mirror of
https://github.com/BerriAI/litellm.git
synced 2026-10-19 04:54:37 +00:00
fix(pricing): add undated azure/gpt-audio-mini and azure/gpt-realtime-mini aliases
This commit is contained in:
Devin AI
parent
b200d664ee
commit
c90ce2bd57
3 changed files with 165 additions and 0 deletions
|
|
@ -4509,6 +4509,37 @@
|
|||
"supports_tool_choice": true,
|
||||
"supports_vision": false
|
||||
},
|
||||
"azure/gpt-audio-mini": {
|
||||
"input_cost_per_audio_token": 1e-05,
|
||||
"input_cost_per_token": 6e-07,
|
||||
"litellm_provider": "azure",
|
||||
"max_input_tokens": 128000,
|
||||
"max_output_tokens": 16384,
|
||||
"max_tokens": 16384,
|
||||
"mode": "chat",
|
||||
"output_cost_per_audio_token": 2e-05,
|
||||
"output_cost_per_token": 2.4e-06,
|
||||
"supported_endpoints": [
|
||||
"/v1/chat/completions"
|
||||
],
|
||||
"supported_modalities": [
|
||||
"text",
|
||||
"audio"
|
||||
],
|
||||
"supported_output_modalities": [
|
||||
"text",
|
||||
"audio"
|
||||
],
|
||||
"supports_function_calling": true,
|
||||
"supports_native_streaming": true,
|
||||
"supports_parallel_function_calling": true,
|
||||
"supports_prompt_caching": false,
|
||||
"supports_reasoning": false,
|
||||
"supports_response_schema": false,
|
||||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": false
|
||||
},
|
||||
"azure/gpt-audio-mini-2025-10-06": {
|
||||
"input_cost_per_audio_token": 1e-05,
|
||||
"input_cost_per_token": 6e-07,
|
||||
|
|
@ -4717,6 +4748,38 @@
|
|||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"azure/gpt-realtime-mini": {
|
||||
"cache_creation_input_audio_token_cost": 3e-07,
|
||||
"cache_read_input_token_cost": 6e-08,
|
||||
"input_cost_per_audio_token": 1e-05,
|
||||
"input_cost_per_image": 8e-07,
|
||||
"input_cost_per_token": 6e-07,
|
||||
"litellm_provider": "azure",
|
||||
"max_input_tokens": 32000,
|
||||
"max_output_tokens": 4096,
|
||||
"max_tokens": 4096,
|
||||
"mode": "chat",
|
||||
"output_cost_per_audio_token": 2e-05,
|
||||
"output_cost_per_token": 2.4e-06,
|
||||
"supported_endpoints": [
|
||||
"/v1/realtime"
|
||||
],
|
||||
"supported_modalities": [
|
||||
"text",
|
||||
"image",
|
||||
"audio"
|
||||
],
|
||||
"supported_output_modalities": [
|
||||
"text",
|
||||
"audio"
|
||||
],
|
||||
"supports_audio_input": true,
|
||||
"supports_audio_output": true,
|
||||
"supports_function_calling": true,
|
||||
"supports_parallel_function_calling": true,
|
||||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"azure/gpt-realtime-mini-2025-10-06": {
|
||||
"cache_creation_input_audio_token_cost": 3e-07,
|
||||
"cache_read_input_token_cost": 6e-08,
|
||||
|
|
|
|||
|
|
@ -4509,6 +4509,37 @@
|
|||
"supports_tool_choice": true,
|
||||
"supports_vision": false
|
||||
},
|
||||
"azure/gpt-audio-mini": {
|
||||
"input_cost_per_audio_token": 1e-05,
|
||||
"input_cost_per_token": 6e-07,
|
||||
"litellm_provider": "azure",
|
||||
"max_input_tokens": 128000,
|
||||
"max_output_tokens": 16384,
|
||||
"max_tokens": 16384,
|
||||
"mode": "chat",
|
||||
"output_cost_per_audio_token": 2e-05,
|
||||
"output_cost_per_token": 2.4e-06,
|
||||
"supported_endpoints": [
|
||||
"/v1/chat/completions"
|
||||
],
|
||||
"supported_modalities": [
|
||||
"text",
|
||||
"audio"
|
||||
],
|
||||
"supported_output_modalities": [
|
||||
"text",
|
||||
"audio"
|
||||
],
|
||||
"supports_function_calling": true,
|
||||
"supports_native_streaming": true,
|
||||
"supports_parallel_function_calling": true,
|
||||
"supports_prompt_caching": false,
|
||||
"supports_reasoning": false,
|
||||
"supports_response_schema": false,
|
||||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true,
|
||||
"supports_vision": false
|
||||
},
|
||||
"azure/gpt-audio-mini-2025-10-06": {
|
||||
"input_cost_per_audio_token": 1e-05,
|
||||
"input_cost_per_token": 6e-07,
|
||||
|
|
@ -4717,6 +4748,38 @@
|
|||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"azure/gpt-realtime-mini": {
|
||||
"cache_creation_input_audio_token_cost": 3e-07,
|
||||
"cache_read_input_token_cost": 6e-08,
|
||||
"input_cost_per_audio_token": 1e-05,
|
||||
"input_cost_per_image": 8e-07,
|
||||
"input_cost_per_token": 6e-07,
|
||||
"litellm_provider": "azure",
|
||||
"max_input_tokens": 32000,
|
||||
"max_output_tokens": 4096,
|
||||
"max_tokens": 4096,
|
||||
"mode": "chat",
|
||||
"output_cost_per_audio_token": 2e-05,
|
||||
"output_cost_per_token": 2.4e-06,
|
||||
"supported_endpoints": [
|
||||
"/v1/realtime"
|
||||
],
|
||||
"supported_modalities": [
|
||||
"text",
|
||||
"image",
|
||||
"audio"
|
||||
],
|
||||
"supported_output_modalities": [
|
||||
"text",
|
||||
"audio"
|
||||
],
|
||||
"supports_audio_input": true,
|
||||
"supports_audio_output": true,
|
||||
"supports_function_calling": true,
|
||||
"supports_parallel_function_calling": true,
|
||||
"supports_system_messages": true,
|
||||
"supports_tool_choice": true
|
||||
},
|
||||
"azure/gpt-realtime-mini-2025-10-06": {
|
||||
"cache_creation_input_audio_token_cost": 3e-07,
|
||||
"cache_read_input_token_cost": 6e-08,
|
||||
|
|
|
|||
|
|
@ -754,6 +754,45 @@ def test_realtime_transcription_duration_cost_resolves_model_from_litellm_name(
|
|||
assert abs(cost - 120.0 * (0.017 / 60)) < 1e-9
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"undated, dated",
|
||||
[
|
||||
("azure/gpt-audio-mini", "azure/gpt-audio-mini-2025-10-06"),
|
||||
("azure/gpt-realtime-mini", "azure/gpt-realtime-mini-2025-10-06"),
|
||||
],
|
||||
)
|
||||
def test_undated_azure_audio_aliases_mirror_dated_pricing(monkeypatch, undated, dated):
|
||||
"""
|
||||
Azure deployments are commonly created against the undated model name, so
|
||||
base_model=azure/gpt-audio-mini must resolve. Missing undated aliases billed
|
||||
text tokens at $0 (issue #33170). Verify the undated alias exists and its
|
||||
token pricing matches the dated variant.
|
||||
"""
|
||||
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
|
||||
monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
|
||||
|
||||
assert undated in litellm.model_cost
|
||||
|
||||
undated_info = litellm.get_model_info(model=undated, custom_llm_provider="azure")
|
||||
dated_info = litellm.get_model_info(model=dated, custom_llm_provider="azure")
|
||||
assert undated_info["input_cost_per_token"] == dated_info["input_cost_per_token"]
|
||||
assert undated_info["output_cost_per_token"] == dated_info["output_cost_per_token"]
|
||||
assert (
|
||||
undated_info["input_cost_per_audio_token"]
|
||||
== dated_info["input_cost_per_audio_token"]
|
||||
)
|
||||
|
||||
prompt_usd, completion_usd = cost_per_token(
|
||||
model=undated,
|
||||
prompt_tokens=1000,
|
||||
completion_tokens=1000,
|
||||
custom_llm_provider="azure",
|
||||
)
|
||||
assert prompt_usd == 1000 * dated_info["input_cost_per_token"]
|
||||
assert completion_usd == 1000 * dated_info["output_cost_per_token"]
|
||||
assert prompt_usd > 0
|
||||
|
||||
|
||||
def test_realtime_transcription_no_completed_events_is_zero(monkeypatch):
|
||||
"""A realtime stream without transcription completed events adds no extra cost."""
|
||||
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue