tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-05 08:23:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat(openai): add 272K tier pricing for GPT-5.4/5.4-pro

Browse Source 
Prompts >272K input tokens priced at 2x input, 1.5x output for full session
(standard, batch, flex). Applies to models with 1.05M context window (gpt-5.4,
gpt-5.4-pro).

- Add input/output_cost_per_token_above_272k_tokens to model_prices
- Add above_272k fields to ModelInfoBase and get_model_info extraction
- Add test_generic_cost_per_token_gpt54_above_272k_tokens

Made-with: Cursor
This commit is contained in:
Sameer Kankute
2026-03-06 22:26:14 +05:30
parent 14b52b1318
commit d8f139fe4d
6 changed files with 100 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/model_prices_and_context_window_backup.json
+24
View File
@@ -20932,16 +20932,22 @@
},
"gpt-5.4": {
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_priority": 5e-06,
"input_cost_per_token_above_272k_tokens_priority": 1e-05,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_272k_tokens": 2.25e-05,
"output_cost_per_token_priority": 2.25e-05,
"output_cost_per_token_above_272k_tokens_priority": 3.375e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@@ -20970,16 +20976,22 @@
},
"gpt-5.4-2026-03-05": {
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_priority": 5e-06,
"input_cost_per_token_above_272k_tokens_priority": 1e-05,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_272k_tokens": 2.25e-05,
"output_cost_per_token_priority": 2.25e-05,
"output_cost_per_token_above_272k_tokens_priority": 3.375e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@@ -21006,16 +21018,22 @@
},
"gpt-5.4-pro": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"cache_read_input_token_cost_priority": 6e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_priority": 6e-05,
"input_cost_per_token_above_272k_tokens_priority": 1.2e-04,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 1.8e-04,
"output_cost_per_token_above_272k_tokens": 2.7e-04,
"output_cost_per_token_priority": 2.7e-04,
"output_cost_per_token_above_272k_tokens_priority": 4.05e-04,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@@ -21045,16 +21063,22 @@
},
"gpt-5.4-pro-2026-03-05": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"cache_read_input_token_cost_priority": 6e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_priority": 6e-05,
"input_cost_per_token_above_272k_tokens_priority": 1.2e-04,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 1.8e-04,
"output_cost_per_token_above_272k_tokens": 2.7e-04,
"output_cost_per_token_priority": 2.7e-04,
"output_cost_per_token_above_272k_tokens_priority": 4.05e-04,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
litellm/types/utils.py
+7
View File
@@ -183,12 +183,16 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
float
] # OpenAI priority service tier pricing
cache_read_input_token_cost_above_200k_tokens: Optional[float]
cache_read_input_token_cost_above_272k_tokens: Optional[float]
input_cost_per_character: Optional[float] # only for vertex ai models
input_cost_per_audio_token: Optional[float]
input_cost_per_token_above_128k_tokens: Optional[float] # only for vertex ai models
input_cost_per_token_above_200k_tokens: Optional[
float
] # only for vertex ai gemini-2.5-pro models
input_cost_per_token_above_272k_tokens: Optional[
float
] # GPT-5.4/5.4-pro: prompts >272K priced at 2x input
input_cost_per_character_above_128k_tokens: Optional[
float
] # only for vertex ai models
@@ -213,6 +217,9 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
output_cost_per_token_above_200k_tokens: Optional[
float
] # only for vertex ai gemini-2.5-pro models
output_cost_per_token_above_272k_tokens: Optional[
float
] # GPT-5.4/5.4-pro: prompts >272K priced at 1.5x output
output_cost_per_character_above_128k_tokens: Optional[
float
] # only for vertex ai models
litellm/utils.py
+9
View File
@@ -5639,6 +5639,9 @@ def _get_model_info_helper( # noqa: PLR0915
cache_read_input_token_cost_above_200k_tokens=_model_info.get(
"cache_read_input_token_cost_above_200k_tokens", None
),
cache_read_input_token_cost_above_272k_tokens=_model_info.get(
"cache_read_input_token_cost_above_272k_tokens", None
),
cache_read_input_token_cost_flex=_model_info.get(
"cache_read_input_token_cost_flex", None
),
@@ -5657,6 +5660,9 @@ def _get_model_info_helper( # noqa: PLR0915
input_cost_per_token_above_200k_tokens=_model_info.get(
"input_cost_per_token_above_200k_tokens", None
),
input_cost_per_token_above_272k_tokens=_model_info.get(
"input_cost_per_token_above_272k_tokens", None
),
input_cost_per_query=_model_info.get("input_cost_per_query", None),
input_cost_per_second=_model_info.get("input_cost_per_second", None),
input_cost_per_audio_token=_model_info.get(
@@ -5703,6 +5709,9 @@ def _get_model_info_helper( # noqa: PLR0915
output_cost_per_token_above_200k_tokens=_model_info.get(
"output_cost_per_token_above_200k_tokens", None
),
output_cost_per_token_above_272k_tokens=_model_info.get(
"output_cost_per_token_above_272k_tokens", None
),
output_cost_per_second=_model_info.get("output_cost_per_second", None),
output_cost_per_video_per_second=_model_info.get(
"output_cost_per_video_per_second", None
model_prices_and_context_window.json
+24
View File
@@ -20932,16 +20932,22 @@
},
"gpt-5.4": {
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_priority": 5e-06,
"input_cost_per_token_above_272k_tokens_priority": 1e-05,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_272k_tokens": 2.25e-05,
"output_cost_per_token_priority": 2.25e-05,
"output_cost_per_token_above_272k_tokens_priority": 3.375e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@@ -20970,16 +20976,22 @@
},
"gpt-5.4-2026-03-05": {
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1e-06,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_priority": 5e-06,
"input_cost_per_token_above_272k_tokens_priority": 1e-05,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_272k_tokens": 2.25e-05,
"output_cost_per_token_priority": 2.25e-05,
"output_cost_per_token_above_272k_tokens_priority": 3.375e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@@ -21006,16 +21018,22 @@
},
"gpt-5.4-pro": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"cache_read_input_token_cost_priority": 6e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_priority": 6e-05,
"input_cost_per_token_above_272k_tokens_priority": 1.2e-04,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 1.8e-04,
"output_cost_per_token_above_272k_tokens": 2.7e-04,
"output_cost_per_token_priority": 2.7e-04,
"output_cost_per_token_above_272k_tokens_priority": 4.05e-04,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@@ -21045,16 +21063,22 @@
},
"gpt-5.4-pro-2026-03-05": {
"cache_read_input_token_cost": 3e-06,
"cache_read_input_token_cost_above_272k_tokens": 6e-06,
"cache_read_input_token_cost_priority": 6e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05,
"input_cost_per_token": 3e-05,
"input_cost_per_token_above_272k_tokens": 6e-05,
"input_cost_per_token_priority": 6e-05,
"input_cost_per_token_above_272k_tokens_priority": 1.2e-04,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 1.8e-04,
"output_cost_per_token_above_272k_tokens": 2.7e-04,
"output_cost_per_token_priority": 2.7e-04,
"output_cost_per_token_above_272k_tokens_priority": 4.05e-04,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
+26
View File
@@ -295,6 +295,32 @@ def test_generic_cost_per_token_above_200k_tokens():
)
def test_generic_cost_per_token_gpt54_above_272k_tokens():
"""GPT-5.4/5.4-pro: prompts >272K input tokens priced at 2x input, 1.5x output."""
model = "gpt-5.4"
custom_llm_provider = "openai"
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
litellm.model_cost = litellm.get_model_cost_map(url="")
model_cost_map = litellm.model_cost[model]
prompt_tokens = 273000 # Above 272K threshold
completion_tokens = 1000
usage = Usage(
prompt_tokens=prompt_tokens,
completion_tokens=completion_tokens,
total_tokens=prompt_tokens + completion_tokens,
)
prompt_cost, completion_cost = generic_cost_per_token(
model=model,
usage=usage,
custom_llm_provider=custom_llm_provider,
)
expected_prompt = model_cost_map["input_cost_per_token_above_272k_tokens"] * prompt_tokens
expected_completion = model_cost_map["output_cost_per_token_above_272k_tokens"] * completion_tokens
assert round(prompt_cost, 10) == round(expected_prompt, 10)
assert round(completion_cost, 10) == round(expected_completion, 10)
def test_generic_cost_per_token_anthropic_prompt_caching():
model = "claude-sonnet-4@20250514"
usage = Usage(
tests/test_litellm/test_utils.py
+10
View File
@@ -513,6 +513,8 @@ def validate_model_cost_values(model_data, exceptions=None):
"output_cost_per_token_above_128k_tokens",
"input_cost_per_token_above_200k_tokens",
"output_cost_per_token_above_200k_tokens",
"input_cost_per_token_above_272k_tokens",
"output_cost_per_token_above_272k_tokens",
"input_cost_per_character_above_128k_tokens",
"output_cost_per_character_above_128k_tokens",
"input_cost_per_image_above_128k_tokens",
@@ -603,6 +605,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
"cache_creation_input_token_cost_above_200k_tokens": {"type": "number"},
"cache_read_input_token_cost": {"type": "number"},
"cache_read_input_token_cost_above_200k_tokens": {"type": "number"},
"cache_read_input_token_cost_above_272k_tokens": {"type": "number"},
"cache_creation_input_token_cost_above_1hr_above_200k_tokens": {"type": "number"},
"cache_read_input_audio_token_cost": {"type": "number"},
"cache_read_input_token_cost_per_audio_token": {"type": "number"},
@@ -618,16 +621,20 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
"input_cost_per_image_above_128k_tokens": {"type": "number"},
"input_cost_per_image_token": {"type": "number"},
"input_cost_per_token_above_200k_tokens": {"type": "number"},
"input_cost_per_token_above_272k_tokens": {"type": "number"},
"cache_read_input_token_cost_flex": {"type": "number"},
"cache_read_input_token_cost_priority": {"type": "number"},
"cache_read_input_token_cost_above_200k_tokens_priority": {"type": "number"},
"cache_read_input_token_cost_above_272k_tokens_priority": {"type": "number"},
"input_cost_per_token_flex": {"type": "number"},
"input_cost_per_token_priority": {"type": "number"},
"input_cost_per_token_above_200k_tokens_priority": {"type": "number"},
"input_cost_per_token_above_272k_tokens_priority": {"type": "number"},
"input_cost_per_audio_token_priority": {"type": "number"},
"output_cost_per_token_flex": {"type": "number"},
"output_cost_per_token_priority": {"type": "number"},
"output_cost_per_token_above_200k_tokens_priority": {"type": "number"},
"output_cost_per_token_above_272k_tokens_priority": {"type": "number"},
"input_cost_per_pixel": {"type": "number"},
"input_cost_per_query": {"type": "number"},
"input_cost_per_request": {"type": "number"},
@@ -694,6 +701,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
"output_cost_per_token": {"type": "number"},
"output_cost_per_token_above_128k_tokens": {"type": "number"},
"output_cost_per_token_above_200k_tokens": {"type": "number"},
"output_cost_per_token_above_272k_tokens": {"type": "number"},
"output_cost_per_image_above_1024_and_1024_pixels": {"type": "number"},
"output_cost_per_image_above_1024_and_1024_pixels_and_premium_image": {
"type": "number"
@@ -732,6 +740,8 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
"supports_web_search": {"type": "boolean"},
"supports_url_context": {"type": "boolean"},
"supports_reasoning": {"type": "boolean"},
"supports_none_reasoning_effort": {"type": "boolean"},
"supports_xhigh_reasoning_effort": {"type": "boolean"},
"supports_service_tier": {"type": "boolean"},
"supports_preset": {"type": "boolean"},
"tool_use_system_prompt_tokens": {"type": "number"},