scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-10 22:41:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 82

fix(registry): add Bedrock gpt-6-astra CRIS + mantle profiles, embed-v4/pegasus global profiles, gpt-image-2.5 entries; cap Vertex grok-4.1-fast output at 128k

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
mateo 2026-09-09 19:15:44 +00:00
parent 23ed208339
commit 00e4380cb5
2 changed files with 368 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

188
litellm/model_prices_and_context_window_backup.json
View file

@ -759,6 +759,14 @@
"mode": "chat",
"supports_video_input": true
},
"global.twelvelabs.pegasus-1-2-v1:0": {
"input_cost_per_video_per_second": 0.00049,
"output_cost_per_token": 7.5e-06,
"litellm_provider": "bedrock",
"mode": "chat",
"supports_video_input": true,
"source": "https://aws.amazon.com/bedrock/pricing/"
},
"amazon.titan-text-express-v1": {
"input_cost_per_token": 1.3e-06,
"litellm_provider": "bedrock",
@ -14431,6 +14439,28 @@
"output_vector_size": 1536,
"supports_embedding_image_input": true
},
"us.cohere.embed-v4:0": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_tokens": 128000,
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 1536,
"supports_embedding_image_input": true,
"source": "https://aws.amazon.com/bedrock/pricing/"
},
"global.cohere.embed-v4:0": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_tokens": 128000,
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 1536,
"supports_embedding_image_input": true,
"source": "https://aws.amazon.com/bedrock/pricing/"
},
"cohere/embed-v4.0": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "cohere",
@ -29748,6 +29778,66 @@
"supports_vision": true,
"supports_pdf_input": true
},
"gpt-image-2.5-flare": {
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 5e-06,
"litellm_provider": "openai",
"mode": "image_generation",
"input_cost_per_image_token": 8e-06,
"output_cost_per_image_token": 3e-05,
"supported_endpoints": [
"/v1/images/generations",
"/v1/images/edits"
],
"supports_vision": true,
"supports_pdf_input": true,
"source": "https://developers.openai.com/api/docs/pricing"
},
"gpt-image-2.5-flare-2026-09-08": {
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 5e-06,
"litellm_provider": "openai",
"mode": "image_generation",
"input_cost_per_image_token": 8e-06,
"output_cost_per_image_token": 3e-05,
"supported_endpoints": [
"/v1/images/generations",
"/v1/images/edits"
],
"supports_vision": true,
"supports_pdf_input": true,
"source": "https://developers.openai.com/api/docs/pricing"
},
"gpt-image-2.5-sunburst": {
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 5e-06,
"litellm_provider": "openai",
"mode": "image_generation",
"input_cost_per_image_token": 8e-06,
"output_cost_per_image_token": 3e-05,
"supported_endpoints": [
"/v1/images/generations",
"/v1/images/edits"
],
"supports_vision": true,
"supports_pdf_input": true,
"source": "https://developers.openai.com/api/docs/pricing"
},
"gpt-image-2.5-sunburst-2026-09-08": {
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 5e-06,
"litellm_provider": "openai",
"mode": "image_generation",
"input_cost_per_image_token": 8e-06,
"output_cost_per_image_token": 3e-05,
"supported_endpoints": [
"/v1/images/generations",
"/v1/images/edits"
],
"supports_vision": true,
"supports_pdf_input": true,
"source": "https://developers.openai.com/api/docs/pricing"
},
"low/1024-x-1024/gpt-image-1.5": {
"deprecation_date": "2026-12-01",
"input_cost_per_image": 0.009,
@ -48040,8 +48130,8 @@
"input_cost_per_token": 2e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 128000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"source": "https://docs.x.ai/developers/models",
@ -48056,8 +48146,8 @@
"input_cost_per_token": 2e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 128000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"source": "https://docs.x.ai/developers/models",
@ -55429,6 +55519,96 @@
"supports_reasoning": true,
"supports_vision": true
},
"bedrock_mantle/openai.gpt-6-astra": {
"input_cost_per_token": 1.1e-05,
"input_cost_per_token_above_272k_tokens": 2.2e-05,
"cache_creation_input_token_cost": 1.375e-05,
"cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
"cache_read_input_token_cost": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
"output_cost_per_token": 5.5e-05,
"output_cost_per_token_above_272k_tokens": 8.25e-05,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html"
},
"us.openai.gpt-6-astra": {
"input_cost_per_token": 1.1e-05,
"input_cost_per_token_above_272k_tokens": 2.2e-05,
"cache_creation_input_token_cost": 1.375e-05,
"cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
"cache_read_input_token_cost": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
"output_cost_per_token": 5.5e-05,
"output_cost_per_token_above_272k_tokens": 8.25e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true,
"source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html"
},
"global.openai.gpt-6-astra": {
"input_cost_per_token": 1e-05,
"input_cost_per_token_above_272k_tokens": 2e-05,
"cache_creation_input_token_cost": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
"cache_read_input_token_cost": 1e-06,
"cache_read_input_token_cost_above_272k_tokens": 2e-06,
"output_cost_per_token": 5e-05,
"output_cost_per_token_above_272k_tokens": 7.5e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true,
"source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html"
},
"bedrock_mantle/openai.gpt-5.5": {
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,

188
model_prices_and_context_window.json
View file

@ -759,6 +759,14 @@
"mode": "chat",
"supports_video_input": true
},
"global.twelvelabs.pegasus-1-2-v1:0": {
"input_cost_per_video_per_second": 0.00049,
"output_cost_per_token": 7.5e-06,
"litellm_provider": "bedrock",
"mode": "chat",
"supports_video_input": true,
"source": "https://aws.amazon.com/bedrock/pricing/"
},
"amazon.titan-text-express-v1": {
"input_cost_per_token": 1.3e-06,
"litellm_provider": "bedrock",
@ -14431,6 +14439,28 @@
"output_vector_size": 1536,
"supports_embedding_image_input": true
},
"us.cohere.embed-v4:0": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_tokens": 128000,
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 1536,
"supports_embedding_image_input": true,
"source": "https://aws.amazon.com/bedrock/pricing/"
},
"global.cohere.embed-v4:0": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_tokens": 128000,
"mode": "embedding",
"output_cost_per_token": 0.0,
"output_vector_size": 1536,
"supports_embedding_image_input": true,
"source": "https://aws.amazon.com/bedrock/pricing/"
},
"cohere/embed-v4.0": {
"input_cost_per_token": 1.2e-07,
"litellm_provider": "cohere",
@ -29748,6 +29778,66 @@
"supports_vision": true,
"supports_pdf_input": true
},
"gpt-image-2.5-flare": {
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 5e-06,
"litellm_provider": "openai",
"mode": "image_generation",
"input_cost_per_image_token": 8e-06,
"output_cost_per_image_token": 3e-05,
"supported_endpoints": [
"/v1/images/generations",
"/v1/images/edits"
],
"supports_vision": true,
"supports_pdf_input": true,
"source": "https://developers.openai.com/api/docs/pricing"
},
"gpt-image-2.5-flare-2026-09-08": {
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 5e-06,
"litellm_provider": "openai",
"mode": "image_generation",
"input_cost_per_image_token": 8e-06,
"output_cost_per_image_token": 3e-05,
"supported_endpoints": [
"/v1/images/generations",
"/v1/images/edits"
],
"supports_vision": true,
"supports_pdf_input": true,
"source": "https://developers.openai.com/api/docs/pricing"
},
"gpt-image-2.5-sunburst": {
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 5e-06,
"litellm_provider": "openai",
"mode": "image_generation",
"input_cost_per_image_token": 8e-06,
"output_cost_per_image_token": 3e-05,
"supported_endpoints": [
"/v1/images/generations",
"/v1/images/edits"
],
"supports_vision": true,
"supports_pdf_input": true,
"source": "https://developers.openai.com/api/docs/pricing"
},
"gpt-image-2.5-sunburst-2026-09-08": {
"cache_read_input_token_cost": 1.25e-06,
"input_cost_per_token": 5e-06,
"litellm_provider": "openai",
"mode": "image_generation",
"input_cost_per_image_token": 8e-06,
"output_cost_per_image_token": 3e-05,
"supported_endpoints": [
"/v1/images/generations",
"/v1/images/edits"
],
"supports_vision": true,
"supports_pdf_input": true,
"source": "https://developers.openai.com/api/docs/pricing"
},
"low/1024-x-1024/gpt-image-1.5": {
"deprecation_date": "2026-12-01",
"input_cost_per_image": 0.009,
@ -48040,8 +48130,8 @@
"input_cost_per_token": 2e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 128000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"source": "https://docs.x.ai/developers/models",
@ -48056,8 +48146,8 @@
"input_cost_per_token": 2e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 128000,
"max_output_tokens": 2000000,
"max_tokens": 2000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5e-07,
"source": "https://docs.x.ai/developers/models",
@ -55429,6 +55519,96 @@
"supports_reasoning": true,
"supports_vision": true
},
"bedrock_mantle/openai.gpt-6-astra": {
"input_cost_per_token": 1.1e-05,
"input_cost_per_token_above_272k_tokens": 2.2e-05,
"cache_creation_input_token_cost": 1.375e-05,
"cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
"cache_read_input_token_cost": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
"output_cost_per_token": 5.5e-05,
"output_cost_per_token_above_272k_tokens": 8.25e-05,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html"
},
"us.openai.gpt-6-astra": {
"input_cost_per_token": 1.1e-05,
"input_cost_per_token_above_272k_tokens": 2.2e-05,
"cache_creation_input_token_cost": 1.375e-05,
"cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
"cache_read_input_token_cost": 1.1e-06,
"cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
"output_cost_per_token": 5.5e-05,
"output_cost_per_token_above_272k_tokens": 8.25e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true,
"source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html"
},
"global.openai.gpt-6-astra": {
"input_cost_per_token": 1e-05,
"input_cost_per_token_above_272k_tokens": 2e-05,
"cache_creation_input_token_cost": 1.25e-05,
"cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
"cache_read_input_token_cost": 1e-06,
"cache_read_input_token_cost_above_272k_tokens": 2e-06,
"output_cost_per_token": 5e-05,
"output_cost_per_token_above_272k_tokens": 7.5e-05,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": true,
"source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html"
},
"bedrock_mantle/openai.gpt-5.5": {
"input_cost_per_token": 5.5e-06,
"input_cost_per_token_above_272k_tokens": 1.1e-05,