Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions gptcli/assistant.py
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,7 @@ def get_completion_provider(
or model.startswith("oai-compat:")
or model.startswith("chatgpt")
or model.startswith("o1")
or model.startswith("o3")
):
return OpenAICompletionProvider(
openai_base_url_override, openai_api_key_override
Expand Down
190 changes: 157 additions & 33 deletions gptcli/providers/openai.py
Original file line number Diff line number Diff line change
Expand Up @@ -87,29 +87,69 @@ def complete(
raise CompletionError(e.message) from e


GPT_3_5_TURBO_PRICE_PER_TOKEN: Pricing = {
GPT_3_5_TURBO_0125_PRICE_PER_TOKEN: Pricing = {
"prompt": 0.50 / 1_000_000,
"response": 1.50 / 1_000_000,
}

GPT_3_5_TURBO_16K_PRICE_PER_TOKEN: Pricing = {
"prompt": 0.003 / 1000,
"response": 0.004 / 1000,
GPT_3_5_TURBO_INSTRUCT_PRICE_PER_TOKEN: Pricing = {
"prompt": 1.50 / 1_000_000,
"response": 2.00 / 1_000_000,
}

GPT_3_5_TURBO_1106_PRICE_PER_TOKEN: Pricing = {
"prompt": 1.00 / 1_000_000,
"response": 2.00 / 1_000_000,
}

GPT_3_5_TURBO_0613_PRICE_PER_TOKEN: Pricing = {
"prompt": 1.50 / 1_000_000,
"response": 2.00 / 1_000_000,
}

GPT_3_5_TURBO_16K_0613_PRICE_PER_TOKEN: Pricing = {
"prompt": 3.00 / 1_000_000,
"response": 4.00 / 1_000_000,
}

GPT_3_5_TURBO_0301_PRICE_PER_TOKEN: Pricing = {
"prompt": 1.50 / 1_000_000,
"response": 2.00 / 1_000_000,
}

GPT_4_PRICE_PER_TOKEN: Pricing = {
"prompt": 30.0 / 1_000_000,
"response": 60.0 / 1_000_000,
}

GPT_4_32K_PRICE_PER_TOKEN: Pricing = {
"prompt": 60.0 / 1_000_000,
"response": 120.0 / 1_000_000,
}

GPT_4_0125_PREVIEW_PRICE_PER_TOKEN: Pricing = {
"prompt": 10.0 / 1_000_000,
"response": 30.0 / 1_000_000,
}

GPT_4_1106_PREVIEW_PRICE_PER_TOKEN: Pricing = {
"prompt": 10.0 / 1_000_000,
"response": 30.0 / 1_000_000,
}

GPT_4_VISION_PREVIEW_PRICE_PER_TOKEN: Pricing = {
"prompt": 10.0 / 1_000_000,
"response": 30.0 / 1_000_000,
}

GPT_4_TURBO_PRICE_PER_TOKEN: Pricing = {
"prompt": 10.0 / 1_000_000,
"response": 30.0 / 1_000_000,
}

GPT_4_32K_PRICE_PER_TOKEN: Pricing = {
"prompt": 60.0 / 1_000_000,
"response": 120.0 / 1_000_000,
GPT_4_TURBO_2024_04_09_PRICE_PER_TOKEN: Pricing = {
"prompt": 10.0 / 1_000_000,
"response": 30.0 / 1_000_000,
}

GPT_4_O_2024_05_13_PRICE_PER_TOKEN: Pricing = {
Expand All @@ -122,42 +162,126 @@ def complete(
"response": 10.0 / 1_000_000,
}

GPT_4_O_2024_11_20_PRICE_PER_TOKEN: Pricing = {
"prompt": 2.50 / 1_000_000,
"response": 10.0 / 1_000_000,
}

GPT_4_O_PRICE_PER_TOKEN: Pricing = {
"prompt": 2.50 / 1_000_000,
"response": 10.0 / 1_000_000,
}

GPT_4_O_AUDIO_PREVIEW_PRICE_PER_TOKEN: Pricing = {
"prompt": 2.50 / 1_000_000,
"response": 10.0 / 1_000_000,
}
GPT_4_O_AUDIO_PREVIEW_2024_10_01_PRICE_PER_TOKEN: Pricing = {
"prompt": 2.50 / 1_000_000,
"response": 10.0 / 1_000_000,
}

GPT_4_O_AUDIO_PREVIEW_2024_12_17_PRICE_PER_TOKEN: Pricing = {
"prompt": 2.50 / 1_000_000,
"response": 10.0 / 1_000_000,
}

GPT_4_O_MINI_PRICE_PER_TOKEN: Pricing = {
"prompt": 0.150 / 1_000_000,
"response": 0.600 / 1_000_000,
}

O_1_PREVIEW_PRICE_PER_TOKEN: Pricing = {
GPT_4_O_MINI_2024_07_18_PRICE_PER_TOKEN: Pricing = {
"prompt": 0.150 / 1_000_000,
"response": 0.600 / 1_000_000,
}
GPT_4_O_MINI_AUDIO_PREVIEW_PRICE_PER_TOKEN: Pricing = {
"prompt": 0.150 / 1_000_000,
"response": 0.600 / 1_000_000,
}
GPT_4_O_MINI_AUDIO_PREVIEW_2024_12_17_PRICE_PER_TOKEN: Pricing = {
"prompt": 0.150 / 1_000_000,
"response": 0.600 / 1_000_000,
}

O_1_PRICE_PER_TOKEN: Pricing = {
"prompt": 15.0 / 1_000_000,
"response": 60.0 / 1_000_000,
}

O_1_2024_12_17_PRICE_PER_TOKEN: Pricing = {
"prompt": 15.0 / 1_000_000,
"response": 60.0 / 1_000_000,
}

O_1_MINI_PRICE_PER_TOKEN: Pricing = {
"prompt": 3.0 / 1_000_000,
"response": 12.0 / 1_000_000,
O_1_PREVIEW_2024_09_12_PRICE_PER_TOKEN: Pricing = {
"prompt": 15.0 / 1_000_000,
"response": 60.0 / 1_000_000,
}

O_3_MINI_PRICE_PER_TOKEN: Pricing = {
"prompt": 1.10 / 1_000_000,
"response": 4.40 / 1_000_000,
}

O_3_MINI_2025_01_31_PRICE_PER_TOKEN: Pricing = {
"prompt": 1.10 / 1_000_000,
"response": 4.40 / 1_000_000,
}

CHATGPT_4O_LATEST_PRICE_PER_TOKEN: Pricing = {
"prompt": 5.00 / 1_000_000,
"response": 15.00 / 1_000_000,
}

DAVINCI_002_PRICE_PER_TOKEN: Pricing = {
"prompt": 2.00 / 1_000_000,
"response": 2.00 / 1_000_000,
}

BABBAGE_002_PRICE_PER_TOKEN: Pricing = {
"prompt": 0.40 / 1_000_000,
"response": 0.40 / 1_000_000,
}

PRICING_MAP: dict[str, Pricing] = {
"davinci-002": DAVINCI_002_PRICE_PER_TOKEN,
"babbage-002": BABBAGE_002_PRICE_PER_TOKEN,
"gpt-3.5-turbo-0125": GPT_3_5_TURBO_0125_PRICE_PER_TOKEN,
"gpt-3.5-turbo-instruct": GPT_3_5_TURBO_INSTRUCT_PRICE_PER_TOKEN,
"gpt-3.5-turbo-1106": GPT_3_5_TURBO_1106_PRICE_PER_TOKEN,
"gpt-3.5-turbo-0613": GPT_3_5_TURBO_0613_PRICE_PER_TOKEN,
"gpt-3.5-turbo-16k-0613": GPT_3_5_TURBO_16K_0613_PRICE_PER_TOKEN,
"gpt-3.5-turbo-0301": GPT_3_5_TURBO_0301_PRICE_PER_TOKEN,
"gpt-4": GPT_4_PRICE_PER_TOKEN,
"gpt-4-32k": GPT_4_32K_PRICE_PER_TOKEN,
"gpt-4-0125-preview": GPT_4_0125_PREVIEW_PRICE_PER_TOKEN,
"gpt-4-1106-preview": GPT_4_1106_PREVIEW_PRICE_PER_TOKEN,
"gpt-4-vision-preview": GPT_4_VISION_PREVIEW_PRICE_PER_TOKEN,
"gpt-4-turbo": GPT_4_TURBO_PRICE_PER_TOKEN,
"gpt-4-turbo-2024-04-09": GPT_4_TURBO_2024_04_09_PRICE_PER_TOKEN,
"gpt-4o-2024-05-13": GPT_4_O_2024_05_13_PRICE_PER_TOKEN,
"gpt-4o-2024-08-06": GPT_4_O_2024_08_06_PRICE_PER_TOKEN,
"gpt-4o-2024-11-20": GPT_4_O_2024_11_20_PRICE_PER_TOKEN,
"gpt-4o": GPT_4_O_PRICE_PER_TOKEN,
"gpt-4o-audio-preview": GPT_4_O_AUDIO_PREVIEW_PRICE_PER_TOKEN,
"gpt-4o-audio-preview-2024-10-01": GPT_4_O_AUDIO_PREVIEW_2024_10_01_PRICE_PER_TOKEN,
"gpt-4o-audio-preview-2024-12-17": GPT_4_O_AUDIO_PREVIEW_2024_12_17_PRICE_PER_TOKEN,
"gpt-4o-mini": GPT_4_O_MINI_PRICE_PER_TOKEN,
"gpt-4o-mini-2024-07-18": GPT_4_O_MINI_2024_07_18_PRICE_PER_TOKEN,
"gpt-4o-mini-audio-preview": GPT_4_O_MINI_AUDIO_PREVIEW_PRICE_PER_TOKEN,
"gpt-4o-mini-audio-preview-2024-12-17": GPT_4_O_MINI_AUDIO_PREVIEW_2024_12_17_PRICE_PER_TOKEN,
"o1": O_1_PRICE_PER_TOKEN,
"o1-2024-12-17": O_1_2024_12_17_PRICE_PER_TOKEN,
"o1-preview-2024-09-12": O_1_PREVIEW_2024_09_12_PRICE_PER_TOKEN,
"o3-mini": O_3_MINI_PRICE_PER_TOKEN,
"o3-mini-2025-01-31": O_3_MINI_2025_01_31_PRICE_PER_TOKEN,
"chatgpt-4o-latest": CHATGPT_4O_LATEST_PRICE_PER_TOKEN,
}


def gpt_pricing(model: str) -> Optional[Pricing]:
if model.startswith("gpt-3.5-turbo-16k"):
return GPT_3_5_TURBO_16K_PRICE_PER_TOKEN
elif model.startswith("gpt-3.5-turbo"):
return GPT_3_5_TURBO_PRICE_PER_TOKEN
elif model.startswith("gpt-4-32k"):
return GPT_4_32K_PRICE_PER_TOKEN
elif model.startswith("gpt-4o-mini"):
return GPT_4_O_MINI_PRICE_PER_TOKEN
elif model.startswith("gpt-4o-2024-05-13") or model.startswith("chatgpt-4o-latest"):
return GPT_4_O_2024_05_13_PRICE_PER_TOKEN
elif model.startswith("gpt-4o"):
return GPT_4_O_2024_08_06_PRICE_PER_TOKEN
elif model.startswith("gpt-4-turbo") or re.match(r"gpt-4-\d\d\d\d-preview", model):
return GPT_4_TURBO_PRICE_PER_TOKEN
elif model.startswith("gpt-4"):
return GPT_4_PRICE_PER_TOKEN
elif model.startswith("o1-preview"):
return O_1_PREVIEW_PRICE_PER_TOKEN
elif model.startswith("o1-mini"):
return O_1_MINI_PRICE_PER_TOKEN
else:
return None
"""
Returns the pricing structure for the given model name using a dictionary lookup.
"""
return PRICING_MAP.get(model)