metergraph-core 0.7.1__tar.gz → 0.7.4__tar.gz

{metergraph_core-0.7.1/src/metergraph_core.egg-info → metergraph_core-0.7.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: metergraph-core
-Version: 0.7.1
+Version: 0.7.4
 Summary: Open, effective-dated LLM pricing catalog and deterministic cost calculator for popular models across major providers and gateways, including OpenAI, Anthropic, Google Gemini, AWS Bedrock, OpenRouter, Vercel AI Gateway, and more.
 Author: Metergraph
 License-Expression: Apache-2.0
@@ -179,6 +179,14 @@ of the applied price. The bundled catalog is USD. `cost` and
 `components.input`, `output`, `cache_read`, `cache_write` and `request` are in
 that currency; the older `cost_usd` and `*_usd` names return the same values.
 
+`ModelUsage(batch=True)`, or `batch=True` on `price` and `cost`, bills at the
+row's batch input and output rates. Its cache reads bill at
+`Price.batch_cache_read_per_mtok` when the row has one, and otherwise at the
+standard `cache_read_per_mtok`, as before. A standard call always uses the
+standard cache-read rate. A row with only a batch cache rate fully prices a
+cached batch call, while a cached standard call on it is `partial` with
+`cache_read_rate_unavailable`.
+
 A `ModelUsage` count left `None` is unknown, not zero. A missing input or
 output count keeps the subtotal that is known, marks the result `partial`, and
 lists `input_tokens` or `output_tokens` in `missing_dimensions`.
@@ -242,7 +250,8 @@ The price in effect when the response was created applies, from `created`,
 creation time is priced now. `catalog=` costs against a catalog you loaded;
 the default is the bundled one.
 
-A batch service tier bills at batch rates. Pass `service_tier=` when the
+A batch service tier bills at batch rates, with cache reads priced as for
+`ModelUsage(batch=True)` above. Pass `service_tier=` when the
 response does not state its tier, such as an OpenAI batch output line. Any other tier besides standard,
 such as `priority` or `flex`, returns `partial` with `service_tier` in
 `missing_dimensions`, since the catalog carries no tier rates. Cost a streamed

{metergraph_core-0.7.1 → metergraph_core-0.7.4}/README.md

@@ -149,6 +149,14 @@ of the applied price. The bundled catalog is USD. `cost` and
 `components.input`, `output`, `cache_read`, `cache_write` and `request` are in
 that currency; the older `cost_usd` and `*_usd` names return the same values.
 
+`ModelUsage(batch=True)`, or `batch=True` on `price` and `cost`, bills at the
+row's batch input and output rates. Its cache reads bill at
+`Price.batch_cache_read_per_mtok` when the row has one, and otherwise at the
+standard `cache_read_per_mtok`, as before. A standard call always uses the
+standard cache-read rate. A row with only a batch cache rate fully prices a
+cached batch call, while a cached standard call on it is `partial` with
+`cache_read_rate_unavailable`.
+
 A `ModelUsage` count left `None` is unknown, not zero. A missing input or
 output count keeps the subtotal that is known, marks the result `partial`, and
 lists `input_tokens` or `output_tokens` in `missing_dimensions`.
@@ -212,7 +220,8 @@ The price in effect when the response was created applies, from `created`,
 creation time is priced now. `catalog=` costs against a catalog you loaded;
 the default is the bundled one.
 
-A batch service tier bills at batch rates. Pass `service_tier=` when the
+A batch service tier bills at batch rates, with cache reads priced as for
+`ModelUsage(batch=True)` above. Pass `service_tier=` when the
 response does not state its tier, such as an OpenAI batch output line. Any other tier besides standard,
 such as `priority` or `flex`, returns `partial` with `service_tier` in
 `missing_dimensions`, since the catalog carries no tier rates. Cost a streamed

{metergraph_core-0.7.1 → metergraph_core-0.7.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "metergraph-core"
-version = "0.7.1"
+version = "0.7.4"
 description = "Open, effective-dated LLM pricing catalog and deterministic cost calculator for popular models across major providers and gateways, including OpenAI, Anthropic, Google Gemini, AWS Bedrock, OpenRouter, Vercel AI Gateway, and more."
 readme = "README.md"
 license = "Apache-2.0"

{metergraph_core-0.7.1 → metergraph_core-0.7.4}/src/metergraph_core/catalog.py

@@ -225,6 +225,22 @@ class Price:
     # The currency every rate on this row is stated in. The `_usd` names on
     # rates and results predate it and are kept for existing callers.
     currency: str = "USD"
+    # The rate a batch call's cache reads bill at, when the provider publishes
+    # one. Absent, batch cache reads keep the standard cache-read rate; it is
+    # never inferred from another rate.
+    batch_cache_read_per_mtok: Decimal | None = None
+
+    def __post_init__(self) -> None:
+        # The loader checks the rate it reads, but a row built or replaced
+        # directly must not bill a negative or undefined cache component.
+        rate = self.batch_cache_read_per_mtok
+        if rate is not None and not (
+            isinstance(rate, Decimal) and rate.is_finite() and rate >= 0
+        ):
+            raise ValueError(
+                "batch_cache_read_per_mtok must be a finite non-negative "
+                f"Decimal or None, not {rate!r}"
+            )
 
 
 @dataclass(frozen=True, slots=True)
@@ -353,6 +369,7 @@ def _billed_terms(resolved: ResolvedPrice) -> tuple[Any, ...]:
         price.cache_write_1h_per_mtok,
         price.batch_input_per_mtok,
         price.batch_output_per_mtok,
+        price.batch_cache_read_per_mtok,
         price.request_fee_per_1k_usd,
         resolved.rules,
     )
@@ -505,12 +522,17 @@ def _price_tokens(
 
     input_rate = price.input_per_mtok
     output_rate = price.output_per_mtok
+    cache_read_rate = price.cache_read_per_mtok
     if batch:
         if price.batch_input_per_mtok is None or price.batch_output_per_mtok is None:
             reasons.append("batch_rate_unavailable")
         else:
             input_rate = price.batch_input_per_mtok
             output_rate = price.batch_output_per_mtok
+        # A row without a batch cache rate keeps billing batch cache reads at
+        # the standard rate, as it always has.
+        if price.batch_cache_read_per_mtok is not None:
+            cache_read_rate = price.batch_cache_read_per_mtok
 
     input_multiplier = Decimal("1")
     output_multiplier = Decimal("1")
@@ -547,12 +569,12 @@ def _price_tokens(
     else:
         output_usd = Decimal(output_count) * output_rate * output_multiplier / _MILLION
     if cache_read_count:
-        if price.cache_read_per_mtok is None:
+        if cache_read_rate is None:
             reasons.append("cache_read_rate_unavailable")
         else:
             cache_read_usd = (
                 Decimal(cache_read_count)
-                * price.cache_read_per_mtok
+                * cache_read_rate
                 * input_multiplier
                 / _MILLION
             )

{metergraph_core-0.7.1 → metergraph_core-0.7.4}/src/metergraph_core/catalog_delta.py

@@ -45,6 +45,7 @@ RATE_FIELDS = (
     "cache_write_1h_per_mtok",
     "batch_input_per_mtok",
     "batch_output_per_mtok",
+    "batch_cache_read_per_mtok",
     "request_fee_per_1k_usd",
 )
 _PRICE_FIELDS = frozenset(

{metergraph_core-0.7.1 → metergraph_core-0.7.4}/src/metergraph_core/data/prices.yaml

@@ -6,9 +6,9 @@
 #
 # Community updates welcome: add an alias or price entry with its provider
 # source_url and open a PR. CI validates structure and date overlaps.
-version: "2026-10-23"
+version: "2026-10-25"
 currency: USD
-pricing_verified_at: "2026-10-23"
+pricing_verified_at: "2026-10-25"
 models:
   - canonical_id: openai/gpt-6-sol
     publisher: openai
@@ -1599,18 +1599,32 @@ models:
       - channel: google-api
         region: global
         effective_from: "2026-10-13"
-        effective_to: "2026-12-01"
+        effective_to: "2026-10-25"
         input_per_mtok: 2.00
         output_per_mtok: 10.00
         cache_read_per_mtok: 0.10
         source_url: https://ai.google.dev/gemini-api/docs/generate-content/latest-model
+      - channel: google-api
+        region: global
+        effective_from: "2026-10-25"
+        effective_to: "2026-12-01"
+        input_per_mtok: 2.00
+        output_per_mtok: 10.00
+        cache_read_per_mtok: 0.10
+        batch_input_per_mtok: 1.00
+        batch_output_per_mtok: 5.00
+        batch_cache_read_per_mtok: 0.05
+        source_url: https://ai.google.dev/gemini-api/docs/pricing
       - channel: google-api
         region: global
         effective_from: "2026-12-01"
         input_per_mtok: 4.00
         output_per_mtok: 20.00
         cache_read_per_mtok: 0.20
-        source_url: https://ai.google.dev/gemini-api/docs/generate-content/latest-model
+        batch_input_per_mtok: 2.00
+        batch_output_per_mtok: 10.00
+        batch_cache_read_per_mtok: 0.10
+        source_url: https://ai.google.dev/gemini-api/docs/pricing
       - channel: vercel-ai-gateway
         region: global
         effective_from: "2026-10-13"
@@ -2506,15 +2520,24 @@ models:
         rules:
           uncaptured_fees: true
         source_url: https://docs.perplexity.ai/docs/getting-started/pricing
-      # The gateway bills Sonar's built-in search per call, so the row carries
-      # it as a request fee and the call is priced in full.
       - channel: vercel-ai-gateway
         region: global
         effective_from: "2026-10-11"
+        effective_to: "2026-10-24"
         input_per_mtok: 0.25
         output_per_mtok: 2.50
         request_fee_per_1k_usd: 2.50
         source_url: https://vercel.com/ai-gateway/models/sonar
+      # The gateway lists Sonar's web searches as a charge of their own, billed
+      # per search and not per request, so no request fee applies.
+      - channel: vercel-ai-gateway
+        region: global
+        effective_from: "2026-10-24"
+        input_per_mtok: 0.25
+        output_per_mtok: 2.50
+        rules:
+          uncaptured_fees: true
+        source_url: https://vercel.com/ai-gateway/models/sonar
 
   - canonical_id: openai/gpt-5-mini
     publisher: openai

{metergraph_core-0.7.1 → metergraph_core-0.7.4}/src/metergraph_core/loader.py

@@ -388,6 +388,17 @@ def parse_catalog(
                         f"{canonical}: overlapping {channel}/{region} price windows"
                     )
             seen_windows.append((channel, region, effective_from, effective_to))
+            batch_cache_read = price.get("batch_cache_read_per_mtok")
+            batch_cache_read_per_mtok = _decimal(batch_cache_read)
+            # A stated batch cache rate replaces the standard one on batch
+            # calls, so one that cannot be read must not quietly fall back.
+            if batch_cache_read is not None and (
+                batch_cache_read_per_mtok is None or batch_cache_read_per_mtok < 0
+            ):
+                raise CatalogError(
+                    f"{canonical}: invalid batch_cache_read_per_mtok "
+                    f"{batch_cache_read!r}"
+                )
             prices.append(
                 Price(
                     id=f"{canonical}:{channel}:{region}:{_id_date(effective_from)}",
@@ -412,6 +423,7 @@ def parse_catalog(
                     source_url=str(price["source_url"]).strip(),
                     publisher=publisher,
                     currency=currency,
+                    batch_cache_read_per_mtok=batch_cache_read_per_mtok,
                 )
             )
     return version, {key: tuple(value) for key, value in aliases.items()}, _unique_ids(prices)

{metergraph_core-0.7.1 → metergraph_core-0.7.4/src/metergraph_core.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: metergraph-core
-Version: 0.7.1
+Version: 0.7.4
 Summary: Open, effective-dated LLM pricing catalog and deterministic cost calculator for popular models across major providers and gateways, including OpenAI, Anthropic, Google Gemini, AWS Bedrock, OpenRouter, Vercel AI Gateway, and more.
 Author: Metergraph
 License-Expression: Apache-2.0
@@ -179,6 +179,14 @@ of the applied price. The bundled catalog is USD. `cost` and
 `components.input`, `output`, `cache_read`, `cache_write` and `request` are in
 that currency; the older `cost_usd` and `*_usd` names return the same values.
 
+`ModelUsage(batch=True)`, or `batch=True` on `price` and `cost`, bills at the
+row's batch input and output rates. Its cache reads bill at
+`Price.batch_cache_read_per_mtok` when the row has one, and otherwise at the
+standard `cache_read_per_mtok`, as before. A standard call always uses the
+standard cache-read rate. A row with only a batch cache rate fully prices a
+cached batch call, while a cached standard call on it is `partial` with
+`cache_read_rate_unavailable`.
+
 A `ModelUsage` count left `None` is unknown, not zero. A missing input or
 output count keeps the subtotal that is known, marks the result `partial`, and
 lists `input_tokens` or `output_tokens` in `missing_dimensions`.
@@ -242,7 +250,8 @@ The price in effect when the response was created applies, from `created`,
 creation time is priced now. `catalog=` costs against a catalog you loaded;
 the default is the bundled one.
 
-A batch service tier bills at batch rates. Pass `service_tier=` when the
+A batch service tier bills at batch rates, with cache reads priced as for
+`ModelUsage(batch=True)` above. Pass `service_tier=` when the
 response does not state its tier, such as an OpenAI batch output line. Any other tier besides standard,
 such as `priority` or `flex`, returns `partial` with `service_tier` in
 `missing_dimensions`, since the catalog carries no tier rates. Cost a streamed