Skip to content

Commit d5ced7e

Browse files
Merge pull request #14639 from danielmklein/main
fix: update sonnet 4 configs to reflect million-token context window pricing
2 parents a482737 + b8b3077 commit d5ced7e

File tree

2 files changed

+108
-48
lines changed

2 files changed

+108
-48
lines changed

litellm/model_prices_and_context_window_backup.json

Lines changed: 54 additions & 24 deletions
Original file line numberDiff line numberDiff line change
@@ -560,10 +560,14 @@
560560
"cache_creation_input_token_cost": 3.75e-06,
561561
"cache_read_input_token_cost": 3e-07,
562562
"input_cost_per_token": 3e-06,
563+
"input_cost_per_token_above_200k_tokens": 6e-06,
564+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
565+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
566+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
563567
"litellm_provider": "bedrock_converse",
564-
"max_input_tokens": 200000,
565-
"max_output_tokens": 64000,
566-
"max_tokens": 64000,
568+
"max_input_tokens": 1000000,
569+
"max_output_tokens": 1000000,
570+
"max_tokens": 1000000,
567571
"mode": "chat",
568572
"output_cost_per_token": 1.5e-05,
569573
"search_context_cost_per_query": {
@@ -824,10 +828,14 @@
824828
"cache_creation_input_token_cost": 3.75e-06,
825829
"cache_read_input_token_cost": 3e-07,
826830
"input_cost_per_token": 3e-06,
831+
"input_cost_per_token_above_200k_tokens": 6e-06,
832+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
833+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
834+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
827835
"litellm_provider": "bedrock_converse",
828-
"max_input_tokens": 200000,
829-
"max_output_tokens": 64000,
830-
"max_tokens": 64000,
836+
"max_input_tokens": 1000000,
837+
"max_output_tokens": 1000000,
838+
"max_tokens": 1000000,
831839
"mode": "chat",
832840
"output_cost_per_token": 1.5e-05,
833841
"search_context_cost_per_query": {
@@ -4787,10 +4795,14 @@
47874795
"cache_creation_input_token_cost_above_1hr": 6e-06,
47884796
"cache_read_input_token_cost": 3e-07,
47894797
"input_cost_per_token": 3e-06,
4798+
"input_cost_per_token_above_200k_tokens": 6e-06,
4799+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
4800+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
4801+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
47904802
"litellm_provider": "anthropic",
4791-
"max_input_tokens": 200000,
4792-
"max_output_tokens": 64000,
4793-
"max_tokens": 64000,
4803+
"max_input_tokens": 1000000,
4804+
"max_output_tokens": 1000000,
4805+
"max_tokens": 1000000,
47944806
"mode": "chat",
47954807
"output_cost_per_token": 1.5e-05,
47964808
"search_context_cost_per_query": {
@@ -7547,10 +7559,14 @@
75477559
"cache_creation_input_token_cost": 3.75e-06,
75487560
"cache_read_input_token_cost": 3e-07,
75497561
"input_cost_per_token": 3e-06,
7562+
"input_cost_per_token_above_200k_tokens": 6e-06,
7563+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
7564+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
7565+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
75507566
"litellm_provider": "bedrock_converse",
7551-
"max_input_tokens": 200000,
7552-
"max_output_tokens": 64000,
7553-
"max_tokens": 64000,
7567+
"max_input_tokens": 1000000,
7568+
"max_output_tokens": 1000000,
7569+
"max_tokens": 1000000,
75547570
"mode": "chat",
75557571
"output_cost_per_token": 1.5e-05,
75567572
"search_context_cost_per_query": {
@@ -16157,10 +16173,12 @@
1615716173
"openrouter/anthropic/claude-sonnet-4": {
1615816174
"input_cost_per_image": 0.0048,
1615916175
"input_cost_per_token": 3e-06,
16176+
"input_cost_per_token_above_200k_tokens": 6e-06,
16177+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
1616016178
"litellm_provider": "openrouter",
16161-
"max_input_tokens": 200000,
16162-
"max_output_tokens": 64000,
16163-
"max_tokens": 64000,
16179+
"max_input_tokens": 1000000,
16180+
"max_output_tokens": 1000000,
16181+
"max_tokens": 1000000,
1616416182
"mode": "chat",
1616516183
"output_cost_per_token": 1.5e-05,
1616616184
"supports_assistant_prefill": true,
@@ -19020,10 +19038,14 @@
1902019038
"cache_creation_input_token_cost": 3.75e-06,
1902119039
"cache_read_input_token_cost": 3e-07,
1902219040
"input_cost_per_token": 3e-06,
19041+
"input_cost_per_token_above_200k_tokens": 6e-06,
19042+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
19043+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
19044+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
1902319045
"litellm_provider": "bedrock_converse",
19024-
"max_input_tokens": 200000,
19025-
"max_output_tokens": 64000,
19026-
"max_tokens": 64000,
19046+
"max_input_tokens": 1000000,
19047+
"max_output_tokens": 1000000,
19048+
"max_tokens": 1000000,
1902719049
"mode": "chat",
1902819050
"output_cost_per_token": 1.5e-05,
1902919051
"search_context_cost_per_query": {
@@ -20356,10 +20378,14 @@
2035620378
"cache_creation_input_token_cost": 3.75e-06,
2035720379
"cache_read_input_token_cost": 3e-07,
2035820380
"input_cost_per_token": 3e-06,
20381+
"input_cost_per_token_above_200k_tokens": 6e-06,
20382+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
20383+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
20384+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
2035920385
"litellm_provider": "vertex_ai-anthropic_models",
20360-
"max_input_tokens": 200000,
20361-
"max_output_tokens": 64000,
20362-
"max_tokens": 64000,
20386+
"max_input_tokens": 1000000,
20387+
"max_output_tokens": 1000000,
20388+
"max_tokens": 1000000,
2036320389
"mode": "chat",
2036420390
"output_cost_per_token": 1.5e-05,
2036520391
"search_context_cost_per_query": {
@@ -20382,10 +20408,14 @@
2038220408
"cache_creation_input_token_cost": 3.75e-06,
2038320409
"cache_read_input_token_cost": 3e-07,
2038420410
"input_cost_per_token": 3e-06,
20411+
"input_cost_per_token_above_200k_tokens": 6e-06,
20412+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
20413+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
20414+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
2038520415
"litellm_provider": "vertex_ai-anthropic_models",
20386-
"max_input_tokens": 200000,
20387-
"max_output_tokens": 64000,
20388-
"max_tokens": 64000,
20416+
"max_input_tokens": 1000000,
20417+
"max_output_tokens": 1000000,
20418+
"max_tokens": 1000000,
2038920419
"mode": "chat",
2039020420
"output_cost_per_token": 1.5e-05,
2039120421
"search_context_cost_per_query": {

model_prices_and_context_window.json

Lines changed: 54 additions & 24 deletions
Original file line numberDiff line numberDiff line change
@@ -560,10 +560,14 @@
560560
"cache_creation_input_token_cost": 3.75e-06,
561561
"cache_read_input_token_cost": 3e-07,
562562
"input_cost_per_token": 3e-06,
563+
"input_cost_per_token_above_200k_tokens": 6e-06,
564+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
565+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
566+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
563567
"litellm_provider": "bedrock_converse",
564-
"max_input_tokens": 200000,
565-
"max_output_tokens": 64000,
566-
"max_tokens": 64000,
568+
"max_input_tokens": 1000000,
569+
"max_output_tokens": 1000000,
570+
"max_tokens": 1000000,
567571
"mode": "chat",
568572
"output_cost_per_token": 1.5e-05,
569573
"search_context_cost_per_query": {
@@ -824,10 +828,14 @@
824828
"cache_creation_input_token_cost": 3.75e-06,
825829
"cache_read_input_token_cost": 3e-07,
826830
"input_cost_per_token": 3e-06,
831+
"input_cost_per_token_above_200k_tokens": 6e-06,
832+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
833+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
834+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
827835
"litellm_provider": "bedrock_converse",
828-
"max_input_tokens": 200000,
829-
"max_output_tokens": 64000,
830-
"max_tokens": 64000,
836+
"max_input_tokens": 1000000,
837+
"max_output_tokens": 1000000,
838+
"max_tokens": 1000000,
831839
"mode": "chat",
832840
"output_cost_per_token": 1.5e-05,
833841
"search_context_cost_per_query": {
@@ -4787,10 +4795,14 @@
47874795
"cache_creation_input_token_cost_above_1hr": 6e-06,
47884796
"cache_read_input_token_cost": 3e-07,
47894797
"input_cost_per_token": 3e-06,
4798+
"input_cost_per_token_above_200k_tokens": 6e-06,
4799+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
4800+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
4801+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
47904802
"litellm_provider": "anthropic",
4791-
"max_input_tokens": 200000,
4792-
"max_output_tokens": 64000,
4793-
"max_tokens": 64000,
4803+
"max_input_tokens": 1000000,
4804+
"max_output_tokens": 1000000,
4805+
"max_tokens": 1000000,
47944806
"mode": "chat",
47954807
"output_cost_per_token": 1.5e-05,
47964808
"search_context_cost_per_query": {
@@ -7547,10 +7559,14 @@
75477559
"cache_creation_input_token_cost": 3.75e-06,
75487560
"cache_read_input_token_cost": 3e-07,
75497561
"input_cost_per_token": 3e-06,
7562+
"input_cost_per_token_above_200k_tokens": 6e-06,
7563+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
7564+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
7565+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
75507566
"litellm_provider": "bedrock_converse",
7551-
"max_input_tokens": 200000,
7552-
"max_output_tokens": 64000,
7553-
"max_tokens": 64000,
7567+
"max_input_tokens": 1000000,
7568+
"max_output_tokens": 1000000,
7569+
"max_tokens": 1000000,
75547570
"mode": "chat",
75557571
"output_cost_per_token": 1.5e-05,
75567572
"search_context_cost_per_query": {
@@ -16157,10 +16173,12 @@
1615716173
"openrouter/anthropic/claude-sonnet-4": {
1615816174
"input_cost_per_image": 0.0048,
1615916175
"input_cost_per_token": 3e-06,
16176+
"input_cost_per_token_above_200k_tokens": 6e-06,
16177+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
1616016178
"litellm_provider": "openrouter",
16161-
"max_input_tokens": 200000,
16162-
"max_output_tokens": 64000,
16163-
"max_tokens": 64000,
16179+
"max_input_tokens": 1000000,
16180+
"max_output_tokens": 1000000,
16181+
"max_tokens": 1000000,
1616416182
"mode": "chat",
1616516183
"output_cost_per_token": 1.5e-05,
1616616184
"supports_assistant_prefill": true,
@@ -19020,10 +19038,14 @@
1902019038
"cache_creation_input_token_cost": 3.75e-06,
1902119039
"cache_read_input_token_cost": 3e-07,
1902219040
"input_cost_per_token": 3e-06,
19041+
"input_cost_per_token_above_200k_tokens": 6e-06,
19042+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
19043+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
19044+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
1902319045
"litellm_provider": "bedrock_converse",
19024-
"max_input_tokens": 200000,
19025-
"max_output_tokens": 64000,
19026-
"max_tokens": 64000,
19046+
"max_input_tokens": 1000000,
19047+
"max_output_tokens": 1000000,
19048+
"max_tokens": 1000000,
1902719049
"mode": "chat",
1902819050
"output_cost_per_token": 1.5e-05,
1902919051
"search_context_cost_per_query": {
@@ -20356,10 +20378,14 @@
2035620378
"cache_creation_input_token_cost": 3.75e-06,
2035720379
"cache_read_input_token_cost": 3e-07,
2035820380
"input_cost_per_token": 3e-06,
20381+
"input_cost_per_token_above_200k_tokens": 6e-06,
20382+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
20383+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
20384+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
2035920385
"litellm_provider": "vertex_ai-anthropic_models",
20360-
"max_input_tokens": 200000,
20361-
"max_output_tokens": 64000,
20362-
"max_tokens": 64000,
20386+
"max_input_tokens": 1000000,
20387+
"max_output_tokens": 1000000,
20388+
"max_tokens": 1000000,
2036320389
"mode": "chat",
2036420390
"output_cost_per_token": 1.5e-05,
2036520391
"search_context_cost_per_query": {
@@ -20382,10 +20408,14 @@
2038220408
"cache_creation_input_token_cost": 3.75e-06,
2038320409
"cache_read_input_token_cost": 3e-07,
2038420410
"input_cost_per_token": 3e-06,
20411+
"input_cost_per_token_above_200k_tokens": 6e-06,
20412+
"output_cost_per_token_above_200k_tokens": 2.25e-05,
20413+
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
20414+
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
2038520415
"litellm_provider": "vertex_ai-anthropic_models",
20386-
"max_input_tokens": 200000,
20387-
"max_output_tokens": 64000,
20388-
"max_tokens": 64000,
20416+
"max_input_tokens": 1000000,
20417+
"max_output_tokens": 1000000,
20418+
"max_tokens": 1000000,
2038920419
"mode": "chat",
2039020420
"output_cost_per_token": 1.5e-05,
2039120421
"search_context_cost_per_query": {

0 commit comments

Comments
 (0)