scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-13 23:11:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 100

feat(model_prices): add gpt-5.6-cyber and the Daybreak Red/Blue aliases

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
mateo 2026-08-10 18:34:05 +00:00
parent 9de3315dad
commit 3a42d3ed0e
3 changed files with 245 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

102
litellm/model_prices_and_context_window_backup.json
View file

@ -24227,6 +24227,108 @@
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"gpt-5.6-cyber": {
"cache_creation_input_token_cost": 1.5625e-05,
"cache_creation_input_token_cost_above_272k_tokens": 3.125e-05,
"cache_read_input_token_cost": 1.25e-06,
"cache_read_input_token_cost_above_272k_tokens": 2.5e-06,
"input_cost_per_token": 1.25e-05,
"input_cost_per_token_above_272k_tokens": 2.5e-05,
"litellm_provider": "openai",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 7.5e-05,
"output_cost_per_token_above_272k_tokens": 0.0001125,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": 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
},
"daybreak-red-latest": {
"cache_creation_input_token_cost": 1.5625e-05,
"cache_creation_input_token_cost_above_272k_tokens": 3.125e-05,
"cache_read_input_token_cost": 1.25e-06,
"cache_read_input_token_cost_above_272k_tokens": 2.5e-06,
"input_cost_per_token": 1.25e-05,
"input_cost_per_token_above_272k_tokens": 2.5e-05,
"litellm_provider": "openai",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 7.5e-05,
"output_cost_per_token_above_272k_tokens": 0.0001125,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": 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
},
"daybreak-blue-latest": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": 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
},
"gpt-5.5": {
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,

102
model_prices_and_context_window.json
View file

@ -24227,6 +24227,108 @@
"supports_web_search": true,
"supports_xhigh_reasoning_effort": true
},
"gpt-5.6-cyber": {
"cache_creation_input_token_cost": 1.5625e-05,
"cache_creation_input_token_cost_above_272k_tokens": 3.125e-05,
"cache_read_input_token_cost": 1.25e-06,
"cache_read_input_token_cost_above_272k_tokens": 2.5e-06,
"input_cost_per_token": 1.25e-05,
"input_cost_per_token_above_272k_tokens": 2.5e-05,
"litellm_provider": "openai",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 7.5e-05,
"output_cost_per_token_above_272k_tokens": 0.0001125,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": 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
},
"daybreak-red-latest": {
"cache_creation_input_token_cost": 1.5625e-05,
"cache_creation_input_token_cost_above_272k_tokens": 3.125e-05,
"cache_read_input_token_cost": 1.25e-06,
"cache_read_input_token_cost_above_272k_tokens": 2.5e-06,
"input_cost_per_token": 1.25e-05,
"input_cost_per_token_above_272k_tokens": 2.5e-05,
"litellm_provider": "openai",
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 7.5e-05,
"output_cost_per_token_above_272k_tokens": 0.0001125,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": 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
},
"daybreak-blue-latest": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1.25e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_272k_tokens": 1e-05,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 3e-05,
"output_cost_per_token_above_272k_tokens": 4.5e-05,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_native_streaming": 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
},
"gpt-5.5": {
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_272k_tokens": 1e-06,

41
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -752,6 +752,47 @@ def test_generic_cost_per_token_gpt56_terra_cache_costs_by_tier_and_context(
assert prompt_cost == pytest.approx(expected_prompt_cost)
@pytest.mark.parametrize("model", ["gpt-5.6-cyber", "daybreak-red-latest"])
@pytest.mark.parametrize(
"prompt_tokens,input_rate,cache_write_rate,cache_read_rate,output_rate",
[
(100000, 1.25e-5, 1.5625e-5, 1.25e-6, 7.5e-5),
(300000, 2.5e-5, 3.125e-5, 2.5e-6, 1.125e-4),
],
)
def test_generic_cost_per_token_gpt56_cyber(
model, prompt_tokens, input_rate, cache_write_rate, cache_read_rate, output_rate
):
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
litellm.model_cost = litellm.get_model_cost_map(url="")
cached_tokens = 50000
cache_write_tokens = 40000
text_tokens = prompt_tokens - cached_tokens - cache_write_tokens
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, cache_write_tokens=cache_write_tokens
),
)
prompt_cost, completion_cost = generic_cost_per_token(
model=model,
usage=usage,
custom_llm_provider="openai",
)
assert prompt_cost == pytest.approx(
text_tokens * input_rate
+ cached_tokens * cache_read_rate
+ cache_write_tokens * cache_write_rate
)
assert completion_cost == pytest.approx(completion_tokens * output_rate)
@pytest.mark.parametrize(
"model,input_cost,output_cost,cache_read_cost",
[