audio patch: price per-request models when unit pricing raises (#5)

Speech and transcription price per character/second/token and raise ValueError
when the model declares none of those rates — every Tinfoil per-request model.
The raise aborted cost calculation before the per-request charge was added, so
the gateway wrote spend 0.0 rows. Catch that case for declared per-request
audio models and price the base at 0, leaving the per-request charge as the
whole bill.
This commit is contained in:
inference-bot committed 2026-11-17 09:04:28 +00:00
1 parent 4b6583c3c0
commit df4e154128
1 file changed
+75
+75
View File
@@ -144,6 +144,75 @@ ANCHOR_RETURN = """ region_name=region_name,
except Exception as e: except Exception as e:
raise e""" raise e"""
# The unit-price call. On speech/transcription LiteLLM prices by character,
# second or token and raises ValueError when the model declares none of those
# rates — which is exactly a per-request model. The declaration is then the
# whole bill, so price the base at 0 instead of letting the raise swallow the
# spend log write (issue #5: rows recorded spend 0.0 and the tail patch below
# never ran because the exception aborted the function first).
ANCHOR_COST = """ response_cost = completion_cost(
completion_response=response_object,
model=model,
call_type=call_type,
custom_llm_provider=custom_llm_provider,
optional_params=optional_params,
custom_pricing=custom_pricing,
base_model=base_model,
prompt=prompt,
standard_built_in_tools_params=standard_built_in_tools_params,
litellm_model_name=litellm_model_name,
router_model_id=router_model_id,
litellm_logging_obj=litellm_logging_obj,
service_tier=service_tier,
data_residency=data_residency,
vertex_location=vertex_location,
region_name=region_name,
)"""
PATCHED_COST = """ try:
response_cost = completion_cost(
completion_response=response_object,
model=model,
call_type=call_type,
custom_llm_provider=custom_llm_provider,
optional_params=optional_params,
custom_pricing=custom_pricing,
base_model=base_model,
prompt=prompt,
standard_built_in_tools_params=standard_built_in_tools_params,
litellm_model_name=litellm_model_name,
router_model_id=router_model_id,
litellm_logging_obj=litellm_logging_obj,
service_tier=service_tier,
data_residency=data_residency,
vertex_location=vertex_location,
region_name=region_name,
)
except Exception as _coop_unit_exc:
# CO-OP PATCH (audio per-request cost, 2026-11-17): a model billed
# per request declares no per-character/second/token rate, so
# LiteLLM's unit pricing raises. The per-request charge is the
# whole bill; let the tail patch below add it to a zero base.
_coop_declared_pr = (
_coop_per_request_cost(
model=model,
litellm_model_name=litellm_model_name,
custom_pricing=custom_pricing,
litellm_logging_obj=litellm_logging_obj,
)
if call_type in ("transcription", "atranscription", "speech", "aspeech")
else 0.0
)
if _coop_declared_pr > 0:
print(
f"[coop-audio] unit pricing unavailable ({type(_coop_unit_exc).__name__}); "
f"pricing at declared per-request={_coop_declared_pr!r}",
flush=True,
)
response_cost = 0.0
else:
raise"""
PATCHED_EARLY = """ if provider_response_cost is not None and not custom_pricing: PATCHED_EARLY = """ if provider_response_cost is not None and not custom_pricing:
# CO-OP PATCH (2026-11-16): a provider-reported cost is not the # CO-OP PATCH (2026-11-16): a provider-reported cost is not the
# whole bill on the audio paths. Speech returns here and never # whole bill on the audio paths. Speech returns here and never
@@ -249,6 +318,12 @@ def main() -> int:
patched = source.replace(ANCHOR_DEF, HELPER + ANCHOR_DEF, 1) patched = source.replace(ANCHOR_DEF, HELPER + ANCHOR_DEF, 1)
patched = patched.replace(ANCHOR_RETURN, PATCHED_RETURN, 1) patched = patched.replace(ANCHOR_RETURN, PATCHED_RETURN, 1)
if ANCHOR_COST in patched:
patched = patched.replace(ANCHOR_COST, PATCHED_COST, 1)
print("[coop-patch] unit-price call made per-request tolerant (speech/transcription)")
else:
print("[coop-patch] WARNING unit-price anchor not found; per-request models "
"will still raise and bill $0")
if ANCHOR_EARLY in patched: if ANCHOR_EARLY in patched:
patched = patched.replace(ANCHOR_EARLY, PATCHED_EARLY, 1) patched = patched.replace(ANCHOR_EARLY, PATCHED_EARLY, 1)
print("[coop-patch] early provider-cost return also patched (audio speech)") print("[coop-patch] early provider-cost return also patched (audio speech)")