scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-11 08:38:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 359

chore(cost-map): openai context fixes, azure gpt-6 flex pricing, bedrock govcloud and gmi rows (#50082)

Browse source 
* chore(cost-map): set openai gpt-5.6-cyber and Daybreak Red max input to 272K and source the sora-2-pro-high-res deprecation

* Absorb GovCloud Bedrock, Azure GPT-6 Flex and GMI registry rows

Roll the verified registry data and Azure Flex cost coverage into the rolling price sync

Co-authored-by: kerry-berri <326648561+kerry-berri@users.noreply.github.com>

Co-authored-by: dguthruf <102602010+danielguthruf@users.noreply.github.com>

Co-authored-by: hisamotodev <hisamotodev@users.noreply.github.com>
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: hisamotodev <hisamotodev@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-11-04 13:23:26 -08:00 • committed by GitHub
parent e39caf7bf8
commit 1967b41368
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 2545 additions and 126 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1320
litellm/model_prices_and_context_window_backup.json
View file

File diff suppressed because it is too large Load diff

1320
model_prices_and_context_window.json
View file

File diff suppressed because it is too large Load diff

31
tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -4310,6 +4310,37 @@ def test_azure_gpt_6_foundry_price_sheet(_local_model_cost_map, model_base):
assert azure_eu_info[field] == pytest.approx(1.2 * base)
@pytest.mark.parametrize("model", ["azure/gpt-6-luna", "azure/gpt-6-luna-2026-09-22"])
@pytest.mark.parametrize(
("prompt_tokens", "input_rate", "cache_read_rate", "output_rate"),
[
(100_000, 5e-08, 5e-09, 2.5e-07),
(300_000, 1e-07, 1e-08, 3.75e-07),
],
)
def test_generic_cost_per_token_azure_gpt_6_luna_flex_tiers(
_local_model_cost_map, model, prompt_tokens, input_rate, cache_read_rate, output_rate
):
"""azure/gpt-6-luna bills Azure's Flex Global rates, half of Standard, with the long context step past 272K."""
cached_tokens = 20_000
completion_tokens = 1_000
usage = Usage(
prompt_tokens=prompt_tokens,
completion_tokens=completion_tokens,
total_tokens=prompt_tokens + completion_tokens,
prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=cached_tokens),
)
prompt_cost, completion_cost = generic_cost_per_token(
model=model,
usage=usage,
custom_llm_provider="azure",
service_tier="flex",
)
expected_prompt = (prompt_tokens - cached_tokens) * input_rate + cached_tokens * cache_read_rate
assert prompt_cost == pytest.approx(expected_prompt)
assert completion_cost == pytest.approx(completion_tokens * output_rate)
@pytest.mark.parametrize("region_prefix", ["azure/", "azure/us/", "azure/eu/"])
def test_azure_gpt_5_6_alias_matches_sol_pricing(_local_model_cost_map, region_prefix):
"""The bare gpt-5.6 alias routes to GPT-5.6 Sol, so every Azure region must bill the