scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-09 22:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 87

feat(registry): add azure_ai/MAI-Thinking-1 from Azure Retail Prices and Foundry docs

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
mateo 2026-09-03 13:43:48 +00:00
parent 55a5f142e6
commit f26407aa8c
3 changed files with 65 additions and 1 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

@ -9713,6 +9713,30 @@
"/v1/images/generations"
]
},
"azure_ai/MAI-Thinking-1": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 256000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 8e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
"supported_endpoints": [
"/v1/chat/completions"
],
"supported_modalities": [
"text"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/Llama-3.2-11B-Vision-Instruct": {
"deprecation_date": "2026-06-13",
"input_cost_per_token": 3.7e-07,

24
model_prices_and_context_window.json
View file

@ -9713,6 +9713,30 @@
"/v1/images/generations"
]
},
"azure_ai/MAI-Thinking-1": {
"cache_read_input_token_cost": 2e-07,
"input_cost_per_token": 2e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 256000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 8e-06,
"source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure",
"supported_endpoints": [
"/v1/chat/completions"
],
"supported_modalities": [
"text"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"azure_ai/Llama-3.2-11B-Vision-Instruct": {
"deprecation_date": "2026-06-13",
"input_cost_per_token": 3.7e-07,

18
tests/test_litellm/llms/azure_ai/test_azure_ai_cost_calculator.py
View file

@ -501,7 +501,7 @@ class TestAzureAIServiceTierCostCalculation:
assert flex_completion < standard_completion
def test_codestral_2501_model_info_and_cost():
def test_codestral_2501_model_info_and_cost(local_model_cost_map):
model_info = get_model_info(model="Codestral-2501", custom_llm_provider="azure_ai")
usage = Usage(prompt_tokens=1_000_000, completion_tokens=1_000_000, total_tokens=2_000_000)
@ -512,3 +512,19 @@ def test_codestral_2501_model_info_and_cost():
assert model_info["max_output_tokens"] == 4096
assert prompt_cost == pytest.approx(0.3)
assert completion_cost == pytest.approx(0.9)
def test_mai_thinking_1_model_info_and_cost(local_model_cost_map):
model_info = get_model_info(model="MAI-Thinking-1", custom_llm_provider="azure_ai")
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="MAI-Thinking-1", usage=usage)
assert model_info["mode"] == "chat"
assert model_info["max_input_tokens"] == 256000
assert model_info["max_output_tokens"] == 64000
assert model_info["cache_read_input_token_cost"] == pytest.approx(2e-07)
assert model_info["supports_reasoning"] is True
assert model_info["supports_function_calling"] is True
assert prompt_cost == pytest.approx(2.0)
assert completion_cost == pytest.approx(8.0)