tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-07-15 10:20:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix gpt-5.4 pricing (#24748)

Browse Source
This commit is contained in:
mubashir1osmani
2026-04-02 21:51:21 -07:00
committed by GitHub
parent 50f4fdea3e
commit d4a3a5e530
1 changed files with 7 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files
model_prices_and_context_window.json
+7 -22
View File
@@ -18847,13 +18847,11 @@
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_flex": 1.3e-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_flex": 1.25e-06,
"input_cost_per_token_batches": 1.25e-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,
@@ -18863,8 +18861,7 @@
"output_cost_per_token_above_272k_tokens": 2.25e-05,
"output_cost_per_token_flex": 7.5e-06,
"output_cost_per_token_batches": 7.5e-06,
"output_cost_per_token_priority": 2.25e-05,
"output_cost_per_token_above_272k_tokens_priority": 3.375e-05,
"output_cost_per_token_priority": 3e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@@ -18897,13 +18894,11 @@
"cache_read_input_token_cost_above_272k_tokens": 5e-07,
"cache_read_input_token_cost_flex": 1.3e-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_flex": 1.25e-06,
"input_cost_per_token_batches": 1.25e-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,
@@ -18913,8 +18908,7 @@
"output_cost_per_token_above_272k_tokens": 2.25e-05,
"output_cost_per_token_flex": 7.5e-06,
"output_cost_per_token_batches": 7.5e-06,
"output_cost_per_token_priority": 2.25e-05,
"output_cost_per_token_above_272k_tokens_priority": 3.375e-05,
"output_cost_per_token_priority": 3e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
@@ -18942,14 +18936,10 @@
"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_flex": 1.5e-05,
"input_cost_per_token_batches": 1.5e-05,
"input_cost_per_token_priority": 6e-05,
"input_cost_per_token_above_272k_tokens_priority": 0.00012,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
@@ -18959,8 +18949,6 @@
"output_cost_per_token_above_272k_tokens": 0.00027,
"output_cost_per_token_flex": 9e-05,
"output_cost_per_token_batches": 9e-05,
"output_cost_per_token_priority": 0.00027,
"output_cost_per_token_above_272k_tokens_priority": 0.000405,
"supported_endpoints": [
"/v1/responses",
"/v1/batch"
@@ -18991,14 +18979,10 @@
"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_flex": 1.5e-05,
"input_cost_per_token_batches": 1.5e-05,
"input_cost_per_token_priority": 6e-05,
"input_cost_per_token_above_272k_tokens_priority": 0.00012,
"litellm_provider": "openai",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
@@ -19008,8 +18992,6 @@
"output_cost_per_token_above_272k_tokens": 0.00027,
"output_cost_per_token_flex": 9e-05,
"output_cost_per_token_batches": 9e-05,
"output_cost_per_token_priority": 0.00027,
"output_cost_per_token_above_272k_tokens_priority": 0.000405,
"supported_endpoints": [
"/v1/responses",
"/v1/batch"
@@ -19039,11 +19021,13 @@
},
"gpt-5.4-mini": {
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_flex": 1e-08,
"cache_read_input_token_cost_batches": 3.8e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"cache_read_input_token_cost_batches": 3.75e-08,
"cache_read_input_token_cost_priority": 1.5e-07,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_flex": 3.75e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_priority": 1.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
@@ -19052,6 +19036,7 @@
"output_cost_per_token": 4.5e-06,
"output_cost_per_token_flex": 2.25e-06,
"output_cost_per_token_batches": 2.25e-06,
"output_cost_per_token_priority": 9e-06,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",