scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-02 02:11:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 101

fix(ci): skip Vercel AI Gateway models without input pricing

Browse source 
The Vercel AI Gateway models endpoint now returns video, image, and
reranking model entries that lack the standard input/output token
pricing keys (some embedding entries also omit the output key). The
auto_update workflow blew up with a KeyError on row['pricing']['output']
the first time it hit one of those rows.

Skip rows that don't expose an input price, default the output price to
zero when only input is provided (covers embedding models), and read
pricing once into a local to drop the redundant 'pricing in row' guard.

Co-authored-by: Krrish Dholakia <krrish-berri-2@users.noreply.github.com>
This commit is contained in:
Cursor Agent 2026-06-07 01:03:33 +00:00
parent 13924fa1d6
commit 17050cdf06
No known key found for this signature in database
1 changed files with 11 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
.github/workflows/auto_update_price_and_context_window_file.py vendored
View file

@ -85,21 +85,24 @@ def transform_openrouter_data(data):
def transform_vercel_ai_gateway_data(data):
transformed = {}
for row in data:
pricing = row.get("pricing") or {}
if "input" not in pricing:
continue
obj = {
"max_tokens": row["context_window"],
"input_cost_per_token": float(row["pricing"]["input"]),
"output_cost_per_token": float(row["pricing"]["output"]),
"input_cost_per_token": float(pricing["input"]),
"output_cost_per_token": float(pricing.get("output", 0.0)),
'max_output_tokens': row['max_tokens'],
'max_input_tokens': row["context_window"],
}
# Handle cache pricing if available
if "pricing" in row:
if "input_cache_read" in row["pricing"] and row["pricing"]["input_cache_read"] is not None:
obj['cache_read_input_token_cost'] = float(f"{float(row['pricing']['input_cache_read']):e}")
if "input_cache_write" in row["pricing"] and row["pricing"]["input_cache_write"] is not None:
obj['cache_creation_input_token_cost'] = float(f"{float(row['pricing']['input_cache_write']):e}")
if "input_cache_read" in pricing and pricing["input_cache_read"] is not None:
obj['cache_read_input_token_cost'] = float(f"{float(pricing['input_cache_read']):e}")
if "input_cache_write" in pricing and pricing["input_cache_write"] is not None:
obj['cache_creation_input_token_cost'] = float(f"{float(pricing['input_cache_write']):e}")
mode = "embedding" if "embedding" in row["id"].lower() else "chat"