scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-04 02:31:27 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 122

Add Azure AI Grok 4.20 metadata

Browse source
This commit is contained in:
Emerson Gomes 2026-05-02 14:28:42 -05:00
parent 934ecdca78
commit 51b731a296
No known key found for this signature in database
GPG key ID: D3DF28AB5D1B5E17
3 changed files with 186 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

43
litellm/model_prices_and_context_window_backup.json
View file

@ -6842,6 +6842,49 @@
"supports_tool_choice": true,
"supports_web_search": true
},
"azure_ai/grok-4-20-non-reasoning": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 6e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/grok-4-20-is-now-available-in-microsoft-foundry/4509377",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"azure_ai/grok-4-20-reasoning": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 6e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/grok-4-20-is-now-available-in-microsoft-foundry/4509377",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"azure_ai/grok-code-fast-1": {
"input_cost_per_token": 2e-07,
"litellm_provider": "azure_ai",

43
model_prices_and_context_window.json
View file

@ -6856,6 +6856,49 @@
"supports_tool_choice": true,
"supports_web_search": true
},
"azure_ai/grok-4-20-non-reasoning": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 6e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/grok-4-20-is-now-available-in-microsoft-foundry/4509377",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"azure_ai/grok-4-20-reasoning": {
"input_cost_per_token": 2e-06,
"output_cost_per_token": 6e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 256000,
"max_output_tokens": 256000,
"max_tokens": 256000,
"mode": "chat",
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/grok-4-20-is-now-available-in-microsoft-foundry/4509377",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"azure_ai/grok-code-fast-1": {
"input_cost_per_token": 2e-07,
"litellm_provider": "azure_ai",

100
tests/test_litellm/llms/azure_ai/test_azure_ai_grok_420_metadata.py Normal file
View file

@ -0,0 +1,100 @@
"""
Test Azure AI Grok 4.20 model metadata.
"""
import json
from importlib.resources import files
import pytest
@pytest.fixture(scope="module")
def use_local_model_cost_map():
monkeypatch = pytest.MonkeyPatch()
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
import litellm
from litellm.utils import _invalidate_model_cost_lowercase_map
original_model_cost = litellm.model_cost
litellm.model_cost = json.loads(
files("litellm")
.joinpath("model_prices_and_context_window_backup.json")
.read_text(encoding="utf-8")
)
litellm.get_model_info.cache_clear()
_invalidate_model_cost_lowercase_map()
try:
yield litellm
finally:
litellm.model_cost = original_model_cost
litellm.get_model_info.cache_clear()
_invalidate_model_cost_lowercase_map()
monkeypatch.undo()
@pytest.mark.parametrize(
"model_name,supports_reasoning",
[
("azure_ai/grok-4-20-reasoning", True),
("azure_ai/grok-4-20-non-reasoning", None),
],
)
def test_azure_ai_grok_420_model_info(
use_local_model_cost_map, model_name: str, supports_reasoning
):
model_info = use_local_model_cost_map.get_model_info(model=model_name)
assert model_info["litellm_provider"] == "azure_ai"
assert model_info["mode"] == "chat"
assert model_info["max_input_tokens"] == 256000
assert model_info["max_output_tokens"] == 256000
assert model_info["max_tokens"] == 256000
assert model_info["input_cost_per_token"] == pytest.approx(2e-06)
assert model_info["output_cost_per_token"] == pytest.approx(6e-06)
assert model_info["supports_function_calling"] is True
assert model_info["supports_tool_choice"] is True
assert model_info["supports_vision"] is True
assert model_info["supports_web_search"] is True
assert model_info.get("supports_reasoning") is supports_reasoning
@pytest.mark.parametrize(
"model_name,supports_reasoning",
[
("azure_ai/grok-4-20-reasoning", True),
("azure_ai/grok-4-20-non-reasoning", None),
],
)
def test_azure_ai_grok_420_raw_model_cost_entry(
use_local_model_cost_map, model_name: str, supports_reasoning
):
model_info = use_local_model_cost_map.model_cost[model_name]
assert model_info["supported_modalities"] == ["text", "image"]
assert model_info["supported_output_modalities"] == ["text"]
assert model_info["supports_function_calling"] is True
assert model_info["supports_tool_choice"] is True
assert model_info["supports_vision"] is True
assert model_info["supports_web_search"] is True
assert model_info.get("supports_reasoning") is supports_reasoning
@pytest.mark.parametrize(
"model_name",
["grok-4-20-reasoning", "grok-4-20-non-reasoning"],
)
def test_azure_ai_grok_420_cost_per_token(use_local_model_cost_map, model_name: str):
from litellm.llms.azure_ai.cost_calculator import cost_per_token
from litellm.types.utils import Usage
usage = Usage(
prompt_tokens=1_000_000,
completion_tokens=1_000_000,
total_tokens=2_000_000,
)
prompt_cost, completion_cost = cost_per_token(model=model_name, usage=usage)
assert prompt_cost == pytest.approx(2.0)
assert completion_cost == pytest.approx(6.0)