laantungir/routstr-core
1
0
Fork 0
mirror of https://github.com/Routstr/routstr-core.git synced 2026-08-09 02:54:37 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor(payment): extract litellm_cost_entry lookup helper

Browse Source 
Pull the litellm model_cost lookup (both id spellings + case-insensitive
fallback) out of backfill_cache_pricing into a reusable litellm_cost_entry
helper. No behaviour change; the upstream price resolver reuses the same
lookup semantics.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Jeroen Ubbink
2026-07-03 14:42:17 +02:00
co-authored by Claude Opus 4.8
parent b7fcf000af
commit ffde661d93
1 changed files with 27 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files
routstr/payment/models.py
+27 -28
View File
@@ -85,6 +85,30 @@ class Model(BaseModel):
return hash(self.id)
def litellm_cost_entry(model_id: str) -> dict | None:
"""Look up ``model_id`` in litellm's bundled cost map.
litellm ships per-model USD rates keyed by the exact OpenRouter id
(``deepseek/deepseek-chat``) or the bare model name (``gpt-4o``,
``claude-sonnet-4-5``), so both spellings are tried. Keys are lowercase, so
a mixed-case upstream id (``deepseek-ai/DeepSeek-V4-Flash``) is retried via
a case-insensitive scan. Returns the matched cost dict, or ``None``.
"""
import litellm
candidates = (model_id, model_id.split("/", 1)[-1])
for key in candidates:
info = litellm.model_cost.get(key)
if isinstance(info, dict):
return info
lowered = {c.lower() for c in candidates}
for key, info in litellm.model_cost.items():
if isinstance(key, str) and key.lower() in lowered and isinstance(info, dict):
return info
return None
def backfill_cache_pricing(model_id: str, pricing: Pricing) -> Pricing:
"""Fill missing cache rates from litellm's bundled cost map.
@@ -92,12 +116,8 @@ def backfill_cache_pricing(model_id: str, pricing: Pricing) -> Pricing:
for many models (most DeepSeek entries, openai/gpt-4o, ...). Without a
cache rate, billing falls back to the full input rate, which overcharges
cache reads (DeepSeek hits are 10x cheaper) and undercharges Anthropic
cache writes (1.25x). litellm ships per-model USD rates keyed by the exact
OpenRouter id (deepseek/deepseek-chat) or by the bare model name
(gpt-4o, claude-sonnet-4-5), so both spellings are tried. litellm keys are
lowercase, but a generic upstream may report a mixed-case id
(``deepseek-ai/DeepSeek-V4-Flash``); an exact match is attempted first, then
a case-insensitive fallback so such ids still resolve.
cache writes (1.25x). The lookup (see ``litellm_cost_entry``) tries both
id spellings and a case-insensitive fallback.
Rates already present (e.g. provided by OpenRouter) are authoritative and
never overwritten. Unknown models are returned unchanged.
@@ -107,28 +127,7 @@ def backfill_cache_pricing(model_id: str, pricing: Pricing) -> Pricing:
if not (needs_read or needs_write):
return pricing
import litellm
candidates = (model_id, model_id.split("/", 1)[-1])
info: dict | None = None
for key in candidates:
candidate = litellm.model_cost.get(key)
if isinstance(candidate, dict):
info = candidate
break
if info is None:
# Case-insensitive fallback: a mixed-case upstream id (e.g.
# ``deepseek-ai/DeepSeek-V4-Flash``) won't match litellm's lowercase
# keys exactly. Build a lowercased index once and retry.
lowered = {c.lower() for c in candidates}
for key, candidate in litellm.model_cost.items():
if (
isinstance(key, str)
and key.lower() in lowered
and isinstance(candidate, dict)
):
info = candidate
break
info = litellm_cost_entry(model_id)
if info is None:
return pricing