tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-07 00:24:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add flex pricing

Browse Source
This commit is contained in:
Sameer Kankute
2026-03-07 01:02:18 +05:30
parent 11e2bdbaec
commit 6034efb9c6
2 changed files with 36 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
litellm/model_prices_and_context_window_backup.json
+18
View File
@@ -20936,10 +20936,13 @@
"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_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",
@@ -20949,6 +20952,8 @@
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"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,
"supported_endpoints": [
@@ -20980,10 +20985,13 @@
"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_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",
@@ -20993,6 +21001,8 @@
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"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,
"supported_endpoints": [
@@ -21026,6 +21036,8 @@
"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": 1.2e-04,
"litellm_provider": "openai",
@@ -21035,6 +21047,8 @@
"mode": "chat",
"output_cost_per_token": 1.8e-04,
"output_cost_per_token_above_272k_tokens": 2.7e-04,
"output_cost_per_token_flex": 9e-05,
"output_cost_per_token_batches": 9e-05,
"output_cost_per_token_priority": 2.7e-04,
"output_cost_per_token_above_272k_tokens_priority": 4.05e-04,
"supported_endpoints": [
@@ -21071,6 +21085,8 @@
"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": 1.2e-04,
"litellm_provider": "openai",
@@ -21080,6 +21096,8 @@
"mode": "chat",
"output_cost_per_token": 1.8e-04,
"output_cost_per_token_above_272k_tokens": 2.7e-04,
"output_cost_per_token_flex": 9e-05,
"output_cost_per_token_batches": 9e-05,
"output_cost_per_token_priority": 2.7e-04,
"output_cost_per_token_above_272k_tokens_priority": 4.05e-04,
"supported_endpoints": [
model_prices_and_context_window.json
+18
View File
@@ -20936,10 +20936,13 @@
"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_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",
@@ -20949,6 +20952,8 @@
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"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,
"supported_endpoints": [
@@ -20980,10 +20985,13 @@
"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_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",
@@ -20993,6 +21001,8 @@
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"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,
"supported_endpoints": [
@@ -21026,6 +21036,8 @@
"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": 1.2e-04,
"litellm_provider": "openai",
@@ -21035,6 +21047,8 @@
"mode": "chat",
"output_cost_per_token": 1.8e-04,
"output_cost_per_token_above_272k_tokens": 2.7e-04,
"output_cost_per_token_flex": 9e-05,
"output_cost_per_token_batches": 9e-05,
"output_cost_per_token_priority": 2.7e-04,
"output_cost_per_token_above_272k_tokens_priority": 4.05e-04,
"supported_endpoints": [
@@ -21071,6 +21085,8 @@
"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": 1.2e-04,
"litellm_provider": "openai",
@@ -21080,6 +21096,8 @@
"mode": "chat",
"output_cost_per_token": 1.8e-04,
"output_cost_per_token_above_272k_tokens": 2.7e-04,
"output_cost_per_token_flex": 9e-05,
"output_cost_per_token_batches": 9e-05,
"output_cost_per_token_priority": 2.7e-04,
"output_cost_per_token_above_272k_tokens_priority": 4.05e-04,
"supported_endpoints": [