scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-11 03:38:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 83

fix(model_prices): azure gpt-4.1-nano retirement date, together deprecations, novita gpt-oss-120b vision flag, fireworks deepseek-v4-pro-0813

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Devin AI 2026-08-26 16:56:53 +00:00
parent 9300018414
commit d266326a42
3 changed files with 128 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
litellm/model_prices_and_context_window_backup.json
View file

@ -4681,7 +4681,7 @@
"supports_web_search": false
},
"azure/gpt-4.1-nano": {
"deprecation_date": "2026-10-14",
"deprecation_date": "2027-04-14",
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_batches": 5e-08,
@ -4714,7 +4714,7 @@
"supports_vision": true
},
"azure/gpt-4.1-nano-2025-04-14": {
"deprecation_date": "2026-10-14",
"deprecation_date": "2027-04-14",
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_batches": 5e-08,
@ -18577,6 +18577,22 @@
"supports_tool_choice": true,
"supports_vision": false
},
"fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": {
"cache_read_input_token_cost": 4.4e-08,
"input_cost_per_token": 1.32e-06,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 3.96e-06,
"source": "https://docs.fireworks.ai/serverless/pricing",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": false
},
"fireworks_ai/accounts/fireworks/models/firefunction-v2": {
"input_cost_per_token": 9e-07,
"litellm_provider": "fireworks_ai",
@ -38475,6 +38491,7 @@
"supports_tool_choice": true
},
"together_ai/google/gemma-3n-E4B-it": {
"deprecation_date": "2026-08-25",
"input_cost_per_token": 6e-08,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
@ -38510,6 +38527,7 @@
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/meta-llama/Llama-Guard-4-12B": {
"deprecation_date": "2026-08-25",
"input_cost_per_token": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 1048576,
@ -47311,7 +47329,7 @@
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_vision": false,
"supports_system_messages": true,
"supports_response_schema": true,
"supports_reasoning": true

24
model_prices_and_context_window.json
View file

@ -4681,7 +4681,7 @@
"supports_web_search": false
},
"azure/gpt-4.1-nano": {
"deprecation_date": "2026-10-14",
"deprecation_date": "2027-04-14",
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_batches": 5e-08,
@ -4714,7 +4714,7 @@
"supports_vision": true
},
"azure/gpt-4.1-nano-2025-04-14": {
"deprecation_date": "2026-10-14",
"deprecation_date": "2027-04-14",
"cache_read_input_token_cost": 2.5e-08,
"input_cost_per_token": 1e-07,
"input_cost_per_token_batches": 5e-08,
@ -18577,6 +18577,22 @@
"supports_tool_choice": true,
"supports_vision": false
},
"fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": {
"cache_read_input_token_cost": 4.4e-08,
"input_cost_per_token": 1.32e-06,
"litellm_provider": "fireworks_ai",
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
"max_tokens": 131072,
"mode": "chat",
"output_cost_per_token": 3.96e-06,
"source": "https://docs.fireworks.ai/serverless/pricing",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": false
},
"fireworks_ai/accounts/fireworks/models/firefunction-v2": {
"input_cost_per_token": 9e-07,
"litellm_provider": "fireworks_ai",
@ -38475,6 +38491,7 @@
"supports_tool_choice": true
},
"together_ai/google/gemma-3n-E4B-it": {
"deprecation_date": "2026-08-25",
"input_cost_per_token": 6e-08,
"litellm_provider": "together_ai",
"max_input_tokens": 32768,
@ -38510,6 +38527,7 @@
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/meta-llama/Llama-Guard-4-12B": {
"deprecation_date": "2026-08-25",
"input_cost_per_token": 2e-07,
"litellm_provider": "together_ai",
"max_input_tokens": 1048576,
@ -47311,7 +47329,7 @@
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_vision": false,
"supports_system_messages": true,
"supports_response_schema": true,
"supports_reasoning": true

86
tests/test_litellm/test_fireworks_serverless_model_costs.py Normal file
View file

@ -0,0 +1,86 @@
"""
Validate the Fireworks AI Serverless entry added for #37274 exists in
`model_prices_and_context_window.json` and that the bare Fireworks model ID
resolves through `get_model_info`.
Pricing as published at https://docs.fireworks.ai/serverless/pricing
(USD per 1M tokens, uncached input / cached input / output):
accounts/fireworks/models/deepseek-v4-pro-0813 -> $1.32 / $0.044 / $3.96
"""
import json
import os
import pytest
import litellm
from litellm.utils import get_model_info
@pytest.fixture(scope="module", autouse=True)
def _local_model_cost_map():
"""
Point litellm at the bundled cost map for the duration of this module
only. ``mp.undo()`` restores both the environment variable and
``litellm.model_cost`` so nothing leaks into later tests.
"""
mp = pytest.MonkeyPatch()
mp.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
mp.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
get_model_info.cache_clear()
yield
mp.undo()
get_model_info.cache_clear()
NEW_ENTRIES = {
"fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": {
"input_cost_per_token": 1.32e-06,
"cache_read_input_token_cost": 4.4e-08,
"output_cost_per_token": 3.96e-06,
"max_input_tokens": 1048576,
"max_output_tokens": 131072,
},
}
@pytest.fixture(scope="module")
def model_data():
json_path = os.path.join(
os.path.dirname(__file__), "../../model_prices_and_context_window.json"
)
with open(json_path) as f:
return json.load(f)
def test_fireworks_serverless_entries_exist(model_data):
"""The new prefixed entry carries the pricing and metadata from #37274."""
for key, expected in NEW_ENTRIES.items():
assert key in model_data, f"{key} is missing from model_prices_and_context_window.json"
entry = model_data[key]
for field, value in expected.items():
assert entry[field] == pytest.approx(value), f"{key}.{field}"
assert entry["litellm_provider"] == "fireworks_ai"
assert entry["mode"] == "chat"
assert entry["supports_function_calling"] is True
assert entry["supports_vision"] is False
def test_bare_fireworks_ids_resolve_through_prefixed_entries():
"""Bare IDs from #37274 resolve via the provider-prefix lookup path."""
for bare_id, prefixed_key in [
(
"accounts/fireworks/models/deepseek-v4-pro-0813",
"fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813",
),
]:
info = get_model_info(model=bare_id, custom_llm_provider="fireworks_ai")
expected = NEW_ENTRIES[prefixed_key]
assert info.get("key") == prefixed_key
assert info["litellm_provider"] == "fireworks_ai"
assert info["input_cost_per_token"] == pytest.approx(expected["input_cost_per_token"])
assert info["cache_read_input_token_cost"] == pytest.approx(expected["cache_read_input_token_cost"])
assert info["output_cost_per_token"] == pytest.approx(expected["output_cost_per_token"])
assert info["max_input_tokens"] == expected["max_input_tokens"]
assert info["max_output_tokens"] == expected["max_output_tokens"]