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 133

fix(pricing): adjust gpt-5.6-terra and gpt-5.6-luna prices according to OpenAI's latest article (#35258)

Browse source 
Adjust the price of gpt-5.6-terra to 80% of its original rate (2/12), and gpt-5.6-luna to 20% of its original rate (0.2/1.2).

References:
  https://openai.com/index/advancing-the-price-performance-frontier-with-gpt-5-6/
  https://developers.openai.com/api/docs/pricing
This commit is contained in:
lihugang 2026-07-31 04:08:01 +08:00 • committed by GitHub
parent c1f5abf817
commit f1b781d06b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 85 additions and 78 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

72
litellm/model_prices_and_context_window_backup.json
View file

@ -23782,29 +23782,29 @@
"supports_xhigh_reasoning_effort": true
},
"gpt-5.6-terra": {
"cache_creation_input_token_cost": 3.125e-06,
"cache_creation_input_token_cost_above_272k_tokens": 6.25e-06,
"cache_creation_input_token_cost_flex": 1.5625e-06,
"cache_creation_input_token_cost_priority": 6.25e-06,
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_flex": 1.25e-07,
"cache_read_input_token_cost_priority": 5e-07,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_batches": 1.25e-06,
"input_cost_per_token_flex": 1.25e-06,
"input_cost_per_token_priority": 5e-06,
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_flex": 1.25e-06,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_flex": 1e-07,
"cache_read_input_token_cost_priority": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_batches": 1e-06,
"input_cost_per_token_flex": 1e-06,
"input_cost_per_token_priority": 4e-06,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_272k_tokens": 2.25e-05,
"output_cost_per_token_batches": 7.5e-06,
"output_cost_per_token_flex": 7.5e-06,
"output_cost_per_token_priority": 3e-05,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"output_cost_per_token_batches": 6e-06,
"output_cost_per_token_flex": 6e-06,
"output_cost_per_token_priority": 2.4e-05,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"supported_endpoints": [
@ -23835,29 +23835,29 @@
"supports_xhigh_reasoning_effort": true
},
"gpt-5.6-luna": {
"cache_creation_input_token_cost": 1.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-06,
"cache_creation_input_token_cost_flex": 6.25e-07,
"cache_creation_input_token_cost_priority": 2.5e-06,
"cache_read_input_token_cost": 1e-07,
"cache_read_input_token_cost_above_272k_tokens": 2e-07,
"cache_read_input_token_cost_flex": 5e-08,
"cache_read_input_token_cost_priority": 2e-07,
"input_cost_per_token": 1e-06,
"input_cost_per_token_above_272k_tokens": 2e-06,
"input_cost_per_token_batches": 5e-07,
"input_cost_per_token_flex": 5e-07,
"input_cost_per_token_priority": 2e-06,
"cache_creation_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5e-07,
"cache_creation_input_token_cost_flex": 1.25e-07,
"cache_creation_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_flex": 1e-08,
"cache_read_input_token_cost_priority": 4e-08,
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_batches": 1e-07,
"input_cost_per_token_flex": 1e-07,
"input_cost_per_token_priority": 4e-07,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token_above_272k_tokens": 9e-06,
"output_cost_per_token_batches": 3e-06,
"output_cost_per_token_flex": 3e-06,
"output_cost_per_token_priority": 1.2e-05,
"output_cost_per_token": 1.2e-06,
"output_cost_per_token_above_272k_tokens": 1.8e-06,
"output_cost_per_token_batches": 6e-07,
"output_cost_per_token_flex": 6e-07,
"output_cost_per_token_priority": 2.4e-06,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"supported_endpoints": [

72
model_prices_and_context_window.json
View file

@ -23857,29 +23857,29 @@
"supports_xhigh_reasoning_effort": true
},
"gpt-5.6-terra": {
"cache_creation_input_token_cost": 3.125e-06,
"cache_creation_input_token_cost_above_272k_tokens": 6.25e-06,
"cache_creation_input_token_cost_flex": 1.5625e-06,
"cache_creation_input_token_cost_priority": 6.25e-06,
"cache_read_input_token_cost": 2.5e-07,
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_flex": 1.25e-07,
"cache_read_input_token_cost_priority": 5e-07,
"input_cost_per_token": 2.5e-06,
"input_cost_per_token_above_272k_tokens": 5e-06,
"input_cost_per_token_batches": 1.25e-06,
"input_cost_per_token_flex": 1.25e-06,
"input_cost_per_token_priority": 5e-06,
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_flex": 1.25e-06,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_flex": 1e-07,
"cache_read_input_token_cost_priority": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_batches": 1e-06,
"input_cost_per_token_flex": 1e-06,
"input_cost_per_token_priority": 4e-06,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_272k_tokens": 2.25e-05,
"output_cost_per_token_batches": 7.5e-06,
"output_cost_per_token_flex": 7.5e-06,
"output_cost_per_token_priority": 3e-05,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"output_cost_per_token_batches": 6e-06,
"output_cost_per_token_flex": 6e-06,
"output_cost_per_token_priority": 2.4e-05,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"supported_endpoints": [
@ -23910,29 +23910,29 @@
"supports_xhigh_reasoning_effort": true
},
"gpt-5.6-luna": {
"cache_creation_input_token_cost": 1.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-06,
"cache_creation_input_token_cost_flex": 6.25e-07,
"cache_creation_input_token_cost_priority": 2.5e-06,
"cache_read_input_token_cost": 1e-07,
"cache_read_input_token_cost_above_272k_tokens": 2e-07,
"cache_read_input_token_cost_flex": 5e-08,
"cache_read_input_token_cost_priority": 2e-07,
"input_cost_per_token": 1e-06,
"input_cost_per_token_above_272k_tokens": 2e-06,
"input_cost_per_token_batches": 5e-07,
"input_cost_per_token_flex": 5e-07,
"input_cost_per_token_priority": 2e-06,
"cache_creation_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5e-07,
"cache_creation_input_token_cost_flex": 1.25e-07,
"cache_creation_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_flex": 1e-08,
"cache_read_input_token_cost_priority": 4e-08,
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_batches": 1e-07,
"input_cost_per_token_flex": 1e-07,
"input_cost_per_token_priority": 4e-07,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-06,
"output_cost_per_token_above_272k_tokens": 9e-06,
"output_cost_per_token_batches": 3e-06,
"output_cost_per_token_flex": 3e-06,
"output_cost_per_token_priority": 1.2e-05,
"output_cost_per_token": 1.2e-06,
"output_cost_per_token_above_272k_tokens": 1.8e-06,
"output_cost_per_token_batches": 6e-07,
"output_cost_per_token_flex": 6e-07,
"output_cost_per_token_priority": 2.4e-06,
"regional_processing_uplift_multiplier_eu": 1.1,
"regional_processing_uplift_multiplier_us": 1.1,
"supported_endpoints": [

4
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -611,8 +611,8 @@ def test_generic_cost_per_token_gpt55_pro():
[
("gpt-5.6", 5e-6, 3e-5, 5e-7, 6.25e-6),
("gpt-5.6-sol", 5e-6, 3e-5, 5e-7, 6.25e-6),
("gpt-5.6-terra", 2.5e-6, 1.5e-5, 2.5e-7, 3.125e-6),
("gpt-5.6-luna", 1e-6, 6e-6, 1e-7, 1.25e-6),
("gpt-5.6-terra", 2e-6, 1.2e-5, 2e-7, 2.5e-6),
("gpt-5.6-luna", 2e-7, 1.2e-6, 2e-8, 2.5e-7),
],
)
def test_generic_cost_per_token_gpt56(

15
tests/test_litellm/test_gpt_5_6_model_metadata.py
View file

@ -7,7 +7,14 @@ from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
GPT_5_6_MODELS = ("gpt-5.6", "gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6-luna")
STANDARD_PRICING = {
OPENAI_STANDARD_PRICING = {
"gpt-5.6": (5e-06, 3e-05, 5e-07, 6.25e-06),
"gpt-5.6-sol": (5e-06, 3e-05, 5e-07, 6.25e-06),
"gpt-5.6-terra": (2e-06, 1.2e-05, 2e-07, 2.5e-06),
"gpt-5.6-luna": (2e-07, 1.2e-06, 2e-08, 2.5e-07),
}
AZURE_STANDARD_PRICING = {
"gpt-5.6": (5e-06, 3e-05, 5e-07, 6.25e-06),
"gpt-5.6-sol": (5e-06, 3e-05, 5e-07, 6.25e-06),
"gpt-5.6-terra": (2.5e-06, 1.5e-05, 2.5e-07, 3.125e-06),
@ -27,7 +34,7 @@ def test_openai_gpt_5_6_model_info(model):
assert info["litellm_provider"] == "openai"
assert info["mode"] == "chat"
input_cost, output_cost, cache_read_cost, cache_write_cost = STANDARD_PRICING[model]
input_cost, output_cost, cache_read_cost, cache_write_cost = OPENAI_STANDARD_PRICING[model]
assert info["input_cost_per_token"] == input_cost
assert info["output_cost_per_token"] == output_cost
assert info["cache_read_input_token_cost"] == cache_read_cost
@ -95,7 +102,7 @@ def test_azure_gpt_5_6_global_model_info(model):
assert info["litellm_provider"] == "azure"
assert info["mode"] == "chat"
input_cost, output_cost, cache_read_cost, _ = STANDARD_PRICING[_tier_key(model)]
input_cost, output_cost, cache_read_cost, _ = AZURE_STANDARD_PRICING[_tier_key(model)]
assert info["input_cost_per_token"] == input_cost
assert info["output_cost_per_token"] == output_cost
assert info["cache_read_input_token_cost"] == cache_read_cost
@ -124,7 +131,7 @@ def test_azure_gpt_5_6_regional_model_info(model):
assert info["litellm_provider"] == "azure"
assert info["mode"] == "chat"
input_cost, output_cost, cache_read_cost, _ = STANDARD_PRICING[_tier_key(model)]
input_cost, output_cost, cache_read_cost, _ = AZURE_STANDARD_PRICING[_tier_key(model)]
assert info["input_cost_per_token"] == pytest.approx(input_cost * 1.1)
assert info["output_cost_per_token"] == pytest.approx(output_cost * 1.1)