 0.032, "input_cost": 0.0192, "output_cost": 0.0128, "prompt_tokens": 120, "completion_tokens": 40},
-        "azure/gpt-5.6": {"spend": 0.032, "input_cost": 0.0192, "output_cost": 0.0128, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-haiku-4-5": {"spend": 0.01, "input_cost": 0.006, "output_cost": 0.004, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-opus-5": {"spend": 0.012, "input_cost": 0.0072, "output_cost": 0.0048, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-sonnet-5": {"spend": 0.014, "input_cost": 0.0084, "output_cost": 0.0056, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.024, "input_cost": 0.0144, "output_cost": 0.0096, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/kimi-k3": {"spend": 0.026, "input_cost": 0.0156, "output_cost": 0.0104, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.028, "input_cost": 0.0168, "output_cost": 0.0112, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.1-pro-preview": {"spend": 0.04, "input_cost": 0.024, "output_cost": 0.016, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.8-flash": {"spend": 0.042, "input_cost": 0.0252, "output_cost": 0.0168, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.016, "input_cost": 0.0096, "output_cost": 0.0064, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.8-flash": {"spend": 0.018, "input_cost": 0.0108, "output_cost": 0.0072, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.3-codex": {"spend": 0.004, "input_cost": 0.0024, "output_cost": 0.0016, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.4-mini": {"spend": 0.002, "input_cost": 0.0012, "output_cost": 0.0008, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.5-pro": {"spend": 0.006, "input_cost": 0.0036, "output_cost": 0.0024, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.6": {"spend": 0.008, "input_cost": 0.0048, "output_cost": 0.0032, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.022, "input_cost": 0.0132, "output_cost": 0.0088, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.02, "input_cost": 0.012, "output_cost": 0.008, "prompt_tokens": 120, "completion_tokens": 40}
-      }
-    },
-    {
-      "name": "stream_response_model_override",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
-      "stream": true,
-      "response_model_override": true,
-      "expected": {
-        "azure/gpt-5.4-mini": {"spend": 0.032, "input_cost": 0.0192, "output_cost": 0.0128, "prompt_tokens": 120, "completion_tokens": 40},
-        "azure/gpt-5.6": {"spend": 0.032, "input_cost": 0.0192, "output_cost": 0.0128, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-haiku-4-5": {"spend": 0.01, "input_cost": 0.006, "output_cost": 0.004, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-opus-5": {"spend": 0.012, "input_cost": 0.0072, "output_cost": 0.0048, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-sonnet-5": {"spend": 0.014, "input_cost": 0.0084, "output_cost": 0.0056, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.024, "input_cost": 0.0144, "output_cost": 0.0096, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/kimi-k3": {"spend": 0.026, "input_cost": 0.0156, "output_cost": 0.0104, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.028, "input_cost": 0.0168, "output_cost": 0.0112, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.1-pro-preview": {"spend": 0.04, "input_cost": 0.024, "output_cost": 0.016, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.8-flash": {"spend": 0.042, "input_cost": 0.0252, "output_cost": 0.0168, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.016, "input_cost": 0.0096, "output_cost": 0.0064, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.8-flash": {"spend": 0.018, "input_cost": 0.0108, "output_cost": 0.0072, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.3-codex": {"spend": 0.004, "input_cost": 0.0024, "output_cost": 0.0016, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.4-mini": {"spend": 0.002, "input_cost": 0.0012, "output_cost": 0.0008, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.5-pro": {"spend": 0.006, "input_cost": 0.0036, "output_cost": 0.0024, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.6": {"spend": 0.008, "input_cost": 0.0048, "output_cost": 0.0032, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.022, "input_cost": 0.0132, "output_cost": 0.0088, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.02, "input_cost": 0.012, "output_cost": 0.008, "prompt_tokens": 120, "completion_tokens": 40}
-      }
-    },
-    {
-      "name": "tool_call",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
-      "tool_call": true,
-      "expected": {
-        "anthropic.claude-sonnet-5-v1:0": {"spend": 0.034, "input_cost": 0.0204, "output_cost": 0.0136, "prompt_tokens": 120, "completion_tokens": 40},
-        "azure/gpt-5.4-mini": {"spend": 0.032, "input_cost": 0.0192, "output_cost": 0.0128, "prompt_tokens": 120, "completion_tokens": 40},
-        "azure/gpt-5.6": {"spend": 0.03, "input_cost": 0.018, "output_cost": 0.012, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-haiku-4-5": {"spend": 0.014, "input_cost": 0.0084, "output_cost": 0.0056, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-opus-5": {"spend": 0.01, "input_cost": 0.006, "output_cost": 0.004, "prompt_tokens": 120, "completion_tokens": 40},
-        "claude-sonnet-5": {"spend": 0.012, "input_cost": 0.0072, "output_cost": 0.0048, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.028, "input_cost": 0.0168, "output_cost": 0.0112, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/kimi-k3": {"spend": 0.024, "input_cost": 0.0144, "output_cost": 0.0096, "prompt_tokens": 120, "completion_tokens": 40},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.026, "input_cost": 0.0156, "output_cost": 0.0104, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.1-pro-preview": {"spend": 0.042, "input_cost": 0.0252, "output_cost": 0.0168, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini-3.8-flash": {"spend": 0.04, "input_cost": 0.024, "output_cost": 0.016, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.018, "input_cost": 0.0108, "output_cost": 0.0072, "prompt_tokens": 120, "completion_tokens": 40},
-        "gemini/gemini-3.8-flash": {"spend": 0.016, "input_cost": 0.0096, "output_cost": 0.0064, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.3-codex": {"spend": 0.006, "input_cost": 0.0036, "output_cost": 0.0024, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.4-mini": {"spend": 0.008, "input_cost": 0.0048, "output_cost": 0.0032, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.5-pro": {"spend": 0.004, "input_cost": 0.0024, "output_cost": 0.0016, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.6": {"spend": 0.002, "input_cost": 0.0012, "output_cost": 0.0008, "prompt_tokens": 120, "completion_tokens": 40},
-        "meta.llama4-maverick-17b-instruct-v1:0": {"spend": 0.038, "input_cost": 0.0228, "output_cost": 0.0152, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.02, "input_cost": 0.012, "output_cost": 0.008, "prompt_tokens": 120, "completion_tokens": 40},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.022, "input_cost": 0.0132, "output_cost": 0.0088, "prompt_tokens": 120, "completion_tokens": 40},
-        "us.anthropic.claude-opus-5-v1:0": {"spend": 0.036, "input_cost": 0.0216, "output_cost": 0.0144, "prompt_tokens": 120, "completion_tokens": 40}
-      }
-    },
-    {
-      "name": "stream_tool_call",
-      "usage": {"fresh_input_tokens": 80, "output_tokens": 25},
-      "stream": true,
-      "tool_call": true,
-      "expected": {
-        "anthropic.claude-sonnet-5-v1:0": {"spend": 0.0221, "input_cost": 0.0136, "output_cost": 0.0085, "prompt_tokens": 80, "completion_tokens": 25},
-        "azure/gpt-5.4-mini": {"spend": 0.0208, "input_cost": 0.0128, "output_cost": 0.008, "prompt_tokens": 80, "completion_tokens": 25},
-        "azure/gpt-5.6": {"spend": 0.0195, "input_cost": 0.012, "output_cost": 0.0075, "prompt_tokens": 80, "completion_tokens": 25},
-        "claude-haiku-4-5": {"spend": 0.0091, "input_cost": 0.0056, "output_cost": 0.0035, "prompt_tokens": 80, "completion_tokens": 25},
-        "claude-opus-5": {"spend": 0.0065, "input_cost": 0.004, "output_cost": 0.0025, "prompt_tokens": 80, "completion_tokens": 25},
-        "claude-sonnet-5": {"spend": 0.0078, "input_cost": 0.0048, "output_cost": 0.003, "prompt_tokens": 80, "completion_tokens": 25},
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.0182, "input_cost": 0.0112, "output_cost": 0.007, "prompt_tokens": 80, "completion_tokens": 25},
-        "fireworks_ai/kimi-k3": {"spend": 0.0156, "input_cost": 0.0096, "output_cost": 0.006, "prompt_tokens": 80, "completion_tokens": 25},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.0169, "input_cost": 0.0104, "output_cost": 0.0065, "prompt_tokens": 80, "completion_tokens": 25},
-        "gemini-3.1-pro-preview": {"spend": 0.0273, "input_cost": 0.0168, "output_cost": 0.0105, "prompt_tokens": 80, "completion_tokens": 25},
-        "gemini-3.8-flash": {"spend": 0.026, "input_cost": 0.016, "output_cost": 0.01, "prompt_tokens": 80, "completion_tokens": 25},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.0117, "input_cost": 0.0072, "output_cost": 0.0045, "prompt_tokens": 80, "completion_tokens": 25},
-        "gemini/gemini-3.8-flash": {"spend": 0.0104, "input_cost": 0.0064, "output_cost": 0.004, "prompt_tokens": 80, "completion_tokens": 25},
-        "gpt-5.3-codex": {"spend": 0.0039, "input_cost": 0.0024, "output_cost": 0.0015, "prompt_tokens": 80, "completion_tokens": 25},
-        "gpt-5.4-mini": {"spend": 0.0052, "input_cost": 0.0032, "output_cost": 0.002, "prompt_tokens": 80, "completion_tokens": 25},
-        "gpt-5.5-pro": {"spend": 0.0026, "input_cost": 0.0016, "output_cost": 0.001, "prompt_tokens": 80, "completion_tokens": 25},
-        "gpt-5.6": {"spend": 0.0013, "input_cost": 0.0008, "output_cost": 0.0005, "prompt_tokens": 80, "completion_tokens": 25},
-        "meta.llama4-maverick-17b-instruct-v1:0": {"spend": 0.0247, "input_cost": 0.0152, "output_cost": 0.0095, "prompt_tokens": 80, "completion_tokens": 25},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.013, "input_cost": 0.008, "output_cost": 0.005, "prompt_tokens": 80, "completion_tokens": 25},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.0143, "input_cost": 0.0088, "output_cost": 0.0055, "prompt_tokens": 80, "completion_tokens": 25},
-        "us.anthropic.claude-opus-5-v1:0": {"spend": 0.0234, "input_cost": 0.0144, "output_cost": 0.009, "prompt_tokens": 80, "completion_tokens": 25}
-      }
-    },
     {
       "name": "stream_no_usage_tool_call",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
       "stream": true,
       "stream_usage": "absent",
       "tool_call": true,
       "exact_spend": false,
       "models": [
-        "anthropic.claude-sonnet-5-v1:0",
-        "azure/gpt-5.4-mini",
+        "gpt-5.6",
+        "gpt-5.4-mini",
         "azure/gpt-5.6",
-        "claude-haiku-4-5",
+        "azure/gpt-5.4-mini",
+        "gpt-5.3-codex",
+        "gpt-5.5-pro",
         "claude-opus-5",
         "claude-sonnet-5",
-        "fireworks_ai/deepseek-v4p1-flash",
-        "fireworks_ai/kimi-k3",
-        "fireworks_ai/qwen3p8-max",
-        "gemini-3.1-pro-preview",
-        "gemini-3.8-flash",
-        "gemini/gemini-3.1-pro-preview",
-        "gemini/gemini-3.8-flash",
-        "gpt-5.3-codex",
-        "gpt-5.4-mini",
-        "gpt-5.5-pro",
-        "gpt-5.6",
+        "claude-haiku-4-5",
+        "us.anthropic.claude-opus-5-v1:0",
+        "anthropic.claude-sonnet-5-v1:0",
         "meta.llama4-maverick-17b-instruct-v1:0",
+        "gemini/gemini-3.1-pro",
+        "gemini/gemini-3.8-flash",
+        "gemini-3.1-pro",
+        "gemini-3.8-flash",
         "together_ai/moonshotai/Kimi-K3",
         "together_ai/zai-org/GLM-5.3",
-        "us.anthropic.claude-opus-5-v1:0"
+        "fireworks_ai/accounts/fireworks/models/kimi-k3",
+        "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash",
+        "fireworks_ai/accounts/fireworks/models/qwen3p8-max"
       ]
     },
     {
       "name": "stream_no_usage_image_input",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
       "stream": true,
       "stream_usage": "absent",
       "image_input": true,
       "exact_spend": false,
       "models": [
-        "anthropic.claude-sonnet-5-v1:0",
-        "azure/gpt-5.4-mini",
+        "gpt-5.6",
+        "gpt-5.4-mini",
         "azure/gpt-5.6",
-        "claude-haiku-4-5",
+        "azure/gpt-5.4-mini",
+        "gpt-5.3-codex",
+        "gpt-5.5-pro",
         "claude-opus-5",
         "claude-sonnet-5",
-        "fireworks_ai/deepseek-v4p1-flash",
-        "fireworks_ai/kimi-k3",
-        "fireworks_ai/qwen3p8-max",
-        "gemini-3.1-pro-preview",
-        "gemini-3.8-flash",
-        "gemini/gemini-3.1-pro-preview",
-        "gemini/gemini-3.8-flash",
-        "gpt-5.3-codex",
-        "gpt-5.4-mini",
-        "gpt-5.5-pro",
-        "gpt-5.6",
+        "claude-haiku-4-5",
+        "us.anthropic.claude-opus-5-v1:0",
+        "anthropic.claude-sonnet-5-v1:0",
         "meta.llama4-maverick-17b-instruct-v1:0",
+        "gemini/gemini-3.1-pro",
+        "gemini/gemini-3.8-flash",
+        "gemini-3.1-pro",
+        "gemini-3.8-flash",
         "together_ai/moonshotai/Kimi-K3",
         "together_ai/zai-org/GLM-5.3",
-        "us.anthropic.claude-opus-5-v1:0"
+        "fireworks_ai/accounts/fireworks/models/kimi-k3",
+        "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash",
+        "fireworks_ai/accounts/fireworks/models/qwen3p8-max"
       ]
     },
     {
       "name": "stream_incomplete",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
       "stream": true,
       "terminal": "incomplete",
       "expected": {
-        "gpt-5.3-codex": {"spend": 0.006, "input_cost": 0.0036, "output_cost": 0.0024, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.5-pro": {"spend": 0.004, "input_cost": 0.0024, "output_cost": 0.0016, "prompt_tokens": 120, "completion_tokens": 40}
+        "gpt-5.3-codex": {
+          "spend": 0.007704,
+          "input_cost": 0.00276,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.07704,
+          "input_cost": 0.0276,
+          "output_cost": 0.04944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
       }
     },
     {
       "name": "stream_no_usage_incomplete",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
       "stream": true,
       "stream_usage": "absent",
       "terminal": "incomplete",
@@ -474,17 +1843,37 @@
     },
     {
       "name": "stream_unvalidated",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
       "stream": true,
       "terminal": "unvalidated",
       "expected": {
-        "gpt-5.3-codex": {"spend": 0.006, "input_cost": 0.0036, "output_cost": 0.0024, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.5-pro": {"spend": 0.004, "input_cost": 0.0024, "output_cost": 0.0016, "prompt_tokens": 120, "completion_tokens": 40}
+        "gpt-5.3-codex": {
+          "spend": 0.007704,
+          "input_cost": 0.00276,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.07704,
+          "input_cost": 0.0276,
+          "output_cost": 0.04944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
       }
     },
     {
       "name": "stream_no_usage_unvalidated",
-      "usage": {"fresh_input_tokens": 120, "output_tokens": 40},
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
       "stream": true,
       "stream_usage": "absent",
       "terminal": "unvalidated",
@@ -496,88 +1885,1008 @@
     },
     {
       "name": "prompt_blocked",
-      "usage": {"fresh_input_tokens": 1000, "output_tokens": 0},
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840
+      },
       "terminal": "prompt_blocked",
-      "response_model_override": true,
       "expected": {
-        "gemini-3.1-pro-preview": {"spend": 0.2, "input_cost": 0.2, "output_cost": 0.0, "prompt_tokens": 1000, "completion_tokens": 0},
-        "gemini-3.8-flash": {"spend": 0.21, "input_cost": 0.21, "output_cost": 0.0, "prompt_tokens": 1000, "completion_tokens": 0},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.08, "input_cost": 0.08, "output_cost": 0.0, "prompt_tokens": 1000, "completion_tokens": 0},
-        "gemini/gemini-3.8-flash": {"spend": 0.09, "input_cost": 0.09, "output_cost": 0.0, "prompt_tokens": 1000, "completion_tokens": 0}
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.00368,
+          "input_cost": 0.00368,
+          "output_cost": 0.0,
+          "prompt_tokens": 1840,
+          "completion_tokens": 0
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.00092,
+          "input_cost": 0.00092,
+          "output_cost": 0.0,
+          "prompt_tokens": 1840,
+          "completion_tokens": 0
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.003864,
+          "input_cost": 0.003864,
+          "output_cost": 0.0,
+          "prompt_tokens": 1840,
+          "completion_tokens": 0
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.0009568,
+          "input_cost": 0.0009568,
+          "output_cost": 0.0,
+          "prompt_tokens": 1840,
+          "completion_tokens": 0
+        }
       }
     },
     {
       "name": "stream_prompt_blocked",
-      "usage": {"fresh_input_tokens": 1000, "output_tokens": 0},
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840
+      },
       "stream": true,
       "terminal": "prompt_blocked",
+      "expected": {
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.00368,
+          "input_cost": 0.00368,
+          "output_cost": 0.0,
+          "prompt_tokens": 1840,
+          "completion_tokens": 0
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.00092,
+          "input_cost": 0.00092,
+          "output_cost": 0.0,
+          "prompt_tokens": 1840,
+          "completion_tokens": 0
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.003864,
+          "input_cost": 0.003864,
+          "output_cost": 0.0,
+          "prompt_tokens": 1840,
+          "completion_tokens": 0
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.0009568,
+          "input_cost": 0.0009568,
+          "output_cost": 0.0,
+          "prompt_tokens": 1840,
+          "completion_tokens": 0
+        }
+      }
+    },
+    {
+      "name": "response_model_override",
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
       "response_model_override": true,
       "expected": {
-        "gemini-3.1-pro-preview": {"spend": 0.2, "input_cost": 0.2, "output_cost": 0.0, "prompt_tokens": 1000, "completion_tokens": 0},
-        "gemini-3.8-flash": {"spend": 0.21, "input_cost": 0.21, "output_cost": 0.0, "prompt_tokens": 1000, "completion_tokens": 0},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.08, "input_cost": 0.08, "output_cost": 0.0, "prompt_tokens": 1000, "completion_tokens": 0},
-        "gemini/gemini-3.8-flash": {"spend": 0.09, "input_cost": 0.09, "output_cost": 0.0, "prompt_tokens": 1000, "completion_tokens": 0}
+        "gpt-5.6": {
+          "spend": 0.0017976,
+          "input_cost": 0.000644,
+          "output_cost": 0.0011536,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.008988,
+          "input_cost": 0.00322,
+          "output_cost": 0.005768,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.00184896,
+          "input_cost": 0.0006624,
+          "output_cost": 0.00118656,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.00184896,
+          "input_cost": 0.0006624,
+          "output_cost": 0.00118656,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.07704,
+          "input_cost": 0.0276,
+          "output_cost": 0.04944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.007704,
+          "input_cost": 0.00276,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-opus-5": {
+          "spend": 0.0117,
+          "input_cost": 0.00552,
+          "output_cost": 0.00618,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-sonnet-5": {
+          "spend": 0.0039,
+          "input_cost": 0.00184,
+          "output_cost": 0.00206,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.0195,
+          "input_cost": 0.0092,
+          "output_cost": 0.0103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.02145,
+          "input_cost": 0.01012,
+          "output_cost": 0.01133,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "spend": 0.01287,
+          "input_cost": 0.006072,
+          "output_cost": 0.006798,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "meta.llama4-maverick-17b-instruct-v1:0": {
+          "spend": 0.00084124,
+          "input_cost": 0.0004416,
+          "output_cost": 0.00039964,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.002156,
+          "input_cost": 0.00092,
+          "output_cost": 0.001236,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.008624,
+          "input_cost": 0.00368,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.00224224,
+          "input_cost": 0.0009568,
+          "output_cost": 0.00128544,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.0090552,
+          "input_cost": 0.003864,
+          "output_cost": 0.0051912,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/moonshotai/Kimi-K3": {
+          "spend": 0.0019184,
+          "input_cost": 0.001012,
+          "output_cost": 0.0009064,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/zai-org/GLM-5.3": {
+          "spend": 0.0035374,
+          "input_cost": 0.002116,
+          "output_cost": 0.0014214,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/kimi-k3": {
+          "spend": 0.0031392,
+          "input_cost": 0.001656,
+          "output_cost": 0.0014832,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
+          "spend": 0.002134,
+          "input_cost": 0.001104,
+          "output_cost": 0.00103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/qwen3p8-max": {
+          "spend": 0.0005232,
+          "input_cost": 0.000276,
+          "output_cost": 0.0002472,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
       }
     },
     {
-      "name": "all_components_chat",
-      "usage": {"fresh_input_tokens": 80, "cache_read_tokens": 40, "cache_write_5m_tokens": 20, "cache_write_1h_tokens": 10, "output_tokens": 25, "reasoning_tokens": 15, "audio_input_tokens": 5, "audio_output_tokens": 3},
-      "expected": {
-        "azure/gpt-5.4-mini": {"spend": 0.0576, "input_cost": 0.03424, "output_cost": 0.02336, "prompt_tokens": 155, "completion_tokens": 43},
-        "azure/gpt-5.6": {"spend": 0.054, "input_cost": 0.0321, "output_cost": 0.0219, "prompt_tokens": 155, "completion_tokens": 43},
-        "gpt-5.4-mini": {"spend": 0.0144, "input_cost": 0.00856, "output_cost": 0.00584, "prompt_tokens": 155, "completion_tokens": 43},
-        "gpt-5.6": {"spend": 0.0036, "input_cost": 0.00214, "output_cost": 0.00146, "prompt_tokens": 155, "completion_tokens": 43},
-        "together_ai/moonshotai/Kimi-K3": {"spend": 0.036, "input_cost": 0.0214, "output_cost": 0.0146, "prompt_tokens": 155, "completion_tokens": 43},
-        "together_ai/zai-org/GLM-5.3": {"spend": 0.0396, "input_cost": 0.02354, "output_cost": 0.01606, "prompt_tokens": 155, "completion_tokens": 43}
-      }
-    },
-    {
-      "name": "all_components_fireworks",
-      "usage": {"fresh_input_tokens": 80, "cache_read_tokens": 40, "output_tokens": 25},
-      "expected": {
-        "fireworks_ai/deepseek-v4p1-flash": {"spend": 0.01876, "input_cost": 0.01176, "output_cost": 0.007, "prompt_tokens": 120, "completion_tokens": 25},
-        "fireworks_ai/kimi-k3": {"spend": 0.01608, "input_cost": 0.01008, "output_cost": 0.006, "prompt_tokens": 120, "completion_tokens": 25},
-        "fireworks_ai/qwen3p8-max": {"spend": 0.01742, "input_cost": 0.01092, "output_cost": 0.0065, "prompt_tokens": 120, "completion_tokens": 25}
-      }
-    },
-    {
-      "name": "all_components_anthropic",
-      "usage": {"fresh_input_tokens": 80, "cache_read_tokens": 40, "cache_write_5m_tokens": 20, "cache_write_1h_tokens": 10, "output_tokens": 25},
-      "expected": {
-        "anthropic.claude-sonnet-5-v1:0": {"spend": 0.03978, "input_cost": 0.03128, "output_cost": 0.0085, "prompt_tokens": 150, "completion_tokens": 25},
-        "claude-haiku-4-5": {"spend": 0.01638, "input_cost": 0.01288, "output_cost": 0.0035, "prompt_tokens": 150, "completion_tokens": 25},
-        "claude-opus-5": {"spend": 0.0117, "input_cost": 0.0092, "output_cost": 0.0025, "prompt_tokens": 150, "completion_tokens": 25},
-        "claude-sonnet-5": {"spend": 0.01404, "input_cost": 0.01104, "output_cost": 0.003, "prompt_tokens": 150, "completion_tokens": 25},
-        "meta.llama4-maverick-17b-instruct-v1:0": {"spend": 0.038, "input_cost": 0.0285, "output_cost": 0.0095, "prompt_tokens": 150, "completion_tokens": 25},
-        "us.anthropic.claude-opus-5-v1:0": {"spend": 0.04212, "input_cost": 0.03312, "output_cost": 0.009, "prompt_tokens": 150, "completion_tokens": 25}
-      }
-    },
-    {
-      "name": "all_components_anthropic_stream",
-      "usage": {"fresh_input_tokens": 80, "cache_read_tokens": 40, "cache_write_5m_tokens": 20, "cache_write_1h_tokens": 10, "output_tokens": 25},
+      "name": "stream_response_model_override",
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
+      "response_model_override": true,
       "stream": true,
       "expected": {
-        "claude-haiku-4-5": {"spend": 0.01638, "input_cost": 0.01288, "output_cost": 0.0035, "prompt_tokens": 150, "completion_tokens": 25},
-        "claude-opus-5": {"spend": 0.0117, "input_cost": 0.0092, "output_cost": 0.0025, "prompt_tokens": 150, "completion_tokens": 25},
-        "claude-sonnet-5": {"spend": 0.01404, "input_cost": 0.01104, "output_cost": 0.003, "prompt_tokens": 150, "completion_tokens": 25}
+        "gpt-5.6": {
+          "spend": 0.0017976,
+          "input_cost": 0.000644,
+          "output_cost": 0.0011536,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.008988,
+          "input_cost": 0.00322,
+          "output_cost": 0.005768,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.00184896,
+          "input_cost": 0.0006624,
+          "output_cost": 0.00118656,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.00184896,
+          "input_cost": 0.0006624,
+          "output_cost": 0.00118656,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.07704,
+          "input_cost": 0.0276,
+          "output_cost": 0.04944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.007704,
+          "input_cost": 0.00276,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-opus-5": {
+          "spend": 0.0117,
+          "input_cost": 0.00552,
+          "output_cost": 0.00618,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-sonnet-5": {
+          "spend": 0.0039,
+          "input_cost": 0.00184,
+          "output_cost": 0.00206,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.0195,
+          "input_cost": 0.0092,
+          "output_cost": 0.0103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.02145,
+          "input_cost": 0.01012,
+          "output_cost": 0.01133,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "spend": 0.01287,
+          "input_cost": 0.006072,
+          "output_cost": 0.006798,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "meta.llama4-maverick-17b-instruct-v1:0": {
+          "spend": 0.00084124,
+          "input_cost": 0.0004416,
+          "output_cost": 0.00039964,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.002156,
+          "input_cost": 0.00092,
+          "output_cost": 0.001236,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.008624,
+          "input_cost": 0.00368,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.00224224,
+          "input_cost": 0.0009568,
+          "output_cost": 0.00128544,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.0090552,
+          "input_cost": 0.003864,
+          "output_cost": 0.0051912,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/moonshotai/Kimi-K3": {
+          "spend": 0.0019184,
+          "input_cost": 0.001012,
+          "output_cost": 0.0009064,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/zai-org/GLM-5.3": {
+          "spend": 0.0035374,
+          "input_cost": 0.002116,
+          "output_cost": 0.0014214,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/kimi-k3": {
+          "spend": 0.0031392,
+          "input_cost": 0.001656,
+          "output_cost": 0.0014832,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
+          "spend": 0.002134,
+          "input_cost": 0.001104,
+          "output_cost": 0.00103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/qwen3p8-max": {
+          "spend": 0.0005232,
+          "input_cost": 0.000276,
+          "output_cost": 0.0002472,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
       }
     },
     {
-      "name": "all_components_gemini",
-      "usage": {"fresh_input_tokens": 80, "cache_read_tokens": 40, "output_tokens": 25, "reasoning_tokens": 15, "audio_input_tokens": 5, "audio_output_tokens": 3},
+      "name": "tool_call",
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
+      "tool_call": true,
       "expected": {
-        "gemini-3.1-pro-preview": {"spend": 0.0546, "input_cost": 0.02394, "output_cost": 0.03066, "prompt_tokens": 125, "completion_tokens": 43},
-        "gemini-3.8-flash": {"spend": 0.052, "input_cost": 0.0228, "output_cost": 0.0292, "prompt_tokens": 125, "completion_tokens": 43},
-        "gemini/gemini-3.1-pro-preview": {"spend": 0.0234, "input_cost": 0.01026, "output_cost": 0.01314, "prompt_tokens": 125, "completion_tokens": 43},
-        "gemini/gemini-3.8-flash": {"spend": 0.0208, "input_cost": 0.00912, "output_cost": 0.01168, "prompt_tokens": 125, "completion_tokens": 43}
+        "gpt-5.6": {
+          "spend": 0.008988,
+          "input_cost": 0.00322,
+          "output_cost": 0.005768,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.0017976,
+          "input_cost": 0.000644,
+          "output_cost": 0.0011536,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.0092448,
+          "input_cost": 0.003312,
+          "output_cost": 0.0059328,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.00184896,
+          "input_cost": 0.0006624,
+          "output_cost": 0.00118656,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.007704,
+          "input_cost": 0.00276,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.07704,
+          "input_cost": 0.0276,
+          "output_cost": 0.04944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-opus-5": {
+          "spend": 0.0195,
+          "input_cost": 0.0092,
+          "output_cost": 0.0103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-sonnet-5": {
+          "spend": 0.0117,
+          "input_cost": 0.00552,
+          "output_cost": 0.00618,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.0039,
+          "input_cost": 0.00184,
+          "output_cost": 0.00206,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.02145,
+          "input_cost": 0.01012,
+          "output_cost": 0.01133,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "spend": 0.01287,
+          "input_cost": 0.006072,
+          "output_cost": 0.006798,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "meta.llama4-maverick-17b-instruct-v1:0": {
+          "spend": 0.00084124,
+          "input_cost": 0.0004416,
+          "output_cost": 0.00039964,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.008624,
+          "input_cost": 0.00368,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.002156,
+          "input_cost": 0.00092,
+          "output_cost": 0.001236,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.0090552,
+          "input_cost": 0.003864,
+          "output_cost": 0.0051912,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.00224224,
+          "input_cost": 0.0009568,
+          "output_cost": 0.00128544,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/moonshotai/Kimi-K3": {
+          "spend": 0.0035374,
+          "input_cost": 0.002116,
+          "output_cost": 0.0014214,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/zai-org/GLM-5.3": {
+          "spend": 0.0019184,
+          "input_cost": 0.001012,
+          "output_cost": 0.0009064,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/kimi-k3": {
+          "spend": 0.002134,
+          "input_cost": 0.001104,
+          "output_cost": 0.00103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
+          "spend": 0.0005232,
+          "input_cost": 0.000276,
+          "output_cost": 0.0002472,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/qwen3p8-max": {
+          "spend": 0.0031392,
+          "input_cost": 0.001656,
+          "output_cost": 0.0014832,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
       }
     },
     {
-      "name": "all_components_responses",
-      "usage": {"fresh_input_tokens": 80, "cache_read_tokens": 40, "output_tokens": 25, "reasoning_tokens": 15},
+      "name": "stream_tool_call",
+      "family": "transport",
+      "usage": {
+        "fresh_input_tokens": 1840,
+        "output_tokens": 412
+      },
+      "stream": true,
+      "tool_call": true,
       "expected": {
-        "gpt-5.3-codex": {"spend": 0.00627, "input_cost": 0.00252, "output_cost": 0.00375, "prompt_tokens": 120, "completion_tokens": 40},
-        "gpt-5.5-pro": {"spend": 0.00418, "input_cost": 0.00168, "output_cost": 0.0025, "prompt_tokens": 120, "completion_tokens": 40}
+        "gpt-5.6": {
+          "spend": 0.008988,
+          "input_cost": 0.00322,
+          "output_cost": 0.005768,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.0017976,
+          "input_cost": 0.000644,
+          "output_cost": 0.0011536,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.0092448,
+          "input_cost": 0.003312,
+          "output_cost": 0.0059328,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.00184896,
+          "input_cost": 0.0006624,
+          "output_cost": 0.00118656,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.007704,
+          "input_cost": 0.00276,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.07704,
+          "input_cost": 0.0276,
+          "output_cost": 0.04944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-opus-5": {
+          "spend": 0.0195,
+          "input_cost": 0.0092,
+          "output_cost": 0.0103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-sonnet-5": {
+          "spend": 0.0117,
+          "input_cost": 0.00552,
+          "output_cost": 0.00618,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.0039,
+          "input_cost": 0.00184,
+          "output_cost": 0.00206,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.02145,
+          "input_cost": 0.01012,
+          "output_cost": 0.01133,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "spend": 0.01287,
+          "input_cost": 0.006072,
+          "output_cost": 0.006798,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "meta.llama4-maverick-17b-instruct-v1:0": {
+          "spend": 0.00084124,
+          "input_cost": 0.0004416,
+          "output_cost": 0.00039964,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.008624,
+          "input_cost": 0.00368,
+          "output_cost": 0.004944,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.002156,
+          "input_cost": 0.00092,
+          "output_cost": 0.001236,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.0090552,
+          "input_cost": 0.003864,
+          "output_cost": 0.0051912,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.00224224,
+          "input_cost": 0.0009568,
+          "output_cost": 0.00128544,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/moonshotai/Kimi-K3": {
+          "spend": 0.0035374,
+          "input_cost": 0.002116,
+          "output_cost": 0.0014214,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/zai-org/GLM-5.3": {
+          "spend": 0.0019184,
+          "input_cost": 0.001012,
+          "output_cost": 0.0009064,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/kimi-k3": {
+          "spend": 0.002134,
+          "input_cost": 0.001104,
+          "output_cost": 0.00103,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
+          "spend": 0.0005232,
+          "input_cost": 0.000276,
+          "output_cost": 0.0002472,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/qwen3p8-max": {
+          "spend": 0.0031392,
+          "input_cost": 0.001656,
+          "output_cost": 0.0014832,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        }
+      }
+    },
+    {
+      "name": "stream_full_usage",
+      "family": "transport",
+      "usage": {},
+      "stream": true,
+      "usage_by_model": {
+        "gpt-5.6": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "reasoning_tokens": 900,
+          "audio_input_tokens": 330,
+          "audio_output_tokens": 280
+        },
+        "gpt-5.4-mini": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "reasoning_tokens": 900,
+          "audio_input_tokens": 330,
+          "audio_output_tokens": 280
+        },
+        "azure/gpt-5.6": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "reasoning_tokens": 900,
+          "audio_input_tokens": 330,
+          "audio_output_tokens": 280
+        },
+        "azure/gpt-5.4-mini": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "reasoning_tokens": 900,
+          "audio_input_tokens": 330,
+          "audio_output_tokens": 280
+        },
+        "gpt-5.3-codex": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "reasoning_tokens": 900
+        },
+        "gpt-5.5-pro": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "reasoning_tokens": 900
+        },
+        "claude-opus-5": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "cache_write_5m_tokens": 2048,
+          "cache_write_1h_tokens": 1024
+        },
+        "claude-sonnet-5": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "cache_write_5m_tokens": 2048,
+          "cache_write_1h_tokens": 1024
+        },
+        "claude-haiku-4-5": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "cache_write_5m_tokens": 2048,
+          "cache_write_1h_tokens": 1024
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "cache_write_5m_tokens": 2048,
+          "cache_write_1h_tokens": 1024
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "cache_write_5m_tokens": 2048,
+          "cache_write_1h_tokens": 1024
+        },
+        "meta.llama4-maverick-17b-instruct-v1:0": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "cache_write_5m_tokens": 2048,
+          "cache_write_1h_tokens": 1024
+        },
+        "gemini/gemini-3.1-pro": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "reasoning_tokens": 900,
+          "audio_input_tokens": 330
+        },
+        "gemini/gemini-3.8-flash": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "reasoning_tokens": 900,
+          "audio_input_tokens": 330,
+          "audio_output_tokens": 280
+        },
+        "gemini-3.1-pro": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "reasoning_tokens": 900,
+          "audio_input_tokens": 330
+        },
+        "gemini-3.8-flash": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144,
+          "reasoning_tokens": 900,
+          "audio_input_tokens": 330,
+          "audio_output_tokens": 280
+        },
+        "together_ai/moonshotai/Kimi-K3": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412
+        },
+        "together_ai/zai-org/GLM-5.3": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/kimi-k3": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144
+        },
+        "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/qwen3p8-max": {
+          "fresh_input_tokens": 1840,
+          "output_tokens": 412,
+          "cache_read_tokens": 6144
+        }
+      },
+      "expected": {
+        "gpt-5.6": {
+          "spend": 0.0600632,
+          "input_cost": 0.0174952,
+          "output_cost": 0.042568,
+          "prompt_tokens": 8314,
+          "completion_tokens": 1592
+        },
+        "gpt-5.4-mini": {
+          "spend": 0.01379264,
+          "input_cost": 0.00415904,
+          "output_cost": 0.0096336,
+          "prompt_tokens": 8314,
+          "completion_tokens": 1592
+        },
+        "azure/gpt-5.6": {
+          "spend": 0.06169072,
+          "input_cost": 0.01794792,
+          "output_cost": 0.0437428,
+          "prompt_tokens": 8314,
+          "completion_tokens": 1592
+        },
+        "azure/gpt-5.4-mini": {
+          "spend": 0.014385144,
+          "input_cost": 0.004348584,
+          "output_cost": 0.01003656,
+          "prompt_tokens": 8314,
+          "completion_tokens": 1592
+        },
+        "gpt-5.3-codex": {
+          "spend": 0.0203256,
+          "input_cost": 0.0036816,
+          "output_cost": 0.016644,
+          "prompt_tokens": 7984,
+          "completion_tokens": 1312
+        },
+        "gpt-5.5-pro": {
+          "spend": 0.203256,
+          "input_cost": 0.036816,
+          "output_cost": 0.16644,
+          "prompt_tokens": 7984,
+          "completion_tokens": 1312
+        },
+        "claude-opus-5": {
+          "spend": 0.045612,
+          "input_cost": 0.035312,
+          "output_cost": 0.0103,
+          "prompt_tokens": 11056,
+          "completion_tokens": 412
+        },
+        "claude-sonnet-5": {
+          "spend": 0.0273672,
+          "input_cost": 0.0211872,
+          "output_cost": 0.00618,
+          "prompt_tokens": 11056,
+          "completion_tokens": 412
+        },
+        "claude-haiku-4-5": {
+          "spend": 0.0091224,
+          "input_cost": 0.0070624,
+          "output_cost": 0.00206,
+          "prompt_tokens": 11056,
+          "completion_tokens": 412
+        },
+        "us.anthropic.claude-opus-5-v1:0": {
+          "spend": 0.0501732,
+          "input_cost": 0.0388432,
+          "output_cost": 0.01133,
+          "prompt_tokens": 11056,
+          "completion_tokens": 412
+        },
+        "anthropic.claude-sonnet-5-v1:0": {
+          "spend": 0.03010392,
+          "input_cost": 0.02330592,
+          "output_cost": 0.006798,
+          "prompt_tokens": 11056,
+          "completion_tokens": 412
+        },
+        "meta.llama4-maverick-17b-instruct-v1:0": {
+          "spend": 0.00305308,
+          "input_cost": 0.00265344,
+          "output_cost": 0.00039964,
+          "prompt_tokens": 11056,
+          "completion_tokens": 412
+        },
+        "gemini/gemini-3.1-pro": {
+          "spend": 0.0224108,
+          "input_cost": 0.0057668,
+          "output_cost": 0.016644,
+          "prompt_tokens": 8314,
+          "completion_tokens": 1312
+        },
+        "gemini/gemini-3.8-flash": {
+          "spend": 0.0076232,
+          "input_cost": 0.0015572,
+          "output_cost": 0.006066,
+          "prompt_tokens": 8314,
+          "completion_tokens": 1592
+        },
+        "gemini-3.1-pro": {
+          "spend": 0.02338644,
+          "input_cost": 0.00604524,
+          "output_cost": 0.0173412,
+          "prompt_tokens": 8314,
+          "completion_tokens": 1312
+        },
+        "gemini-3.8-flash": {
+          "spend": 0.007460128,
+          "input_cost": 0.001619488,
+          "output_cost": 0.00584064,
+          "prompt_tokens": 8314,
+          "completion_tokens": 1592
+        },
+        "together_ai/moonshotai/Kimi-K3": {
+          "spend": 0.0035374,
+          "input_cost": 0.002116,
+          "output_cost": 0.0014214,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "together_ai/zai-org/GLM-5.3": {
+          "spend": 0.0019184,
+          "input_cost": 0.001012,
+          "output_cost": 0.0009064,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/kimi-k3": {
+          "spend": 0.00250264,
+          "input_cost": 0.00147264,
+          "output_cost": 0.00103,
+          "prompt_tokens": 7984,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
+          "spend": 0.0005232,
+          "input_cost": 0.000276,
+          "output_cost": 0.0002472,
+          "prompt_tokens": 1840,
+          "completion_tokens": 412
+        },
+        "fireworks_ai/accounts/fireworks/models/qwen3p8-max": {
+          "spend": 0.00369216,
+          "input_cost": 0.00220896,
+          "output_cost": 0.0014832,
+          "prompt_tokens": 7984,
+          "completion_tokens": 412
+        }
       }
     }
   ]
diff --git a/tests/e2e/cost_calculation/conftest.py b/tests/e2e/cost_calculation/conftest.py
index 1473edb119b..e735de40027 100644
--- a/tests/e2e/cost_calculation/conftest.py
+++ b/tests/e2e/cost_calculation/conftest.py
@@ -7,6 +7,11 @@ deployment under test, and the request shapes plus asserted goldens live in
 scripted-provider sidecar (``scripted_provider.py``), registered per scenario
 over its control API.
 
+The proxy must also run with ``MODEL_COST_MAP_MIN_MODEL_COUNT=1`` and
+``MODEL_COST_MAP_MAX_SHRINK_RATIO=0``: the 21-entry test map trips the
+fetched-cost-map integrity check (too few models, large shrink versus the
+bundled map) at those env vars' defaults.
+
 Deselected unless E2E_COST_MAP_STACK is set (marker `cost_map_stack`).
 """
 
diff --git a/tests/e2e/cost_calculation/cost_matrix.py b/tests/e2e/cost_calculation/cost_matrix.py
index 7999d827060..5e652421182 100644
--- a/tests/e2e/cost_calculation/cost_matrix.py
+++ b/tests/e2e/cost_calculation/cost_matrix.py
@@ -13,9 +13,12 @@ Two data files drive the suite; nothing in Python lists models or cases:
 from __future__ import annotations
 
 import base64
+import io
 import json
+import math
 import random
 import struct
+import wave
 import zlib
 from collections.abc import Mapping
 from dataclasses import dataclass
@@ -37,22 +40,41 @@ class SearchContextCostPerQuery(BaseModel):
     search_context_size_high: float | None = None
 
 
+class ProviderSpecificEntry(BaseModel):
+    """Provider-specific key rates, keyed by the named suffix litellm looks up
+    (``fast`` for Anthropic fast mode, ``us`` for US inference geography)."""
+
+    model_config = ConfigDict(frozen=True)
+
+    fast: float | None = None
+    us: float | None = None
+
+
 class CostMapEntry(BaseModel):
     """The pricing fields of a cost-map entry the matrix reads. Shaped like a
-    ``model_prices_and_context_window.json`` entry; unmodelled keys are ignored."""
+    ``model_prices_and_context_window.json`` entry; the file is test-owned so
+    undeclared keys are forbidden rather than ignored."""
 
-    model_config = ConfigDict(frozen=True, extra="ignore")
+    model_config = ConfigDict(frozen=True, extra="forbid")
 
     litellm_provider: str
     mode: str
+    max_tokens: int | None = None
+    max_input_tokens: int | None = None
+    max_output_tokens: int | None = None
+    supports_function_calling: bool | None = None
     input_cost_per_token: float | None = None
     output_cost_per_token: float | None = None
     cache_read_input_token_cost: float | None = None
     cache_creation_input_token_cost: float | None = None
     cache_creation_input_token_cost_above_1hr: float | None = None
+    cache_read_input_token_cost_above_200k_tokens: float | None = None
+    cache_creation_input_token_cost_above_200k_tokens: float | None = None
     output_cost_per_reasoning_token: float | None = None
     input_cost_per_audio_token: float | None = None
     output_cost_per_audio_token: float | None = None
+    input_cost_per_image_token: float | None = None
+    input_cost_per_video_token: float | None = None
     input_cost_per_token_above_200k_tokens: float | None = None
     output_cost_per_token_above_200k_tokens: float | None = None
     input_cost_per_token_flex: float | None = None
@@ -61,6 +83,70 @@ class CostMapEntry(BaseModel):
     output_cost_per_token_priority: float | None = None
     search_context_cost_per_query: SearchContextCostPerQuery | None = None
     web_search_billing_unit: str | None = None
+    google_maps_grounding_cost_per_query: float | None = None
+    file_search_cost_per_1k_calls: float | None = None
+    provider_specific_entry: ProviderSpecificEntry | None = None
+
+
+_METADATA_FIELDS: Final = frozenset(
+    {
+        "litellm_provider",
+        "mode",
+        "max_tokens",
+        "max_input_tokens",
+        "max_output_tokens",
+        "supports_function_calling",
+    }
+)
+_CONTAINER_FIELDS: Final = frozenset({"search_context_cost_per_query", "provider_specific_entry"})
+
+
+def _submodel_rate_keys(
+    field: str, sub: SearchContextCostPerQuery | ProviderSpecificEntry | None
+) -> tuple[str, ...]:
+    if sub is None:
+        return ()
+    return tuple(
+        f"{field}.{name}"
+        for name in type(sub).model_fields
+        if getattr(sub, name) is not None
+    )
+
+
+def _entry_rate_keys(entry: CostMapEntry) -> frozenset[str]:
+    """Every cost key an entry carries, with container subfields expanded to
+    dotted names (``search_context_cost_per_query.search_context_size_low``).
+    ``web_search_billing_unit`` counts as a rate key whenever present,
+    for both ``per_query`` and ``per_prompt`` values."""
+    plain: Final = frozenset(
+        name
+        for name in CostMapEntry.model_fields
+        if name not in _METADATA_FIELDS
+        and name not in _CONTAINER_FIELDS
+        and getattr(entry, name) is not None
+    )
+    return (
+        plain
+        | frozenset(
+            _submodel_rate_keys("search_context_cost_per_query", entry.search_context_cost_per_query)
+        )
+        | frozenset(_submodel_rate_keys("provider_specific_entry", entry.provider_specific_entry))
+    )
+
+
+def _entry_has_rate_key(entry: CostMapEntry, rate_key: str) -> bool:
+    outer, _, inner = rate_key.partition(".")
+    if outer == "search_context_cost_per_query":
+        return f"{outer}.{inner}" in _submodel_rate_keys(outer, entry.search_context_cost_per_query)
+    if outer == "provider_specific_entry":
+        return f"{outer}.{inner}" in _submodel_rate_keys(outer, entry.provider_specific_entry)
+    value: Final[object] = getattr(entry, outer, None)
+    return value is not None
+
+
+SERVICE_TIER_REQUEST_WIRES: Final = frozenset(
+    {"openai_chat", "azure_chat", "openai_responses", "bedrock_converse"}
+)
 
 
 COST_MAP_ADAPTER: Final = TypeAdapter(dict[str, CostMapEntry])
@@ -94,22 +180,42 @@ class ExpectedCell(BaseModel):
 
 
 class Case(BaseModel):
-    """One request/response shape from cases.json. An exact-spend case names
-    its models implicitly by carrying one ``expected`` golden per map key; a
-    recount case (``exact_spend=False``) names them in ``models`` instead."""
+    """One request/response shape from cases.json.
+
+    ``family`` splits the matrix: ``pricing`` cases own cost keys (``owns``,
+    dotted subfield names allowed) or declare which keys they deliberately
+    leave absent (``fallback_for``) so every cost key in the map has exactly
+    one owning case; ``transport`` cases exercise counting/transport only and
+    run wherever they list membership. An exact-spend case names its models
+    implicitly by carrying one ``expected`` golden per map key; a recount
+    case (``exact_spend=False``) names them in ``models`` instead. The
+    feature flags drive request realism in ``_chat_body``."""
 
     model_config = ConfigDict(frozen=True)
 
     name: str
+    family: Literal["pricing", "transport"]
     usage: ScriptedUsage
+    usage_by_model: Mapping[str, ScriptedUsage] = Field(default_factory=lambda: MappingProxyType({}))
     stream: bool = False
     stream_usage: Literal["final_chunk", "absent"] = "final_chunk"
     service_tier: Literal["flex", "priority"] | None = None
+    speed: Literal["fast"] | None = None
+    inference_geo: Literal["us"] | None = None
     response_model_override: bool = False
     exact_spend: bool = True
     tool_call: bool = False
     image_input: bool = False
+    audio_input: bool = False
+    audio_output: bool = False
+    video_input: bool = False
+    reasoning: bool = False
+    web_search: Literal["low", "medium", "high"] | None = None
+    google_maps: bool = False
+    file_search: bool = False
     terminal: Literal["completed", "incomplete", "unvalidated", "prompt_blocked"] = "completed"
+    owns: tuple[str, ...] = ()
+    fallback_for: tuple[str, ...] = ()
     expected: Mapping[str, ExpectedCell] = Field(default_factory=lambda: MappingProxyType({}))
     models: tuple[str, ...] = ()
 
@@ -121,11 +227,14 @@ class Case(BaseModel):
     def expected_for(self, model: FrontierModel) -> ExpectedCell:
         return self.expected[model.map_key]
 
+    def usage_for(self, map_key: str) -> ScriptedUsage:
+        return self.usage_by_model.get(map_key, self.usage)
+
     def scenario(self, scenario_id: str, model: FrontierModel, text: str) -> Scenario:
         return Scenario(
             scenario_id=scenario_id,
             wire=model.wire,
-            usage=self.usage,
+            usage=self.usage_for(model.map_key),
             model=model.provider_model,
             output=ScriptedOutput(
                 text=text,
@@ -137,6 +246,8 @@ class Case(BaseModel):
             ),
             stream_usage=self.stream_usage,
             service_tier=self.service_tier,
+            speed=self.speed,
+            inference_geo=self.inference_geo,
         )
 
 
@@ -183,7 +294,7 @@ _PROVIDER_WIRING: Final[Mapping[tuple[str, str], _ProviderWiring]] = MappingProx
     {
         ("openai", "chat"): _ProviderWiring("openai_chat", "openai", MappingProxyType({})),
         ("openai", "responses"): _ProviderWiring(
-            "openai_responses", "openai", MappingProxyType({})
+            "openai_responses", "openai/responses", MappingProxyType({})
         ),
         ("anthropic", "chat"): _ProviderWiring(
             "anthropic_messages", "anthropic", MappingProxyType({})
@@ -226,7 +337,13 @@ class FrontierModel:
 
     @property
     def override_rates(self) -> CostMapEntry:
-        if self.base_model is not None or self.override_map_key is None:
+        # bedrock_converse responses carry no model field, so a reported-model
+        # override can never repoint pricing there, same as a base_model pin.
+        if (
+            self.base_model is not None
+            or self.wire == "bedrock_converse"
+            or self.override_map_key is None
+        ):
             return self.rates
         return COST_MAP[self.override_map_key]
 
@@ -338,6 +455,31 @@ def _png_chunk(tag: bytes, payload: bytes) -> bytes:
     return struct.pack(">I", len(payload)) + tag + payload + struct.pack(">I", zlib.crc32(tag + payload))
 
 
+def audio_input_data_url() -> str:
+    """A deterministic 0.5 s 16-bit PCM WAV (8 kHz, 220 Hz sine) as a data
+    URL, small enough to stay a fixture but real audio to the provider."""
+    frames: Final = b"".join(
+        struct.pack("<h", int(12000 * math.sin(2 * math.pi * 220 * i / 8000)))
+        for i in range(4000)
+    )
+    buffer: Final = io.BytesIO()
+    with wave.open(buffer, "wb") as wav:
+        wav.setnchannels(1)
+        wav.setsampwidth(2)
+        wav.setframerate(8000)
+        wav.writeframes(frames)
+    return "data:audio/wav;base64," + base64.b64encode(buffer.getvalue()).decode()
+
+
+def video_input_data_url() -> str:
+    """A deterministic mp4-looking blob (ftyp box plus a fixed mdat payload)
+    as a data URL; only the media type and bytes matter to the wire."""
+    ftyp: Final = struct.pack(">I4s4sI4s4s", 24, b"ftyp", b"isom", 0x200, b"isom", b"iso6")
+    mdat_payload: Final = bytes((i * 7 + 13) % 256 for i in range(4096))
+    mdat: Final = struct.pack(">I4s", 8 + len(mdat_payload), b"mdat") + mdat_payload
+    return "data:video/mp4;base64," + base64.b64encode(ftyp + mdat).decode()
+
+
 def image_input_data_url() -> str:
     """A deterministic 256x256 RGB noise PNG as a data URL; noise compresses
     poorly on purpose so the base64 payload stays well above 100 KB and would
@@ -357,6 +499,8 @@ def image_input_data_url() -> str:
 
 
 IMAGE_INPUT_DATA_URL: Final = image_input_data_url()
+AUDIO_INPUT_DATA_URL: Final = audio_input_data_url()
+VIDEO_INPUT_DATA_URL: Final = video_input_data_url()
 
 
 def matrix_data_errors() -> tuple[str, ...]:
@@ -381,6 +525,48 @@ def matrix_data_errors() -> tuple[str, ...]:
         for case in CASES
         if case.exact_spend == bool(case.models) or case.exact_spend != bool(case.expected)
     )
+    all_pairs: Final = frozenset(
+        (map_key, key)
+        for map_key, entry in COST_MAP.items()
+        for key in _entry_rate_keys(entry)
+    )
+    owned_pairs: Final = tuple(
+        (map_key, key)
+        for case in CASES
+        if case.family == "pricing"
+        for map_key in case.expected
+        for key in case.owns
+        if map_key in COST_MAP and _entry_has_rate_key(COST_MAP[map_key], key)
+    )
+    unowned_pairs: Final = sorted(
+        f"{map_key}:{key}" for map_key, key in all_pairs - frozenset(owned_pairs)
+    )
+    duplicate_pairs: Final = sorted(
+        f"{map_key}:{key}"
+        for map_key, key in set(owned_pairs)
+        if owned_pairs.count((map_key, key)) > 1
+    )
+    owns_without_holder: Final = sorted(
+        f"{case.name}:{key}"
+        for case in CASES
+        for key in case.owns
+        if not any(
+            map_key in COST_MAP and _entry_has_rate_key(COST_MAP[map_key], key)
+            for map_key in case.expected
+        )
+    )
+    fallback_violations: Final = sorted(
+        f"{case.name}:{map_key}:{key}"
+        for case in CASES
+        for key in case.fallback_for
+        for map_key in (*case.expected, *case.models)
+        if map_key in COST_MAP and _entry_has_rate_key(COST_MAP[map_key], key)
+    )
+    family_violations: Final = sorted(
+        case.name
+        for case in CASES
+        if (case.family == "transport") != (not case.owns and not case.fallback_for)
+    )
     input_rates: Final = tuple(entry.input_cost_per_token for entry in COST_MAP.values())
     findings: Final = (
         (
@@ -404,5 +590,30 @@ def matrix_data_errors() -> tuple[str, ...]:
             if len(input_rates) != len(set(input_rates))
             else None
         ),
+        (
+            f"(model, rate key) pairs with no owning case: {unowned_pairs}"
+            if unowned_pairs
+            else None
+        ),
+        (
+            f"(model, rate key) pairs owned by more than one case: {duplicate_pairs}"
+            if duplicate_pairs
+            else None
+        ),
+        (
+            f"owns keys absent on all of the case's expected models: {owns_without_holder}"
+            if owns_without_holder
+            else None
+        ),
+        (
+            f"fallback_for keys a case's models actually carry: {fallback_violations}"
+            if fallback_violations
+            else None
+        ),
+        (
+            f"cases with owns/fallback_for inconsistent with family: {family_violations}"
+            if family_violations
+            else None
+        ),
     )
     return tuple(finding for finding in findings if finding is not None)
diff --git a/tests/e2e/cost_calculation/scripted_provider.py b/tests/e2e/cost_calculation/scripted_provider.py
index 90d95441e5c..c154dcdae62 100644
--- a/tests/e2e/cost_calculation/scripted_provider.py
+++ b/tests/e2e/cost_calculation/scripted_provider.py
@@ -87,6 +87,56 @@ _TERMINAL_CAPS: Final[Mapping[str, frozenset[str]]] = MappingProxyType(
 )
 
 
+_BASE_USAGE_FIELDS: Final = frozenset({"fresh_input_tokens", "output_tokens"})
+_OPENAI_FAMILY_USAGE: Final = frozenset(
+    {
+        "cache_read_tokens",
+        "reasoning_tokens",
+        "audio_input_tokens",
+        "audio_output_tokens",
+        "web_search_calls",
+    }
+)
+_CACHE_WRITE_USAGE: Final = frozenset({"cache_write_5m_tokens", "cache_write_1h_tokens"})
+_GEMINI_USAGE: Final = frozenset(
+    {
+        "cache_read_tokens",
+        "reasoning_tokens",
+        "audio_input_tokens",
+        "audio_output_tokens",
+        "image_input_tokens",
+        "video_input_tokens",
+        "web_search_calls",
+        "google_maps_calls",
+    }
+)
+
+_USAGE_CAPS: Final[Mapping[str, frozenset[str]]] = MappingProxyType(
+    {
+        wire: usage
+        for wire, usage in (
+            ("openai_chat", _OPENAI_FAMILY_USAGE),
+            ("azure_chat", _OPENAI_FAMILY_USAGE),
+            ("together_chat", _OPENAI_FAMILY_USAGE),
+            ("fireworks_chat", _OPENAI_FAMILY_USAGE),
+            (
+                "openai_responses",
+                frozenset(
+                    {"cache_read_tokens", "reasoning_tokens", "web_search_calls", "file_search_calls"}
+                ),
+            ),
+            (
+                "anthropic_messages",
+                frozenset({"cache_read_tokens", "web_search_calls"}) | _CACHE_WRITE_USAGE,
+            ),
+            ("bedrock_converse", frozenset({"cache_read_tokens"}) | _CACHE_WRITE_USAGE),
+            ("gemini_generate", _GEMINI_USAGE),
+            ("vertex_generate", _GEMINI_USAGE),
+        )
+    }
+)
+
+
 class ScriptedToolCall(BaseModel):
     """A single function call the scripted output emits instead of text.
     ``arguments`` is the wire's JSON string (~250 chars), sliced into deltas
@@ -116,7 +166,11 @@ class ScriptedUsage(BaseModel):
     reasoning_tokens: int = 0
     audio_input_tokens: int = 0
     audio_output_tokens: int = 0
+    image_input_tokens: int = 0
+    video_input_tokens: int = 0
     web_search_calls: int = 0
+    google_maps_calls: int = 0
+    file_search_calls: int = 0
 
 
 class ScriptedOutput(BaseModel):
@@ -151,6 +205,10 @@ class Scenario(BaseModel):
     model: str
     stream_usage: StreamUsage = "final_chunk"
     service_tier: ServiceTier | None = None
+    # Anthropic fast mode and US inference geography; emitted on the anthropic
+    # usage object only (litellm reads them there), so they are response-side.
+    speed: Literal["fast"] | None = None
+    inference_geo: Literal["us"] | None = None
 
     @model_validator(mode="after")
     def _check_terminal_supported(self) -> Scenario:
@@ -161,6 +219,20 @@ class Scenario(BaseModel):
             raise ValueError(
                 f"wire {self.wire} cannot emit terminal={self.output.terminal}"
             )
+        unsupported: Final = frozenset(
+            field
+            for field in self.usage.model_fields_set
+            if getattr(self.usage, field)
+            and field not in (_USAGE_CAPS.get(self.wire, frozenset()) | _BASE_USAGE_FIELDS)
+        )
+        if unsupported:
+            raise ValueError(
+                f"wire {self.wire} cannot express usage fields {sorted(unsupported)}"
+            )
+        if (self.speed or self.inference_geo) and self.wire != "anthropic_messages":
+            raise ValueError(
+                f"wire {self.wire} cannot emit speed/inference_geo (anthropic usage fields)"
+            )
         return self
 
     @property
@@ -215,32 +287,10 @@ def _sse(events: tuple[tuple[str | None, Mapping[str, object] | str], ...]) -> b
 
 
 def _openai_usage(u: ScriptedUsage) -> Mapping[str, object]:
-    prompt_tokens: Final = (
-        u.fresh_input_tokens
-        + u.cache_read_tokens
-        + u.cache_write_5m_tokens
-        + u.cache_write_1h_tokens
-        + u.audio_input_tokens
-    )
+    prompt_tokens: Final = u.fresh_input_tokens + u.cache_read_tokens + u.audio_input_tokens
     completion_tokens: Final = u.output_tokens + u.reasoning_tokens + u.audio_output_tokens
     prompt_details: Final = _jobj_opt(
         ("cached_tokens", u.cache_read_tokens) if u.cache_read_tokens else None,
-        (
-            ("cache_write_tokens", u.cache_write_5m_tokens + u.cache_write_1h_tokens)
-            if u.cache_write_5m_tokens or u.cache_write_1h_tokens
-            else None
-        ),
-        (
-            (
-                "cache_creation_token_details",
-                _jobj(
-                    ("ephemeral_5m_input_tokens", u.cache_write_5m_tokens),
-                    ("ephemeral_1h_input_tokens", u.cache_write_1h_tokens),
-                ),
-            )
-            if u.cache_write_5m_tokens or u.cache_write_1h_tokens
-            else None
-        ),
         ("audio_tokens", u.audio_input_tokens) if u.audio_input_tokens else None,
     )
     completion_details: Final = _jobj_opt(
@@ -256,12 +306,16 @@ def _openai_usage(u: ScriptedUsage) -> Mapping[str, object]:
     )
 
 
-def _anthropic_usage(u: ScriptedUsage) -> Mapping[str, object]:
+def _anthropic_usage(scenario: Scenario) -> Mapping[str, object]:
     # Anthropic reports uncached-only input_tokens; cache reads and writes ride
     # top-level fields, with the 5m/1h write split under cache_creation.
+    u: Final = scenario.usage
     return _jobj_opt(
         ("input_tokens", u.fresh_input_tokens),
         ("output_tokens", u.output_tokens),
+        ("service_tier", scenario.service_tier) if scenario.service_tier else None,
+        ("speed", scenario.speed) if scenario.speed else None,
+        ("inference_geo", scenario.inference_geo) if scenario.inference_geo else None,
         ("cache_read_input_tokens", u.cache_read_tokens) if u.cache_read_tokens else None,
         (
             ("cache_creation_input_tokens", u.cache_write_5m_tokens + u.cache_write_1h_tokens)
@@ -287,18 +341,24 @@ def _anthropic_usage(u: ScriptedUsage) -> Mapping[str, object]:
     )
 
 
-def _gemini_usage(u: ScriptedUsage) -> Mapping[str, object]:
-    # promptTokenCount carries the cached count inside it; TEXT modality is the
-    # cached-inclusive text count so litellm's implicit-caching subtraction lands
-    # on the fresh figure. candidatesTokenCount includes reasoning + audio.
-    prompt_tokens: Final = u.fresh_input_tokens + u.cache_read_tokens + u.audio_input_tokens
-    candidates: Final = u.output_tokens + u.reasoning_tokens + u.audio_output_tokens
+def _gemini_usage(scenario: Scenario) -> Mapping[str, object]:
+    # Real generateContent accounting: promptTokenCount carries the cached count
+    # inside it (TEXT modality is the cached-inclusive text count so litellm's
+    # implicit-caching subtraction lands on the fresh figure), candidatesTokenCount
+    # excludes thoughts, thoughtsTokenCount reports them separately, and
+    # totalTokenCount sums all three. Image/video input ride promptTokensDetails.
+    u: Final = scenario.usage
+    prompt_tokens: Final = (
+        u.fresh_input_tokens + u.cache_read_tokens + u.audio_input_tokens
+        + u.image_input_tokens + u.video_input_tokens
+    )
+    candidates: Final = u.output_tokens + u.audio_output_tokens
     return _jobj_opt(
         ("promptTokenCount", prompt_tokens),
         ("candidatesTokenCount", candidates),
-        ("totalTokenCount", prompt_tokens + candidates),
-        ("cachedContentTokenCount", u.cache_read_tokens) if u.cache_read_tokens else None,
         ("thoughtsTokenCount", u.reasoning_tokens) if u.reasoning_tokens else None,
+        ("totalTokenCount", prompt_tokens + candidates + u.reasoning_tokens),
+        ("cachedContentTokenCount", u.cache_read_tokens) if u.cache_read_tokens else None,
         (
             "promptTokensDetails",
             (
@@ -308,19 +368,66 @@ def _gemini_usage(u: ScriptedUsage) -> Mapping[str, object]:
                     if u.audio_input_tokens
                     else ()
                 ),
+                *(
+                    (_jobj(("modality", "IMAGE"), ("tokenCount", u.image_input_tokens)),)
+                    if u.image_input_tokens
+                    else ()
+                ),
+                *(
+                    (_jobj(("modality", "VIDEO"), ("tokenCount", u.video_input_tokens)),)
+                    if u.video_input_tokens
+                    else ()
+                ),
             ),
         ),
         (
             (
                 "candidatesTokensDetails",
                 (
-                    _jobj(("modality", "TEXT"), ("tokenCount", u.output_tokens + u.reasoning_tokens)),
+                    _jobj(("modality", "TEXT"), ("tokenCount", u.output_tokens)),
                     _jobj(("modality", "AUDIO"), ("tokenCount", u.audio_output_tokens)),
                 ),
             )
             if u.audio_output_tokens
             else None
         ),
+        (
+            (
+                "trafficType",
+                {"flex": "ON_DEMAND_FLEX", "priority": "ON_DEMAND_PRIORITY"}[
+                    scenario.service_tier
+                ],
+            )
+            if scenario.service_tier
+            else None
+        ),
+    )
+
+
+def _gemini_grounding_metadata(scenario: Scenario) -> Mapping[str, object] | None:
+    """groundingMetadata for the search/Maps flags. Maps items carry maps
+    chunks and googleMapsWidgetContextToken so litellm bills them as Maps
+    queries, not web search."""
+    u: Final = scenario.usage
+    if not u.web_search_calls and not u.google_maps_calls:
+        return None
+    if u.google_maps_calls:
+        return _jobj(
+            (
+                "webSearchQueries",
+                tuple(f"maps query {i}" for i in range(u.google_maps_calls)),
+            ),
+            (
+                "groundingChunks",
+                tuple(
+                    _jobj(("maps", _jobj(("uri", f"https://maps.google.com/?cid={i}"))))
+                    for i in range(u.google_maps_calls)
+                ),
+            ),
+            ("googleMapsWidgetContextToken", f"token_{scenario.scenario_id}"),
+        )
+    return _jobj(
+        ("webSearchQueries", tuple(f"query {i}" for i in range(u.web_search_calls))),
     )
 
 
@@ -572,7 +679,7 @@ def _anthropic_body(scenario: Scenario, requested_model: str) -> Mapping[str, ob
         ("model", scenario.output.response_model or requested_model),
         ("content", _anthropic_content(scenario)),
         ("stop_reason", _anthropic_stop_reason(scenario)),
-        ("usage", _anthropic_usage(scenario.usage)),
+        ("usage", _anthropic_usage(scenario)),
     )
 
 
@@ -581,7 +688,7 @@ def _anthropic_sse(scenario: Scenario, requested_model: str) -> bytes:
     input_usage: Final = _jobj(
         *(
             (key, value)
-            for key, value in _anthropic_usage(scenario.usage).items()
+            for key, value in _anthropic_usage(scenario).items()
             if key != "output_tokens"
         )
     )
@@ -685,7 +792,7 @@ def _gemini_prompt_blocked_body(scenario: Scenario, requested_model: str) -> Map
                 ),
             ),
         ),
-        ("usageMetadata", _gemini_usage(scenario.usage)),
+        ("usageMetadata", _gemini_usage(scenario)),
         ("modelVersion", scenario.output.response_model or requested_model),
     )
 
@@ -728,22 +835,14 @@ def _gemini_body(scenario: Scenario, requested_model: str) -> Mapping[str, objec
                     ),
                     ("index", 0),
                     (
-                        (
-                            "groundingMetadata",
-                            _jobj(
-                                (
-                                    "webSearchQueries",
-                                    tuple(f"query {i}" for i in range(scenario.usage.web_search_calls)),
-                                )
-                            ),
-                        )
-                        if scenario.usage.web_search_calls
+                        ("groundingMetadata", _gemini_grounding_metadata(scenario))
+                        if _gemini_grounding_metadata(scenario) is not None
                         else None
                     ),
                 ),
             ),
         ),
-        ("usageMetadata", _gemini_usage(scenario.usage)),
+        ("usageMetadata", _gemini_usage(scenario)),
         ("modelVersion", scenario.output.response_model or requested_model),
     )
 
@@ -762,7 +861,7 @@ def _gemini_sse(scenario: Scenario, requested_model: str) -> bytes:
                         None,
                         _jobj(
                             ("candidates", ()),
-                            ("usageMetadata", _gemini_usage(scenario.usage)),
+                            ("usageMetadata", _gemini_usage(scenario)),
                             ("modelVersion", scenario.output.response_model or requested_model),
                         ),
                     ),
@@ -788,6 +887,16 @@ def _responses_output(scenario: Scenario) -> tuple[Mapping[str, object], ...]:
             _jobj(("type", "web_search_call"), ("id", f"ws_{i}"), ("status", "completed"))
             for i in range(scenario.usage.web_search_calls)
         ),
+        *(
+            _jobj(
+                ("type", "file_search_call"),
+                ("id", f"fs_{i}"),
+                ("status", "completed"),
+                ("queries", (f"query {i}",)),
+                ("results", ()),
+            )
+            for i in range(scenario.usage.file_search_calls)
+        ),
         _jobj(
             ("type", "function_call"),
             ("id", f"fc_{scenario.scenario_id}"),
@@ -853,9 +962,50 @@ def _responses_sse(scenario: Scenario, requested_model: str) -> bytes:
         "response.incomplete" if scenario.output.terminal == "incomplete" else "response.completed"
     )
     output_index: Final = (
-        scenario.usage.web_search_calls + (1 if scenario.output.terminal == "unvalidated" else 0)
+        scenario.usage.web_search_calls
+        + scenario.usage.file_search_calls
+        + (1 if scenario.output.terminal == "unvalidated" else 0)
     )
-    middle_events: Final[tuple[tuple[str, Mapping[str, object]], ...]] = (
+    file_search_events: Final[tuple[tuple[str, Mapping[str, object]], ...]] = tuple(
+        event
+        for i in range(scenario.usage.file_search_calls)
+        for event in (
+            (
+                "response.output_item.added",
+                _jobj(
+                    ("type", "response.output_item.added"),
+                    ("output_index", i),
+                    (
+                        "item",
+                        _jobj(
+                            ("type", "file_search_call"),
+                            ("id", f"fs_{i}"),
+                            ("status", "in_progress"),
+                            ("queries", ()),
+                        ),
+                    ),
+                ),
+            ),
+            (
+                "response.output_item.done",
+                _jobj(
+                    ("type", "response.output_item.done"),
+                    ("output_index", i),
+                    (
+                        "item",
+                        _jobj(
+                            ("type", "file_search_call"),
+                            ("id", f"fs_{i}"),
+                            ("status", "completed"),
+                            ("queries", (f"query {i}",)),
+                            ("results", ()),
+                        ),
+                    ),
+                ),
+            ),
+        )
+    )
+    call_events: Final[tuple[tuple[str, Mapping[str, object]], ...]] = (
         (
             (
                 "response.output_item.added",
@@ -911,6 +1061,10 @@ def _responses_sse(scenario: Scenario, requested_model: str) -> bytes:
             ),
         )
     )
+    middle_events: Final[tuple[tuple[str, Mapping[str, object]], ...]] = (
+        *file_search_events,
+        *call_events,
+    )
     return _sse(
         (
             ("response.created", _jobj(("type", "response.created"), ("response", created))),
@@ -976,7 +1130,7 @@ def _bedrock_content(scenario: Scenario) -> tuple[Mapping[str, object], ...]:
 
 
 def _bedrock_body(scenario: Scenario) -> Mapping[str, object]:
-    return _jobj(
+    return _jobj_opt(
         (
             "output",
             _jobj(
@@ -992,6 +1146,11 @@ def _bedrock_body(scenario: Scenario) -> Mapping[str, object]:
         ("stopReason", _bedrock_stop_reason(scenario)),
         ("usage", _bedrock_usage(scenario.usage)),
         ("metrics", _jobj(("latencyMs", 42))),
+        (
+            ("serviceTier", _jobj(("type", scenario.service_tier)))
+            if scenario.service_tier
+            else None
+        ),
     )
 
 
@@ -1083,9 +1242,14 @@ def _bedrock_eventstream(scenario: Scenario) -> bytes:
                 (
                     _aws_event_frame(
                         "metadata",
-                        _jobj(
+                        _jobj_opt(
                             ("usage", _bedrock_usage(scenario.usage)),
                             ("metrics", _jobj(("latencyMs", 42))),
+                            (
+                                ("serviceTier", _jobj(("type", scenario.service_tier)))
+                                if scenario.service_tier
+                                else None
+                            ),
                         ),
                     ),
                 )
diff --git a/tests/e2e/cost_calculation/test_token_pricing_e2e.py b/tests/e2e/cost_calculation/test_token_pricing_e2e.py
index 03dab6be5e7..004cb4d839e 100644
--- a/tests/e2e/cost_calculation/test_token_pricing_e2e.py
+++ b/tests/e2e/cost_calculation/test_token_pricing_e2e.py
@@ -16,8 +16,11 @@ from typing import Final
 
 from conftest import CostCalcClient, cost_rows, register_scenario_deployment
 from cost_matrix import (
+    AUDIO_INPUT_DATA_URL,
     FRONTIER_MODELS,
     IMAGE_INPUT_DATA_URL,
+    SERVICE_TIER_REQUEST_WIRES,
+    VIDEO_INPUT_DATA_URL,
     Case,
     FrontierModel,
     cases_for,
@@ -27,15 +30,27 @@ from cost_matrix import (
 from e2e_config import unique_marker
 from lifecycle import ResourceManager
 from models import (
+    CacheControl,
+    ChatAudio,
     ChatBody,
     ChatMessage,
     ChatStreamOptions,
     ChatTool,
     ChatToolFunction,
+    FileContentPart,
+    FileObject,
+    FileSearchTool,
+    GoogleMapsTool,
+    GoogleSearchTool,
+    HostedWebSearchTool,
     ImageContentPart,
     ImageUrl,
+    InputAudio,
+    InputAudioContentPart,
     TextContentPart,
+    WebSearchOptions,
 )
+from scripted_provider import ScriptedUsage, Wire
 
 pytestmark: Final = [pytest.mark.e2e, pytest.mark.cost_map_stack]  # mutable-ok: pytest only accepts a list for pytestmark
 
@@ -52,40 +67,131 @@ def _case_id(param: tuple[FrontierModel, Case]) -> str:
     return f"{model.map_key.replace('/', '-')}-{case.name}"
 
 
-def _chat_body(model_name: str, marker: str, case: Case) -> ChatBody:
-    return ChatBody(
-        model=model_name,
-        messages=(
-            ChatMessage(
-                role="user",
-                content=(
-                    [
-                        TextContentPart(text=f"{marker} scripted pricing call"),
-                        ImageContentPart(image_url=ImageUrl(url=IMAGE_INPUT_DATA_URL)),
-                    ]
-                    if case.image_input
-                    else f"{marker} scripted pricing call"
-                ),
-            ),
+_CACHE_WIRES: Final = frozenset({"anthropic_messages", "bedrock_converse"})
+_WEB_SEARCH_OPTION_WIRES: Final = frozenset({"openai_chat", "azure_chat", "openai_responses"})
+
+
+def _cache_control(usage: ScriptedUsage, wire: Wire) -> CacheControl | None:
+    if wire not in _CACHE_WIRES:
+        return None
+    if not (usage.cache_read_tokens or usage.cache_write_5m_tokens or usage.cache_write_1h_tokens):
+        return None
+    return CacheControl(type="ephemeral", ttl="1h" if usage.cache_write_1h_tokens else None)
+
+
+def _chat_body(model: FrontierModel, case: Case, model_name: str, marker: str) -> ChatBody:
+    usage: Final = case.usage_for(model.map_key)
+    user_parts: Final = (
+        TextContentPart(
+            text=f"{marker} summarize the attached material in one line and name the city weather",
         ),
-        stream=case.stream,
-        stream_options=ChatStreamOptions(include_usage=True) if case.stream else None,
-        service_tier=case.service_tier,
-        tools=(
+        *(
+            (ImageContentPart(image_url=ImageUrl(url=IMAGE_INPUT_DATA_URL, detail="high")),)
+            if case.image_input
+            else ()
+        ),
+        *(
+            (
+                InputAudioContentPart(
+                    input_audio=InputAudio(data=AUDIO_INPUT_DATA_URL.split(",", 1)[1], format="wav")
+                ),
+            )
+            if case.audio_input
+            else ()
+        ),
+        *(
+            (FileContentPart(file=FileObject(file_data=VIDEO_INPUT_DATA_URL, format="mp4")),)
+            if case.video_input
+            else ()
+        ),
+    )
+    tools: Final = (
+        *(
             (
                 ChatTool(
                     function=ChatToolFunction(
                         name="get_weather",
+                        description="Get the current weather and a short forecast for a city.",
                         parameters={
                             "type": "object",
-                            "properties": {"city": {"type": "string"}},
+                            "properties": {
+                                "city": {"type": "string", "description": "City name"},
+                                "days": {"type": "integer", "description": "Forecast horizon in days"},
+                                "units": {"type": "string", "enum": ["metric", "imperial"]},
+                            },
+                            "required": ["city"],
                         },
                     )
                 ),
             )
             if case.tool_call
+            else ()
+        ),
+        *(
+            (HostedWebSearchTool(type="web_search_20250305", name="web_search", max_uses=5),)
+            if case.web_search is not None and model.wire == "anthropic_messages"
+            else ()
+        ),
+        *(
+            (GoogleSearchTool(),)
+            if case.web_search is not None and model.wire in ("gemini_generate", "vertex_generate")
+            else ()
+        ),
+        *((GoogleMapsTool(),) if case.google_maps else ()),
+        *((FileSearchTool(vector_store_ids=["vs_cost_calc_fixture"]),) if case.file_search else ()),
+    )
+    return ChatBody(
+        model=model_name,
+        messages=(
+            ChatMessage(
+                role="system",
+                content=[
+                    TextContentPart(
+                        text=(
+                            "You are a deterministic pricing-harness assistant. "
+                            "Keep answers to a single short line."
+                        ),
+                        cache_control=_cache_control(usage, model.wire),
+                    )
+                ],
+            ),
+            ChatMessage(role="user", content=list(user_parts)),
+        ),
+        stream=case.stream,
+        stream_options=ChatStreamOptions(include_usage=True) if case.stream else None,
+        service_tier=(
+            case.service_tier
+            if case.service_tier is not None and model.wire in SERVICE_TIER_REQUEST_WIRES
             else None
         ),
+        reasoning_effort="medium" if case.reasoning else None,
+        modalities=(
+            ["text"] if case.audio_input else (["text", "audio"] if case.audio_output else None)
+        ),
+        audio=(
+            ChatAudio(voice="alloy", format="pcm16") if case.audio_output else None
+        ),
+        web_search_options=(
+            WebSearchOptions(search_context_size=case.web_search)
+            if case.web_search is not None and model.wire in _WEB_SEARCH_OPTION_WIRES
+            else None
+        ),
+        tools=tools or None,
+        tool_choice="auto" if case.tool_call and model.wire != "bedrock_converse" else None,
+        # The test-owned cost map carries no supports_* flags, so litellm's
+        # optional-params gate rejects the realistic request fields; allowlist
+        # exactly the ones this case sends.
+        allowed_openai_params=[
+            name
+            for name, sent in (
+                ("tool_choice", case.tool_call and model.wire != "bedrock_converse"),
+                ("modalities", case.audio_input or case.audio_output),
+                ("audio", case.audio_output),
+                ("web_search_options", case.web_search is not None),
+                ("reasoning_effort", case.reasoning),
+            )
+            if sent
+        ],
     )
 
 
@@ -105,7 +211,7 @@ class TestTokenPricing:
         response: Final = client.proxy.transport.send(
             "/chat/completions",
             headers=client.proxy.transport.bearer(scoped_key),
-            json=_chat_body(model_name, marker, case),
+            json=_chat_body(model, case, model_name, marker),
             stream=case.stream,
         )
         assert response.ok, (
diff --git a/tests/e2e/cost_map.json b/tests/e2e/cost_map.json
index 85cd5ade3d5..117e9b33636 100644
--- a/tests/e2e/cost_map.json
+++ b/tests/e2e/cost_map.json
@@ -1,525 +1,411 @@
 {
-  "anthropic.claude-sonnet-5-v1:0": {
-    "cache_creation_input_token_cost": 0.00051,
-    "cache_creation_input_token_cost_above_1hr": 0.00068,
-    "cache_read_input_token_cost": 1.7e-05,
-    "input_cost_per_token": 0.00017,
-    "litellm_provider": "bedrock_converse",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+  "gpt-5.6": {
+    "cache_read_input_token_cost": 1.75e-07,
+    "input_cost_per_audio_token": 4e-05,
+    "input_cost_per_token": 1.75e-06,
+    "input_cost_per_token_flex": 8.75e-07,
+    "input_cost_per_token_priority": 3.5e-06,
+    "litellm_provider": "openai",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_token": 0.00034,
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true
-  },
-  "azure/gpt-5.4-mini": {
-    "cache_creation_input_token_cost": 0.00048,
-    "cache_creation_input_token_cost_above_1hr": 0.00064,
-    "cache_read_input_token_cost": 1.6e-05,
-    "input_cost_per_audio_token": 0.00096,
-    "input_cost_per_token": 0.00016,
-    "input_cost_per_token_above_200k_tokens": 0.00128,
-    "input_cost_per_token_flex": 0.00024,
-    "input_cost_per_token_priority": 0.000272,
-    "litellm_provider": "azure",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
-    "mode": "chat",
-    "output_cost_per_audio_token": 0.00112,
-    "output_cost_per_reasoning_token": 0.0008,
-    "output_cost_per_token": 0.00032,
-    "output_cost_per_token_above_200k_tokens": 0.00144,
-    "output_cost_per_token_flex": 0.0004,
-    "output_cost_per_token_priority": 0.000432,
+    "output_cost_per_audio_token": 8e-05,
+    "output_cost_per_reasoning_token": 1.6e-05,
+    "output_cost_per_token": 1.4e-05,
+    "output_cost_per_token_flex": 7e-06,
+    "output_cost_per_token_priority": 2.8e-05,
     "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
       "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
+      "search_context_size_medium": 0.0125,
+      "search_context_size_high": 0.015
     },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
+    "supports_function_calling": true
+  },
+  "gpt-5.4-mini": {
+    "cache_read_input_token_cost": 3.5e-08,
+    "input_cost_per_audio_token": 1e-05,
+    "input_cost_per_token": 3.5e-07,
+    "input_cost_per_token_flex": 1.75e-07,
+    "input_cost_per_token_priority": 7e-07,
+    "litellm_provider": "openai",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
+    "mode": "chat",
+    "output_cost_per_audio_token": 2e-05,
+    "output_cost_per_reasoning_token": 3.2e-06,
+    "output_cost_per_token": 2.8e-06,
+    "output_cost_per_token_flex": 1.4e-06,
+    "output_cost_per_token_priority": 5.6e-06,
+    "search_context_cost_per_query": {
+      "search_context_size_low": 0.01,
+      "search_context_size_medium": 0.0125,
+      "search_context_size_high": 0.015
+    },
+    "supports_function_calling": true
   },
   "azure/gpt-5.6": {
-    "cache_creation_input_token_cost": 0.00045,
-    "cache_creation_input_token_cost_above_1hr": 0.0006,
-    "cache_read_input_token_cost": 1.5e-05,
-    "input_cost_per_audio_token": 0.0009,
-    "input_cost_per_token": 0.00015,
-    "input_cost_per_token_above_200k_tokens": 0.0012,
-    "input_cost_per_token_flex": 0.000225,
-    "input_cost_per_token_priority": 0.000255,
+    "cache_read_input_token_cost": 1.8e-07,
+    "input_cost_per_audio_token": 4.1e-05,
+    "input_cost_per_token": 1.8e-06,
+    "input_cost_per_token_flex": 9e-07,
+    "input_cost_per_token_priority": 3.6e-06,
     "litellm_provider": "azure",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_audio_token": 0.00105,
-    "output_cost_per_reasoning_token": 0.00075,
-    "output_cost_per_token": 0.0003,
-    "output_cost_per_token_above_200k_tokens": 0.00135,
-    "output_cost_per_token_flex": 0.000375,
-    "output_cost_per_token_priority": 0.000405,
+    "output_cost_per_audio_token": 8.2e-05,
+    "output_cost_per_reasoning_token": 1.65e-05,
+    "output_cost_per_token": 1.44e-05,
+    "output_cost_per_token_flex": 7.2e-06,
+    "output_cost_per_token_priority": 2.88e-05,
     "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
       "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
+      "search_context_size_medium": 0.0125,
+      "search_context_size_high": 0.015
     },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
+    "supports_function_calling": true
   },
-  "claude-haiku-4-5": {
-    "cache_creation_input_token_cost": 0.00021,
-    "cache_creation_input_token_cost_above_1hr": 0.00028000000000000003,
-    "cache_read_input_token_cost": 7e-06,
-    "input_cost_per_token": 7.000000000000001e-05,
-    "litellm_provider": "anthropic",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+  "azure/gpt-5.4-mini": {
+    "cache_read_input_token_cost": 3.6e-08,
+    "input_cost_per_audio_token": 1.05e-05,
+    "input_cost_per_token": 3.6e-07,
+    "input_cost_per_token_flex": 1.8e-07,
+    "input_cost_per_token_priority": 7.2e-07,
+    "litellm_provider": "azure",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_token": 0.00014000000000000001,
+    "output_cost_per_audio_token": 2.1e-05,
+    "output_cost_per_reasoning_token": 3.3e-06,
+    "output_cost_per_token": 2.88e-06,
+    "output_cost_per_token_flex": 1.44e-06,
+    "output_cost_per_token_priority": 5.76e-06,
     "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
       "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
+      "search_context_size_medium": 0.0125,
+      "search_context_size_high": 0.015
     },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
+    "supports_function_calling": true
+  },
+  "gpt-5.3-codex": {
+    "cache_read_input_token_cost": 1.5e-07,
+    "file_search_cost_per_1k_calls": 0.0025,
+    "input_cost_per_token": 1.5e-06,
+    "input_cost_per_token_flex": 7.5e-07,
+    "input_cost_per_token_priority": 3e-06,
+    "litellm_provider": "openai",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
+    "mode": "responses",
+    "output_cost_per_reasoning_token": 1.3e-05,
+    "output_cost_per_token": 1.2e-05,
+    "output_cost_per_token_flex": 6e-06,
+    "output_cost_per_token_priority": 2.4e-05,
+    "search_context_cost_per_query": {
+      "search_context_size_low": 0.01,
+      "search_context_size_medium": 0.0125,
+      "search_context_size_high": 0.015
+    },
+    "supports_function_calling": true
+  },
+  "gpt-5.5-pro": {
+    "cache_read_input_token_cost": 1.5e-06,
+    "file_search_cost_per_1k_calls": 0.0025,
+    "input_cost_per_token": 1.5e-05,
+    "input_cost_per_token_flex": 7.5e-06,
+    "input_cost_per_token_priority": 3e-05,
+    "litellm_provider": "openai",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
+    "mode": "responses",
+    "output_cost_per_reasoning_token": 0.00013,
+    "output_cost_per_token": 0.00012,
+    "output_cost_per_token_flex": 6e-05,
+    "output_cost_per_token_priority": 0.00024,
+    "search_context_cost_per_query": {
+      "search_context_size_low": 0.01,
+      "search_context_size_medium": 0.0125,
+      "search_context_size_high": 0.015
+    },
+    "supports_function_calling": true
   },
   "claude-opus-5": {
-    "cache_creation_input_token_cost": 0.00015000000000000001,
-    "cache_creation_input_token_cost_above_1hr": 0.0002,
-    "cache_read_input_token_cost": 4.9999999999999996e-06,
-    "input_cost_per_token": 5e-05,
+    "cache_creation_input_token_cost": 6.25e-06,
+    "cache_creation_input_token_cost_above_1hr": 1e-05,
+    "cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
+    "cache_read_input_token_cost": 5e-07,
+    "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+    "input_cost_per_token": 5e-06,
+    "input_cost_per_token_above_200k_tokens": 1e-05,
+    "input_cost_per_token_priority": 6.25e-06,
     "litellm_provider": "anthropic",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_token": 0.0001,
-    "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
+    "output_cost_per_token": 2.5e-05,
+    "output_cost_per_token_above_200k_tokens": 3.75e-05,
+    "output_cost_per_token_priority": 3.125e-05,
+    "provider_specific_entry": {
+      "fast": 6.0,
+      "us": 1.1
     },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
+    "search_context_cost_per_query": {
+      "search_context_size_medium": 0.01
+    },
+    "supports_function_calling": true
   },
   "claude-sonnet-5": {
-    "cache_creation_input_token_cost": 0.00018,
-    "cache_creation_input_token_cost_above_1hr": 0.00024000000000000003,
-    "cache_read_input_token_cost": 6e-06,
-    "input_cost_per_token": 6.000000000000001e-05,
+    "cache_creation_input_token_cost": 3.75e-06,
+    "cache_creation_input_token_cost_above_1hr": 6e-06,
+    "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
+    "cache_read_input_token_cost": 3e-07,
+    "cache_read_input_token_cost_above_200k_tokens": 6e-07,
+    "input_cost_per_token": 3e-06,
+    "input_cost_per_token_above_200k_tokens": 6e-06,
+    "input_cost_per_token_priority": 3.75e-06,
     "litellm_provider": "anthropic",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_token": 0.00012000000000000002,
-    "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
+    "output_cost_per_token": 1.5e-05,
+    "output_cost_per_token_above_200k_tokens": 2.25e-05,
+    "output_cost_per_token_priority": 1.875e-05,
+    "provider_specific_entry": {
+      "us": 1.1
     },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
+    "search_context_cost_per_query": {
+      "search_context_size_medium": 0.01
+    },
+    "supports_function_calling": true
   },
-  "fireworks_ai/deepseek-v4p1-flash": {
-    "cache_creation_input_token_cost": 0.00033,
-    "cache_creation_input_token_cost_above_1hr": 0.00044,
-    "cache_read_input_token_cost": 1.4e-05,
-    "input_cost_per_audio_token": 0.00066,
-    "input_cost_per_token": 0.00014000000000000001,
-    "litellm_provider": "fireworks_ai",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+  "claude-haiku-4-5": {
+    "cache_creation_input_token_cost": 1.25e-06,
+    "cache_creation_input_token_cost_above_1hr": 2e-06,
+    "cache_read_input_token_cost": 1e-07,
+    "input_cost_per_token": 1e-06,
+    "input_cost_per_token_priority": 1.25e-06,
+    "litellm_provider": "anthropic",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_audio_token": 0.00077,
-    "output_cost_per_reasoning_token": 0.00055,
-    "output_cost_per_token": 0.00028000000000000003,
-    "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
+    "output_cost_per_token": 5e-06,
+    "output_cost_per_token_priority": 6.25e-06,
+    "provider_specific_entry": {
+      "us": 1.1
     },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
+    "search_context_cost_per_query": {
+      "search_context_size_medium": 0.01
+    },
+    "supports_function_calling": true
   },
-  "fireworks_ai/kimi-k3": {
-    "cache_creation_input_token_cost": 0.00033,
-    "cache_creation_input_token_cost_above_1hr": 0.00044,
-    "cache_read_input_token_cost": 1.2e-05,
-    "input_cost_per_audio_token": 0.00066,
-    "input_cost_per_token": 0.00012000000000000002,
-    "litellm_provider": "fireworks_ai",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+  "us.anthropic.claude-opus-5-v1:0": {
+    "cache_creation_input_token_cost": 6.875e-06,
+    "cache_creation_input_token_cost_above_1hr": 1.1e-05,
+    "cache_creation_input_token_cost_above_200k_tokens": 1.375e-05,
+    "cache_read_input_token_cost": 5.5e-07,
+    "cache_read_input_token_cost_above_200k_tokens": 1.1e-06,
+    "input_cost_per_token": 5.5e-06,
+    "input_cost_per_token_above_200k_tokens": 1.1e-05,
+    "input_cost_per_token_flex": 2.75e-06,
+    "input_cost_per_token_priority": 6.875e-06,
+    "litellm_provider": "bedrock_converse",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_audio_token": 0.00077,
-    "output_cost_per_reasoning_token": 0.00055,
-    "output_cost_per_token": 0.00024000000000000003,
-    "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
-    },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
+    "output_cost_per_token": 2.75e-05,
+    "output_cost_per_token_above_200k_tokens": 4.125e-05,
+    "output_cost_per_token_flex": 1.375e-05,
+    "output_cost_per_token_priority": 3.4375e-05,
+    "supports_function_calling": true
   },
-  "fireworks_ai/qwen3p8-max": {
-    "cache_creation_input_token_cost": 0.00033,
-    "cache_creation_input_token_cost_above_1hr": 0.00044,
-    "cache_read_input_token_cost": 1.3e-05,
-    "input_cost_per_audio_token": 0.00066,
-    "input_cost_per_token": 0.00013000000000000002,
-    "litellm_provider": "fireworks_ai",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+  "anthropic.claude-sonnet-5-v1:0": {
+    "cache_creation_input_token_cost": 4.125e-06,
+    "cache_creation_input_token_cost_above_1hr": 6.6e-06,
+    "cache_read_input_token_cost": 3.3e-07,
+    "input_cost_per_token": 3.3e-06,
+    "input_cost_per_token_flex": 1.65e-06,
+    "input_cost_per_token_priority": 4.125e-06,
+    "litellm_provider": "bedrock_converse",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_audio_token": 0.00077,
-    "output_cost_per_reasoning_token": 0.00055,
-    "output_cost_per_token": 0.00026000000000000003,
-    "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
-    },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
+    "output_cost_per_token": 1.65e-05,
+    "output_cost_per_token_flex": 8.25e-06,
+    "output_cost_per_token_priority": 2.0625e-05,
+    "supports_function_calling": true
   },
-  "gemini-3.1-pro-preview": {
-    "cache_read_input_token_cost": 2.1e-05,
-    "input_cost_per_audio_token": 0.00126,
-    "input_cost_per_token": 0.00021,
-    "input_cost_per_token_above_200k_tokens": 0.00168,
-    "input_cost_per_token_flex": 0.000315,
-    "input_cost_per_token_priority": 0.000357,
-    "litellm_provider": "vertex_ai-language-models",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+  "meta.llama4-maverick-17b-instruct-v1:0": {
+    "input_cost_per_token": 2.4e-07,
+    "litellm_provider": "bedrock_converse",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_audio_token": 0.00147,
-    "output_cost_per_reasoning_token": 0.00105,
-    "output_cost_per_token": 0.00042,
-    "output_cost_per_token_above_200k_tokens": 0.00189,
-    "output_cost_per_token_flex": 0.000525,
-    "output_cost_per_token_priority": 0.000567,
-    "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
-    },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true,
-    "web_search_billing_unit": "per_query"
+    "output_cost_per_token": 9.7e-07,
+    "supports_function_calling": true
   },
-  "gemini-3.8-flash": {
-    "cache_read_input_token_cost": 2e-05,
-    "input_cost_per_audio_token": 0.0012,
-    "input_cost_per_token": 0.0002,
-    "input_cost_per_token_above_200k_tokens": 0.0016,
-    "input_cost_per_token_flex": 0.0003,
-    "input_cost_per_token_priority": 0.00034,
-    "litellm_provider": "vertex_ai-language-models",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
-    "mode": "chat",
-    "output_cost_per_audio_token": 0.0014,
-    "output_cost_per_reasoning_token": 0.001,
-    "output_cost_per_token": 0.0004,
-    "output_cost_per_token_above_200k_tokens": 0.0018,
-    "output_cost_per_token_flex": 0.0005,
-    "output_cost_per_token_priority": 0.00054,
-    "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
-    },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true,
-    "web_search_billing_unit": "per_query"
-  },
-  "gemini/gemini-3.1-pro-preview": {
-    "cache_read_input_token_cost": 9e-06,
-    "input_cost_per_audio_token": 0.00054,
-    "input_cost_per_token": 9e-05,
-    "input_cost_per_token_above_200k_tokens": 0.00072,
-    "input_cost_per_token_flex": 0.000135,
-    "input_cost_per_token_priority": 0.000153,
+  "gemini/gemini-3.1-pro": {
+    "cache_read_input_token_cost": 2e-07,
+    "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+    "google_maps_grounding_cost_per_query": 0.025,
+    "input_cost_per_audio_token": 2.6e-06,
+    "input_cost_per_image_token": 2.2e-06,
+    "input_cost_per_token": 2e-06,
+    "input_cost_per_token_above_200k_tokens": 4e-06,
+    "input_cost_per_token_flex": 1e-06,
+    "input_cost_per_token_priority": 2.5e-06,
+    "input_cost_per_video_token": 2.4e-06,
     "litellm_provider": "gemini",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+    "max_input_tokens": 1048576,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_audio_token": 0.0006299999999999999,
-    "output_cost_per_reasoning_token": 0.00045000000000000004,
-    "output_cost_per_token": 0.00018,
-    "output_cost_per_token_above_200k_tokens": 0.0008100000000000001,
-    "output_cost_per_token_flex": 0.00022500000000000002,
-    "output_cost_per_token_priority": 0.000243,
+    "output_cost_per_reasoning_token": 1.3e-05,
+    "output_cost_per_token": 1.2e-05,
+    "output_cost_per_token_above_200k_tokens": 1.8e-05,
+    "output_cost_per_token_flex": 6e-06,
+    "output_cost_per_token_priority": 1.5e-05,
     "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
+      "search_context_size_medium": 0.035
     },
     "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true,
     "web_search_billing_unit": "per_query"
   },
   "gemini/gemini-3.8-flash": {
-    "cache_read_input_token_cost": 8e-06,
-    "input_cost_per_audio_token": 0.00048,
-    "input_cost_per_token": 8e-05,
-    "input_cost_per_token_above_200k_tokens": 0.00064,
-    "input_cost_per_token_flex": 0.00012,
-    "input_cost_per_token_priority": 0.000136,
+    "cache_read_input_token_cost": 5e-08,
+    "google_maps_grounding_cost_per_query": 0.025,
+    "input_cost_per_audio_token": 1e-06,
+    "input_cost_per_image_token": 5.5e-07,
+    "input_cost_per_token": 5e-07,
+    "input_cost_per_token_flex": 2.5e-07,
+    "input_cost_per_token_priority": 6.25e-07,
+    "input_cost_per_video_token": 6e-07,
     "litellm_provider": "gemini",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+    "max_input_tokens": 1048576,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_audio_token": 0.00056,
-    "output_cost_per_reasoning_token": 0.0004,
-    "output_cost_per_token": 0.00016,
-    "output_cost_per_token_above_200k_tokens": 0.00072,
-    "output_cost_per_token_flex": 0.0002,
-    "output_cost_per_token_priority": 0.000216,
+    "output_cost_per_audio_token": 6e-06,
+    "output_cost_per_reasoning_token": 3.5e-06,
+    "output_cost_per_token": 3e-06,
+    "output_cost_per_token_flex": 1.5e-06,
+    "output_cost_per_token_priority": 3.75e-06,
     "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
+      "search_context_size_medium": 0.035
+    },
+    "supports_function_calling": true,
+    "web_search_billing_unit": "per_prompt"
+  },
+  "gemini-3.1-pro": {
+    "cache_read_input_token_cost": 2.1e-07,
+    "cache_read_input_token_cost_above_200k_tokens": 4.2e-07,
+    "google_maps_grounding_cost_per_query": 0.025,
+    "input_cost_per_audio_token": 2.7e-06,
+    "input_cost_per_image_token": 2.3e-06,
+    "input_cost_per_token": 2.1e-06,
+    "input_cost_per_token_above_200k_tokens": 4.2e-06,
+    "input_cost_per_token_flex": 1.05e-06,
+    "input_cost_per_token_priority": 2.625e-06,
+    "litellm_provider": "vertex_ai-language-models",
+    "max_input_tokens": 1048576,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
+    "mode": "chat",
+    "output_cost_per_reasoning_token": 1.35e-05,
+    "output_cost_per_token": 1.26e-05,
+    "output_cost_per_token_above_200k_tokens": 1.89e-05,
+    "output_cost_per_token_flex": 6.3e-06,
+    "output_cost_per_token_priority": 1.575e-05,
+    "search_context_cost_per_query": {
+      "search_context_size_medium": 0.035
     },
     "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true,
     "web_search_billing_unit": "per_query"
   },
-  "gpt-5.3-codex": {
-    "cache_read_input_token_cost": 3e-06,
-    "input_cost_per_token": 3.0000000000000004e-05,
-    "input_cost_per_token_above_200k_tokens": 0.00024000000000000003,
-    "input_cost_per_token_flex": 4.5e-05,
-    "input_cost_per_token_priority": 5.1e-05,
-    "litellm_provider": "openai",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
-    "mode": "responses",
-    "output_cost_per_reasoning_token": 0.00015000000000000001,
-    "output_cost_per_token": 6.000000000000001e-05,
-    "output_cost_per_token_above_200k_tokens": 0.00027,
-    "output_cost_per_token_flex": 7.500000000000001e-05,
-    "output_cost_per_token_priority": 8.099999999999999e-05,
-    "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
-    },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
-  },
-  "gpt-5.4-mini": {
-    "cache_creation_input_token_cost": 0.00012,
-    "cache_creation_input_token_cost_above_1hr": 0.00016,
-    "cache_read_input_token_cost": 4e-06,
-    "input_cost_per_audio_token": 0.00024,
-    "input_cost_per_token": 4e-05,
-    "input_cost_per_token_above_200k_tokens": 0.00032,
-    "input_cost_per_token_flex": 6e-05,
-    "input_cost_per_token_priority": 6.8e-05,
-    "litellm_provider": "openai",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+  "gemini-3.8-flash": {
+    "cache_read_input_token_cost": 5.2e-08,
+    "google_maps_grounding_cost_per_query": 0.025,
+    "input_cost_per_audio_token": 1.04e-06,
+    "input_cost_per_token": 5.2e-07,
+    "input_cost_per_token_flex": 2.6e-07,
+    "input_cost_per_token_priority": 6.5e-07,
+    "input_cost_per_video_token": 6.2e-07,
+    "litellm_provider": "vertex_ai-language-models",
+    "max_input_tokens": 1048576,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_audio_token": 0.00028,
-    "output_cost_per_reasoning_token": 0.0002,
-    "output_cost_per_token": 8e-05,
-    "output_cost_per_token_above_200k_tokens": 0.00036,
-    "output_cost_per_token_flex": 0.0001,
-    "output_cost_per_token_priority": 0.000108,
+    "output_cost_per_audio_token": 6.24e-06,
+    "output_cost_per_token": 3.12e-06,
+    "output_cost_per_token_flex": 1.56e-06,
+    "output_cost_per_token_priority": 3.9e-06,
     "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
+      "search_context_size_medium": 0.035
     },
     "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
-  },
-  "gpt-5.5-pro": {
-    "cache_read_input_token_cost": 2e-06,
-    "input_cost_per_token": 2e-05,
-    "input_cost_per_token_above_200k_tokens": 0.00016,
-    "input_cost_per_token_flex": 3e-05,
-    "input_cost_per_token_priority": 3.4e-05,
-    "litellm_provider": "openai",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
-    "mode": "responses",
-    "output_cost_per_reasoning_token": 0.0001,
-    "output_cost_per_token": 4e-05,
-    "output_cost_per_token_above_200k_tokens": 0.00018,
-    "output_cost_per_token_flex": 5e-05,
-    "output_cost_per_token_priority": 5.4e-05,
-    "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
-    },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
-  },
-  "gpt-5.6": {
-    "cache_creation_input_token_cost": 3e-05,
-    "cache_creation_input_token_cost_above_1hr": 4e-05,
-    "cache_read_input_token_cost": 1e-06,
-    "input_cost_per_audio_token": 6e-05,
-    "input_cost_per_token": 1e-05,
-    "input_cost_per_token_above_200k_tokens": 8e-05,
-    "input_cost_per_token_flex": 1.5e-05,
-    "input_cost_per_token_priority": 1.7e-05,
-    "litellm_provider": "openai",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
-    "mode": "chat",
-    "output_cost_per_audio_token": 7e-05,
-    "output_cost_per_reasoning_token": 5e-05,
-    "output_cost_per_token": 2e-05,
-    "output_cost_per_token_above_200k_tokens": 9e-05,
-    "output_cost_per_token_flex": 2.5e-05,
-    "output_cost_per_token_priority": 2.7e-05,
-    "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
-    },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
-  },
-  "meta.llama4-maverick-17b-instruct-v1:0": {
-    "input_cost_per_token": 0.00019,
-    "litellm_provider": "bedrock_converse",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
-    "mode": "chat",
-    "output_cost_per_token": 0.00038,
-    "supports_function_calling": true
+    "web_search_billing_unit": "per_prompt"
   },
   "together_ai/moonshotai/Kimi-K3": {
-    "cache_creation_input_token_cost": 0.00030000000000000003,
-    "cache_creation_input_token_cost_above_1hr": 0.0004,
-    "cache_read_input_token_cost": 9.999999999999999e-06,
-    "input_cost_per_audio_token": 0.0006000000000000001,
-    "input_cost_per_token": 0.0001,
-    "input_cost_per_token_above_200k_tokens": 0.0008,
-    "input_cost_per_token_flex": 0.00015000000000000001,
-    "input_cost_per_token_priority": 0.00017,
+    "input_cost_per_token": 1.15e-06,
     "litellm_provider": "together_ai",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_audio_token": 0.0006999999999999999,
-    "output_cost_per_reasoning_token": 0.0005,
-    "output_cost_per_token": 0.0002,
-    "output_cost_per_token_above_200k_tokens": 0.0009000000000000001,
-    "output_cost_per_token_flex": 0.00025,
-    "output_cost_per_token_priority": 0.00027,
-    "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
-    },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
+    "output_cost_per_token": 3.45e-06,
+    "supports_function_calling": true
   },
   "together_ai/zai-org/GLM-5.3": {
-    "cache_creation_input_token_cost": 0.00033,
-    "cache_creation_input_token_cost_above_1hr": 0.00044,
-    "cache_read_input_token_cost": 1.1e-05,
-    "input_cost_per_audio_token": 0.00066,
-    "input_cost_per_token": 0.00011,
-    "input_cost_per_token_above_200k_tokens": 0.00088,
-    "input_cost_per_token_flex": 0.000165,
-    "input_cost_per_token_priority": 0.000187,
+    "input_cost_per_token": 5.5e-07,
     "litellm_provider": "together_ai",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_audio_token": 0.00077,
-    "output_cost_per_reasoning_token": 0.00055,
-    "output_cost_per_token": 0.00022,
-    "output_cost_per_token_above_200k_tokens": 0.00099,
-    "output_cost_per_token_flex": 0.000275,
-    "output_cost_per_token_priority": 0.000297,
-    "search_context_cost_per_query": {
-      "search_context_size_high": 0.03,
-      "search_context_size_low": 0.01,
-      "search_context_size_medium": 0.02
-    },
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true,
-    "supports_web_search": true
+    "output_cost_per_token": 2.2e-06,
+    "supports_function_calling": true
   },
-  "us.anthropic.claude-opus-5-v1:0": {
-    "cache_creation_input_token_cost": 0.00054,
-    "cache_creation_input_token_cost_above_1hr": 0.00072,
-    "cache_read_input_token_cost": 1.8e-05,
-    "input_cost_per_token": 0.00018,
-    "litellm_provider": "bedrock_converse",
-    "max_input_tokens": 2000000,
-    "max_output_tokens": 128000,
-    "max_tokens": 128000,
+  "fireworks_ai/accounts/fireworks/models/kimi-k3": {
+    "cache_read_input_token_cost": 6e-08,
+    "input_cost_per_token": 6e-07,
+    "litellm_provider": "fireworks_ai",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
     "mode": "chat",
-    "output_cost_per_token": 0.00036,
-    "supports_function_calling": true,
-    "supports_prompt_caching": true,
-    "supports_reasoning": true
+    "output_cost_per_token": 2.5e-06,
+    "supports_function_calling": true
+  },
+  "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
+    "input_cost_per_token": 1.5e-07,
+    "litellm_provider": "fireworks_ai",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
+    "mode": "chat",
+    "output_cost_per_token": 6e-07,
+    "supports_function_calling": true
+  },
+  "fireworks_ai/accounts/fireworks/models/qwen3p8-max": {
+    "cache_read_input_token_cost": 9e-08,
+    "input_cost_per_token": 9e-07,
+    "litellm_provider": "fireworks_ai",
+    "max_input_tokens": 400000,
+    "max_output_tokens": 65536,
+    "max_tokens": 65536,
+    "mode": "chat",
+    "output_cost_per_token": 3.6e-06,
+    "supports_function_calling": true
   }
 }
diff --git a/tests/e2e/models.py b/tests/e2e/models.py
index 98fcc1b1f04..b0ff6fdcd86 100644
--- a/tests/e2e/models.py
+++ b/tests/e2e/models.py
@@ -186,6 +186,18 @@ class ChatMetadata(BaseModel):
 
 class ImageUrl(BaseModel):
     url: str
+    detail: str | None = None
+
+
+class InputAudio(BaseModel):
+    data: str
+    format: str
+
+
+class FileObject(BaseModel):
+    file_data: str | None = None
+    file_id: str | None = None
+    format: str | None = None
 
 
 class TextContentPart(BaseModel):
@@ -199,7 +211,17 @@ class ImageContentPart(BaseModel):
     image_url: ImageUrl
 
 
-ContentPart = TextContentPart | ImageContentPart
+class InputAudioContentPart(BaseModel):
+    type: str = "input_audio"
+    input_audio: InputAudio
+
+
+class FileContentPart(BaseModel):
+    type: str = "file"
+    file: FileObject
+
+
+ContentPart = TextContentPart | ImageContentPart | InputAudioContentPart | FileContentPart
 
 
 class ChatMessage(BaseModel):
@@ -284,6 +306,37 @@ class ChatToolResultTurn(BaseModel):
 type ChatTurn = ChatMessage | ChatAssistantTurn | ChatToolResultTurn
 
 
+class HostedWebSearchTool(BaseModel):
+    """A provider-hosted web-search tool sent inside an OpenAI tools list
+    (Anthropic's ``web_search_20250305`` shape)."""
+
+    type: str
+    name: str
+    max_uses: int | None = None
+
+
+class GoogleSearchTool(BaseModel):
+    googleSearch: dict[str, object] = {}
+
+
+class GoogleMapsTool(BaseModel):
+    googleMaps: dict[str, object] = {}
+
+
+class FileSearchTool(BaseModel):
+    type: Literal["file_search"] = "file_search"
+    vector_store_ids: list[str]
+
+
+class WebSearchOptions(BaseModel):
+    search_context_size: Literal["low", "medium", "high"] | None = None
+
+
+class ChatAudio(BaseModel):
+    voice: str
+    format: str
+
+
 class ChatStreamOptions(BaseModel):
     include_usage: bool
 
@@ -302,10 +355,16 @@ class ChatBody(BaseModel):
     thinking: ThinkingParam | None = None
     service_tier: str | None = None
     prompt_cache_key: str | None = None
-    tools: Sequence[ChatTool | McpChatTool] | None = None
+    tools: Sequence[
+        ChatTool | McpChatTool | HostedWebSearchTool | GoogleSearchTool | GoogleMapsTool | FileSearchTool
+    ] | None = None
     tool_choice: str | None = None
+    modalities: list[str] | None = None
+    audio: ChatAudio | None = None
+    web_search_options: WebSearchOptions | None = None
     guardrails: list[str] | None = None
     response_format: dict[str, object] | None = None
+    allowed_openai_params: list[str] | None = None
     chat_template_kwargs: dict[str, bool] | None = None
     cache: dict[str, bool] | None = {"no-cache": True}