tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-07-15 08:27:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update 5.4 family values correctly

Browse Source
This commit is contained in:
Sameer Kankute
2026-03-17 22:47:45 +05:30
parent 8a8047e519
commit bb8e0cd3e2
2 changed files with 16 additions and 48 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/model_prices_and_context_window_backup.json
+8 -24
View File
@@ -18749,27 +18749,19 @@
},
"gpt-5.4-mini": {
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_above_272k_tokens": 1.5e-07,
"cache_read_input_token_cost_flex": 3.9e-08,
"cache_read_input_token_cost_priority": 1.5e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 3e-07,
"cache_read_input_token_cost_flex": 3.75e-08,
"cache_read_input_token_cost_batches": 3.8e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_above_272k_tokens": 1.5e-06,
"input_cost_per_token_flex": 3.75e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_priority": 1.5e-06,
"input_cost_per_token_above_272k_tokens_priority": 3e-06,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.5e-06,
"output_cost_per_token_above_272k_tokens": 6.75e-06,
"output_cost_per_token_flex": 2.25e-06,
"output_cost_per_token_batches": 2.25e-06,
"output_cost_per_token_priority": 6.75e-06,
"output_cost_per_token_above_272k_tokens_priority": 1.0125e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@@ -18798,27 +18790,19 @@
},
"gpt-5.4-nano": {
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_flex": 1.04e-08,
"cache_read_input_token_cost_priority": 4e-08,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"cache_read_input_token_cost_flex": 1e-08,
"cache_read_input_token_cost_batches": 1e-08,
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_flex": 1e-07,
"input_cost_per_token_batches": 1e-07,
"input_cost_per_token_priority": 4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8e-07,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.25e-06,
"output_cost_per_token_above_272k_tokens": 1.875e-06,
"output_cost_per_token_flex": 6.25e-07,
"output_cost_per_token_batches": 6.25e-07,
"output_cost_per_token_priority": 1.875e-06,
"output_cost_per_token_above_272k_tokens_priority": 2.8125e-06,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
model_prices_and_context_window.json
+8 -24
View File
@@ -18749,27 +18749,19 @@
},
"gpt-5.4-mini": {
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_above_272k_tokens": 1.5e-07,
"cache_read_input_token_cost_flex": 3.9e-08,
"cache_read_input_token_cost_priority": 1.5e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 3e-07,
"cache_read_input_token_cost_flex": 3.75e-08,
"cache_read_input_token_cost_batches": 3.8e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_above_272k_tokens": 1.5e-06,
"input_cost_per_token_flex": 3.75e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_priority": 1.5e-06,
"input_cost_per_token_above_272k_tokens_priority": 3e-06,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 4.5e-06,
"output_cost_per_token_above_272k_tokens": 6.75e-06,
"output_cost_per_token_flex": 2.25e-06,
"output_cost_per_token_batches": 2.25e-06,
"output_cost_per_token_priority": 6.75e-06,
"output_cost_per_token_above_272k_tokens_priority": 1.0125e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@@ -18798,27 +18790,19 @@
},
"gpt-5.4-nano": {
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_flex": 1.04e-08,
"cache_read_input_token_cost_priority": 4e-08,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"cache_read_input_token_cost_flex": 1e-08,
"cache_read_input_token_cost_batches": 1e-08,
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_flex": 1e-07,
"input_cost_per_token_batches": 1e-07,
"input_cost_per_token_priority": 4e-07,
"input_cost_per_token_above_272k_tokens_priority": 8e-07,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.25e-06,
"output_cost_per_token_above_272k_tokens": 1.875e-06,
"output_cost_per_token_flex": 6.25e-07,
"output_cost_per_token_batches": 6.25e-07,
"output_cost_per_token_priority": 1.875e-06,
"output_cost_per_token_above_272k_tokens_priority": 2.8125e-06,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",