scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-17 04:34:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 265

fix(sambanova): correct DeepSeek-V3.2 context window (32k -> 128k)

Browse source
This commit is contained in:
bhumikadangayach 2026-06-26 12:05:51 +05:30
parent 710f6b2dcd
commit 34111e1213
2 changed files with 293 additions and 53 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

340
litellm/model_prices_and_context_window_backup.json
View file

@ -16410,6 +16410,47 @@
"tpm": 8000000,
"supports_image_size": false
},
"gemini-3-pro-image": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_batches": 6e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"web_search_billing_unit": "per_query",
"supports_service_tier": true
},
"gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
@ -16450,6 +16491,44 @@
},
"web_search_billing_unit": "per_query"
},
"gemini-3.1-flash-image": {
"input_cost_per_image": 0.00056,
"input_cost_per_token": 5e-07,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.0672,
"output_cost_per_image_token": 6e-05,
"output_cost_per_token": 3e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"web_search_billing_unit": "per_query"
},
"gemini-3.1-flash-image-preview": {
"input_cost_per_image": 0.00056,
"input_cost_per_token": 5e-07,
@ -17864,6 +17943,49 @@
},
"supports_image_size": false
},
"gemini/gemini-3-pro-image": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "gemini",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"rpm": 1000,
"tpm": 4000000,
"output_cost_per_token_batches": 6e-06,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"web_search_billing_unit": "per_query",
"supports_service_tier": true
},
"gemini/gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
@ -17906,6 +18028,48 @@
},
"web_search_billing_unit": "per_query"
},
"gemini/gemini-3.1-flash-image": {
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
"litellm_provider": "gemini",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.045,
"output_cost_per_image_token": 6e-05,
"output_cost_per_image_token_batches": 3e-05,
"output_cost_per_token": 1.5e-06,
"output_cost_per_token_batches": 7.5e-07,
"rpm": 1000,
"tpm": 4000000,
"source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_function_calling": false,
"supports_prompt_caching": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_vision": true,
"supports_web_search": true,
"search_context_cost_per_query": {
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"web_search_billing_unit": "per_query"
},
"gemini/gemini-3.1-flash-image-preview": {
"input_cost_per_token": 2.5e-07,
"input_cost_per_token_batches": 1.25e-07,
@ -22334,7 +22498,7 @@
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_priority": 1.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -22380,7 +22544,7 @@
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_priority": 1.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -22424,7 +22588,7 @@
"input_cost_per_token_flex": 1e-07,
"input_cost_per_token_batches": 1e-07,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -22467,7 +22631,7 @@
"input_cost_per_token_flex": 1e-07,
"input_cost_per_token_batches": 1e-07,
"litellm_provider": "openai",
"max_input_tokens": 272000,
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -22507,9 +22671,9 @@
"input_cost_per_token": 1.5e-05,
"input_cost_per_token_batches": 7.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 272000,
"max_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 0.00012,
"output_cost_per_token_batches": 6e-05,
@ -22543,9 +22707,9 @@
"input_cost_per_token": 1.5e-05,
"input_cost_per_token_batches": 7.5e-06,
"litellm_provider": "openai",
"max_input_tokens": 128000,
"max_output_tokens": 272000,
"max_tokens": 272000,
"max_input_tokens": 400000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"output_cost_per_token": 0.00012,
"output_cost_per_token_batches": 6e-05,
@ -29802,6 +29966,22 @@
"supports_reasoning": true,
"supports_tool_choice": true
},
"openrouter/z-ai/glm-5.1": {
"input_cost_per_token": 1.05e-06,
"output_cost_per_token": 3.5e-06,
"cache_read_input_token_cost": 5.25e-07,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "openrouter",
"max_input_tokens": 202752,
"max_output_tokens": 65535,
"max_tokens": 65535,
"mode": "chat",
"source": "https://openrouter.ai/z-ai/glm-5.1",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true
},
"openrouter/minimax/minimax-m2.1": {
"input_cost_per_token": 2.7e-07,
"output_cost_per_token": 1.2e-06,
@ -31406,7 +31586,7 @@
"supports_tool_choice": true
},
"sambanova/Meta-Llama-3.2-1B-Instruct": {
"deprecation_date": "2025-06-25",
"deprecation_date": "2025-06-25",
"input_cost_per_token": 4e-08,
"litellm_provider": "sambanova",
"max_input_tokens": 16384,
@ -31515,9 +31695,9 @@
"source": "https://cloud.sambanova.ai/plans/pricing"
},
"sambanova/DeepSeek-V3.2": {
"max_tokens": 32768,
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 3e-06,
"output_cost_per_token": 4.5e-06,
"litellm_provider": "sambanova",
@ -35576,6 +35756,21 @@
"tpm": 8000000,
"supports_image_size": false
},
"vertex_ai/gemini-3-pro-image": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
"input_cost_per_token_batches": 1e-06,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.134,
"output_cost_per_image_token": 0.00012,
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_batches": 6e-06,
"source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
},
"vertex_ai/gemini-3-pro-image-preview": {
"input_cost_per_image": 0.0011,
"input_cost_per_token": 2e-06,
@ -35591,6 +35786,19 @@
"output_cost_per_token_batches": 6e-06,
"source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
},
"vertex_ai/gemini-3.1-flash-image": {
"input_cost_per_image": 0.00056,
"input_cost_per_token": 5e-07,
"litellm_provider": "vertex_ai-language-models",
"max_input_tokens": 65536,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "image_generation",
"output_cost_per_image": 0.0672,
"output_cost_per_image_token": 6e-05,
"output_cost_per_token": 3e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
},
"vertex_ai/gemini-3.1-flash-image-preview": {
"input_cost_per_image": 0.00056,
"input_cost_per_token": 5e-07,
@ -37851,6 +38059,21 @@
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5.1": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 2.6e-07,
"input_cost_per_token": 1.4e-06,
"output_cost_per_token": 4.4e-06,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-5-code": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 3e-07,
@ -37881,6 +38104,21 @@
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.7-flash": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 0,
"input_cost_per_token": 0,
"output_cost_per_token": 0,
"litellm_provider": "zai",
"max_input_tokens": 200000,
"max_output_tokens": 128000,
"mode": "chat",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"source": "https://docs.z.ai/guides/overview/pricing"
},
"zai/glm-4.6": {
"cache_creation_input_token_cost": 0,
"cache_read_input_token_cost": 1.1e-07,
@ -43636,40 +43874,6 @@
"supports_tool_choice": true,
"supports_vision": false
},
"darkbloom/gemma-4-26b": {
"input_cost_per_token": 3e-08,
"litellm_provider": "darkbloom",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.65e-07,
"source": "https://www.darkbloom.dev/",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"darkbloom/gpt-oss-20b": {
"input_cost_per_token": 1.45e-08,
"litellm_provider": "darkbloom",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 7e-08,
"source": "https://www.darkbloom.dev/",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"deepseek/deepseek-v4-pro": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 3.625e-09,
@ -43773,7 +43977,43 @@
"supports_reasoning": false,
"source": "https://pinstripes.io/pricing"
},
"fallback_generalizations": {
"darkbloom/gemma-4-26b": {
"input_cost_per_token": 3e-08,
"litellm_provider": "darkbloom",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 1.65e-07,
"source": "https://www.darkbloom.dev/",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"darkbloom/gpt-oss-20b": {
"input_cost_per_token": 1.45e-08,
"litellm_provider": "darkbloom",
"max_input_tokens": 131072,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 7e-08,
"source": "https://www.darkbloom.dev/",
"supported_endpoints": [
"/v1/chat/completions"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_system_messages": true,
"supports_tool_choice": true
}
},
"fallback_generalizations": {
"rules": [
{
"name": "anthropic-claude-adaptive-thinking",
@ -43808,4 +44048,4 @@
}
]
}
}
}

6
model_prices_and_context_window.json
View file

@ -31689,9 +31689,9 @@
"source": "https://cloud.sambanova.ai/plans/pricing"
},
"sambanova/DeepSeek-V3.2": {
"max_tokens": 32768,
"max_input_tokens": 32768,
"max_output_tokens": 32768,
"max_tokens": 131072,
"max_input_tokens": 131072,
"max_output_tokens": 131072,
"input_cost_per_token": 3e-06,
"output_cost_per_token": 4.5e-06,
"litellm_provider": "sambanova",