scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-30 01:52:18 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 70

fix(sail): restore pinstripes cost rows and tidy tests

Browse source
This commit is contained in:
shrey kharbanda 2026-09-24 00:48:44 +00:00
parent c6e5d0fadd
commit fdcccc674a
3 changed files with 56 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

26
litellm/model_prices_and_context_window_backup.json
View file

@ -58142,6 +58142,32 @@
"supports_vision": true,
"source": "https://docs.sailresearch.com/models"
},
"pinstripes/ps/deepseek-v4-flash": {
"max_tokens": 163840,
"max_input_tokens": 163840,
"max_output_tokens": 163840,
"input_cost_per_token": 1e-07,
"output_cost_per_token": 2e-07,
"litellm_provider": "pinstripes",
"mode": "chat",
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": true,
"source": "https://pinstripes.io/"
},
"pinstripes/ps/minimax-m2.7": {
"max_tokens": 1000192,
"max_input_tokens": 1000192,
"max_output_tokens": 1000192,
"input_cost_per_token": 2.55e-07,
"output_cost_per_token": 5.5e-07,
"litellm_provider": "pinstripes",
"mode": "chat",
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": false,
"source": "https://pinstripes.io/"
},
"darkbloom/gemma-4-26b": {
"input_cost_per_token": 3e-08,
"litellm_provider": "darkbloom",

26
model_prices_and_context_window.json
View file

@ -58142,6 +58142,32 @@
"supports_vision": true,
"source": "https://docs.sailresearch.com/models"
},
"pinstripes/ps/deepseek-v4-flash": {
"max_tokens": 163840,
"max_input_tokens": 163840,
"max_output_tokens": 163840,
"input_cost_per_token": 1e-07,
"output_cost_per_token": 2e-07,
"litellm_provider": "pinstripes",
"mode": "chat",
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": true,
"source": "https://pinstripes.io/"
},
"pinstripes/ps/minimax-m2.7": {
"max_tokens": 1000192,
"max_input_tokens": 1000192,
"max_output_tokens": 1000192,
"input_cost_per_token": 2.55e-07,
"output_cost_per_token": 5.5e-07,
"litellm_provider": "pinstripes",
"mode": "chat",
"supports_function_calling": true,
"supports_assistant_prefill": true,
"supports_reasoning": false,
"source": "https://pinstripes.io/"
},
"darkbloom/gemma-4-26b": {
"input_cost_per_token": 3e-08,
"litellm_provider": "darkbloom",

16
tests/test_litellm/llms/openai_like/test_sail_provider.py
View file

@ -1,17 +1,13 @@
"""
Tests for the Sail (sailresearch.com) JSON-configured provider.
Each test asserts the outbound HTTP request that litellm would send to Sail,
via a mocked httpx transport, rather than asserting registry contents.
"""
"""Tests for the Sail (sailresearch.com) JSON-configured provider."""
import json
import httpx
import pytest
import respx
import litellm
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
from litellm.types.utils import PromptTokensDetailsWrapper, Usage
SAIL_BASE_URL = "https://api.sailresearch.com/v1"
SAIL_CHAT_COMPLETIONS = f"{SAIL_BASE_URL}/chat/completions"
@ -79,7 +75,7 @@ def _responses_payload() -> dict:
@pytest.fixture(autouse=True)
def _sail_env(monkeypatch: pytest.MonkeyPatch):
litellm.disable_aiohttp_transport = True
monkeypatch.setattr(litellm, "disable_aiohttp_transport", True)
monkeypatch.setenv("SAIL_API_KEY", "sk-sail-test")
monkeypatch.delenv("SAIL_API_BASE", raising=False)
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
@ -101,8 +97,6 @@ class TestSailRequestShape:
assert request.url == SAIL_CHAT_COMPLETIONS
assert request.headers["Authorization"] == "Bearer sk-sail-test"
from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
_, provider, _, _ = get_llm_provider(
model=MODEL, custom_llm_provider=None, api_base=None, api_key=None
)
@ -229,8 +223,6 @@ class TestSailRequestShape:
class TestSailCostTracking:
def test_cached_tokens_billed_at_sail_cache_read_rate(self, monkeypatch: pytest.MonkeyPatch):
from litellm.types.utils import PromptTokensDetailsWrapper, Usage
rates = litellm.model_cost[MODEL]
prompt_tokens = 1000
cached_tokens = 600