scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-06 08:16:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

fix: correct max_input_tokens for Claude Opus 4.6 from 1M to 200K base limit (#23506)

Browse source
This commit is contained in:
yash27-lab 2026-03-25 20:37:31 -04:00
parent 0d2b454cec
commit 2d96454bfb
2 changed files with 28 additions and 54 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

41
litellm/model_prices_and_context_window_backup.json
View file

@ -977,7 +977,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -1007,7 +1007,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -1037,7 +1037,7 @@
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_200k_tokens": 1.1e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -1067,7 +1067,7 @@
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_200k_tokens": 1.1e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -1097,7 +1097,7 @@
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_200k_tokens": 1.1e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -8702,7 +8702,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -8737,7 +8737,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -14604,17 +14604,14 @@
"uses_embed_content": true
},
"vertex_ai/gemini-embedding-2-preview": {
"input_cost_per_audio_per_second": 0.00016,
"input_cost_per_image": 0.00012,
"input_cost_per_token": 2e-07,
"input_cost_per_video_per_second": 0.00079,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
"supports_multimodal": true,
"uses_embed_content": true
},
@ -14631,18 +14628,6 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"uses_embed_content": true
},
"vertex_ai/gemini-embedding-2-preview": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
"supports_multimodal": true,
"uses_embed_content": true
},
"gemini/gemini-embedding-001": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "gemini",
@ -30329,7 +30314,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -30359,7 +30344,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -31147,7 +31132,9 @@
"mode": "chat",
"output_cost_per_token": 3.2e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models",
"supported_regions": ["global"],
"supported_regions": [
"global"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,

41
model_prices_and_context_window.json
View file

@ -977,7 +977,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -1007,7 +1007,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -1037,7 +1037,7 @@
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_200k_tokens": 1.1e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -1067,7 +1067,7 @@
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_200k_tokens": 1.1e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -1097,7 +1097,7 @@
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_200k_tokens": 1.1e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -8702,7 +8702,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -8737,7 +8737,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -14604,17 +14604,14 @@
"uses_embed_content": true
},
"vertex_ai/gemini-embedding-2-preview": {
"input_cost_per_audio_per_second": 0.00016,
"input_cost_per_image": 0.00012,
"input_cost_per_token": 2e-07,
"input_cost_per_video_per_second": 0.00079,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
"supports_multimodal": true,
"uses_embed_content": true
},
@ -14631,18 +14628,6 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"uses_embed_content": true
},
"vertex_ai/gemini-embedding-2-preview": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
"supports_multimodal": true,
"uses_embed_content": true
},
"gemini/gemini-embedding-001": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "gemini",
@ -30329,7 +30314,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -30359,7 +30344,7 @@
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -31147,7 +31132,9 @@
"mode": "chat",
"output_cost_per_token": 3.2e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models",
"supported_regions": ["global"],
"supported_regions": [
"global"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,