scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-18 04:44:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 125

test(cost): bill vertex gemini-3.8-flash reasoning tokens at the reasoning price (#46939)

Browse source 
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-10-16 11:32:34 -07:00 • committed by GitHub
parent f8217d2a03
commit f811a5923e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 3 additions and 58 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

60
tests/integration/cost_calculation/cases/vertex_ai.py
View file

@ -2181,61 +2181,6 @@ GEMINI_3_8_FLASH_GOOGLE_MAPS_GROUNDING: Final = CostTrackingTestCase(
),
)
GEMINI_3_8_FLASH_FALLBACK_REASONING_AT_OUTPUT_RATE: Final = CostTrackingTestCase(
name="gemini-3.8-flash-fallback_reasoning_at_output_rate",
covers="quota_management.spend_tracking.cost_matrix.logs_cost",
model="gemini-3.8-flash",
request={
"model": "$MODEL",
"messages": [
{
"role": "system",
"content": [
{
"type": "text",
"text": "You are a deterministic pricing-harness assistant. Keep answers to a single short line.",
}
],
},
{
"role": "user",
"content": [
{
"type": "text",
"text": "f92946792f44 summarize the attached material in one line and name the city weather",
}
],
},
],
"stream": False,
"reasoning_effort": "medium",
"allowed_openai_params": ["reasoning_effort"],
},
response=JsonResponse(
content_type="application/json",
body={
"candidates": [
{
"content": {"parts": [{"text": "scripted answer f92946792f44"}], "role": "model"},
"finishReason": "STOP",
"index": 0,
}
],
"usageMetadata": {
"promptTokenCount": 1240,
"candidatesTokenCount": 560,
"thoughtsTokenCount": 3480,
"totalTokenCount": 5280,
"promptTokensDetails": [{"modality": "TEXT", "tokenCount": 1240}],
},
"modelVersion": "gemini-3.8-flash",
},
),
expected=ExactExpected(
spend=0.0132496, input_cost=0.0006448, output_cost=0.0126048, prompt_tokens=1240, completion_tokens=4040
),
)
GEMINI_3_8_FLASH_FALLBACK_IMAGE_TOKENS_AT_INPUT_RATE: Final = CostTrackingTestCase(
name="gemini-3.8-flash-fallback_image_tokens_at_input_rate",
covers="quota_management.spend_tracking.cost_matrix.logs_cost",
@ -3020,7 +2965,7 @@ GEMINI_3_8_FLASH_STREAM_FULL_USAGE: Final = CostTrackingTestCase(
),
),
expected=ExactExpected(
spend=0.007460128, input_cost=0.001619488, output_cost=0.00584064, prompt_tokens=8314, completion_tokens=1592
spend=0.006992128, input_cost=0.001619488, output_cost=0.00537264, prompt_tokens=8314, completion_tokens=1592
),
)
@ -3368,7 +3313,7 @@ GEMINI_3_1_PRO_PREVIEW_CACHE_READ: Final = _gemini_case(
ExactExpected(spend=0.00912736, input_cost=0.00411136, output_cost=0.005016, prompt_tokens=12928, completion_tokens=380)
)
GEMINI_3_1_PRO_PREVIEW_REASONING: Final = _gemini_case(
GEMINI_3_8_FLASH_FALLBACK_REASONING_AT_OUTPUT_RATE, "gemini-3.1-pro-preview-reasoning", "gemini-3.1-pro-preview",
GEMINI_3_1_PRO_REASONING, "gemini-3.1-pro-preview-reasoning", "gemini-3.1-pro-preview",
ExactExpected(spend=0.056056, input_cost=0.002728, output_cost=0.053328, prompt_tokens=1240, completion_tokens=4040)
)
GEMINI_3_1_PRO_PREVIEW_TOOL_CALL: Final = _gemini_case(
@ -3410,7 +3355,6 @@ CASES: Final[tuple[CostTrackingTestCase, ...]] = (
GEMINI_3_8_FLASH_SERVICE_TIER_PRIORITY,
GEMINI_3_8_FLASH_WEB_SEARCH_PER_PROMPT,
GEMINI_3_8_FLASH_GOOGLE_MAPS_GROUNDING,
GEMINI_3_8_FLASH_FALLBACK_REASONING_AT_OUTPUT_RATE,
GEMINI_3_8_FLASH_FALLBACK_IMAGE_TOKENS_AT_INPUT_RATE,
GEMINI_3_8_FLASH_STREAM,
GEMINI_3_8_FLASH_STREAM_NO_USAGE,

1
tests/integration/cost_calculation/cost_map.py
View file

@ -579,6 +579,7 @@ COST_MAP_ENTRIES: Final[dict[str, dict[str, JsonValue]]] = {
"mode": "chat",
"output_cost_per_audio_token": 6.24e-06,
"output_cost_per_token": 3.12e-06,
"output_cost_per_reasoning_token": 2.6e-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_medium": 0.035},