scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-14 23:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 102

Merge pull request #40976 from BerriAI/litellm_azure_gpt_chat_latest_pricing

Browse source 
feat(pricing): add azure gpt-chat-latest rates and drop retired friendliai llama-3.1 entries
This commit is contained in:
Mateo Wang 2026-09-14 11:21:20 -07:00 • committed by GitHub
commit cab1e113f7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 261 additions and 56 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

139
litellm/model_prices_and_context_window_backup.json
View file

@ -7413,6 +7413,80 @@
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"azure/gpt-chat-latest": {
"cache_read_input_token_cost": 5e-07,
"deprecation_date": "2026-12-02",
"input_cost_per_token": 5e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"reasoning_effort_levels": [
"medium"
],
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"azure/chat-latest": {
"cache_read_input_token_cost": 5e-07,
"deprecation_date": "2026-12-02",
"input_cost_per_token": 5e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"reasoning_effort_levels": [
"medium"
],
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"azure/us/gpt-5.6": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
@ -7679,6 +7753,43 @@
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"azure/us/gpt-chat-latest": {
"cache_read_input_token_cost": 5.5e-07,
"deprecation_date": "2026-12-02",
"input_cost_per_token": 5.5e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"reasoning_effort_levels": [
"medium"
],
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"azure/eu/gpt-5.6": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
@ -23057,34 +23168,6 @@
"output_cost_per_token": 0.0,
"source": "https://fireworks.ai/pricing"
},
"friendliai/meta-llama-3.1-70b-instruct": {
"input_cost_per_token": 6e-07,
"litellm_provider": "friendliai",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"friendliai/meta-llama-3.1-8b-instruct": {
"input_cost_per_token": 1e-07,
"litellm_provider": "friendliai",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 1e-07,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"friendliai/zai-org/GLM-5.3-Flash": {
"litellm_provider": "friendliai",
"max_input_tokens": 1048576,

139
model_prices_and_context_window.json
View file

@ -7413,6 +7413,80 @@
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"azure/gpt-chat-latest": {
"cache_read_input_token_cost": 5e-07,
"deprecation_date": "2026-12-02",
"input_cost_per_token": 5e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"reasoning_effort_levels": [
"medium"
],
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"azure/chat-latest": {
"cache_read_input_token_cost": 5e-07,
"deprecation_date": "2026-12-02",
"input_cost_per_token": 5e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"reasoning_effort_levels": [
"medium"
],
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"azure/us/gpt-5.6": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
@ -7679,6 +7753,43 @@
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"azure/us/gpt-chat-latest": {
"cache_read_input_token_cost": 5.5e-07,
"deprecation_date": "2026-12-02",
"input_cost_per_token": 5.5e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.3e-05,
"reasoning_effort_levels": [
"medium"
],
"source": "https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true,
"supports_web_search": true
},
"azure/eu/gpt-5.6": {
"cache_creation_input_token_cost": 6.875e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
@ -23057,34 +23168,6 @@
"output_cost_per_token": 0.0,
"source": "https://fireworks.ai/pricing"
},
"friendliai/meta-llama-3.1-70b-instruct": {
"input_cost_per_token": 6e-07,
"litellm_provider": "friendliai",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"friendliai/meta-llama-3.1-8b-instruct": {
"input_cost_per_token": 1e-07,
"litellm_provider": "friendliai",
"max_input_tokens": 8192,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 1e-07,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"friendliai/zai-org/GLM-5.3-Flash": {
"litellm_provider": "friendliai",
"max_input_tokens": 1048576,

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

@ -2101,6 +2101,37 @@ def test_generic_cost_per_token_azure_gpt_6_astra_foundry_price_sheet(
assert completion_cost == pytest.approx(zone_multiplier * output_multiplier * completion_tokens * 5e-5)
@pytest.mark.parametrize(
"model,input_rate,cache_read_rate,output_rate",
[
("azure/gpt-chat-latest", 5e-6, 5e-7, 3e-5),
("azure/chat-latest", 5e-6, 5e-7, 3e-5),
("azure/us/gpt-chat-latest", 5.5e-6, 5.5e-7, 3.3e-5),
],
)
def test_generic_cost_per_token_azure_gpt_chat_latest_price_sheet(
_local_model_cost_map, model, input_rate, cache_read_rate, output_rate
):
"""The Azure OpenAI price sheet lists GPT-Chat Latest at $5 input, $0.50 cached input and $30 output per 1M
tokens on Global, and $5.50, $0.55 and $33 on Data Zone. Foundry names the product gpt-chat-latest and the
OpenAI API names the same model chat-latest, so both spellings bill the Global sheet.
"""
prompt_tokens = 100000
cached_tokens = 40000
completion_tokens = 1000
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")
assert prompt_cost == pytest.approx((prompt_tokens - cached_tokens) * input_rate + cached_tokens * cache_read_rate)
assert completion_cost == pytest.approx(completion_tokens * output_rate)
def test_generic_cost_per_token_azure_ai_gpt_6_astra_flex_bills_the_standard_rate(_local_model_cost_map):
usage = Usage(prompt_tokens=1000, completion_tokens=100, total_tokens=1100)

8
tests/test_litellm/test_model_prices_schema.py
View file

@ -221,6 +221,14 @@ def test_chat_latest_declares_the_one_effort_openai_accepts(prices: dict):
assert resolve_supported_reasoning_efforts(prices["chat-latest"], deployment_is_mapped=True) == ("medium",)
@pytest.mark.parametrize("key", ["azure/gpt-chat-latest", "azure/chat-latest", "azure/us/gpt-chat-latest"])
def test_azure_gpt_chat_latest_declares_the_one_effort_azure_accepts(prices: dict, key: str):
"""Azure answers every reasoning_effort on a gpt-chat-latest deployment except medium with
"Unsupported value ... Supported values are: 'medium'", the same fixed level OpenAI's chat-latest
carries, so the Foundry product name and the OpenAI API name both declare that one level."""
assert resolve_supported_reasoning_efforts(prices[key], deployment_is_mapped=True) == ("medium",)
BEDROCK_OPENAI_GPT_MARKERS: Final = ("openai.gpt-5.4", "openai.gpt-5.5", "openai.gpt-5.6", "openai.gpt-6-astra")
BEDROCK_PROVIDERS: Final = frozenset(("bedrock", "bedrock_converse", "bedrock_mantle"))
BEDROCK_ROW_PREFIXES: Final = ("bedrock_mantle/", "us.", "global.")