scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-19 00:01:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 88

fix(pricing): update Gemini aliases and Nova cache prices

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
kerry 2026-09-14 23:45:51 +00:00
parent c626ff098b
commit c2424f1752
4 changed files with 456 additions and 243 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

322
litellm/model_prices_and_context_window_backup.json
View file

@ -354,6 +354,8 @@
},
"amazon.nova-lite-v1:0": {
"input_cost_per_token": 6e-08,
"cache_read_input_token_cost": 1.5e-08,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 300000,
"max_output_tokens": 10000,
@ -369,6 +371,7 @@
},
"amazon.nova-2-lite-v1:0": {
"cache_read_input_token_cost": 7.5e-08,
"cache_creation_input_token_cost": 0.0,
"input_cost_per_token": 3e-07,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
@ -407,6 +410,7 @@
},
"apac.amazon.nova-2-lite-v1:0": {
"cache_read_input_token_cost": 8.25e-08,
"cache_creation_input_token_cost": 0.0,
"input_cost_per_token": 3.3e-07,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
@ -445,6 +449,7 @@
},
"eu.amazon.nova-2-lite-v1:0": {
"cache_read_input_token_cost": 8.25e-08,
"cache_creation_input_token_cost": 0.0,
"input_cost_per_token": 3.3e-07,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
@ -483,6 +488,7 @@
},
"us.amazon.nova-2-lite-v1:0": {
"cache_read_input_token_cost": 8.25e-08,
"cache_creation_input_token_cost": 0.0,
"input_cost_per_token": 3.3e-07,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
@ -538,6 +544,8 @@
},
"amazon.nova-micro-v1:0": {
"input_cost_per_token": 3.5e-08,
"cache_read_input_token_cost": 8.75e-09,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 128000,
"max_output_tokens": 10000,
@ -551,6 +559,8 @@
},
"amazon.nova-pro-v1:0": {
"input_cost_per_token": 8e-07,
"cache_read_input_token_cost": 2e-07,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 300000,
"max_output_tokens": 10000,
@ -26391,16 +26401,82 @@
"supports_image_size": false
},
"gemini/gemini-flash-latest": {
"cache_read_input_token_cost": 3e-08,
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_flex": 3.75e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 3.75e-06,
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"rpm": 15,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_audio_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"tpm": 250000,
"input_cost_per_token_priority": 1.35e-06,
"output_cost_per_token_priority": 6.75e-06,
"cache_read_input_token_cost_priority": 1.35e-07,
"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",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini/gemini-flash-lite-latest": {
"cache_read_input_token_cost": 3e-08,
"cache_read_input_token_cost_flex": 2e-08,
"cache_read_input_token_cost_priority": 5e-08,
"input_cost_per_token": 3e-07,
"input_cost_per_token_batches": 1.5e-07,
"input_cost_per_token_flex": 1.5e-07,
"input_cost_per_token_priority": 5.4e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 2.5e-06,
"output_cost_per_token": 2.5e-06,
"output_cost_per_token_batches": 1.25e-06,
"output_cost_per_token_flex": 1.25e-06,
"output_cost_per_token_priority": 4.5e-06,
"rpm": 15,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
@ -26417,6 +26493,7 @@
"supported_output_modalities": [
"text"
],
"supports_audio_input": true,
"supports_audio_output": false,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -26427,62 +26504,18 @@
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"tpm": 250000,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"google_maps_grounding_cost_per_query": 0.025
},
"gemini/gemini-flash-lite-latest": {
"cache_read_input_token_cost": 1e-08,
"input_cost_per_audio_token": 3e-07,
"input_cost_per_token": 1e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"mode": "chat",
"output_cost_per_reasoning_token": 4e-07,
"output_cost_per_token": 4e-07,
"rpm": 15,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_vision": true,
"supports_web_search": true,
"tpm": 250000,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
},
"google_maps_grounding_cost_per_query": 0.025
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini/gemini-2.5-flash-lite-preview-06-17": {
"deprecation_date": "2025-11-18",
@ -29005,6 +29038,7 @@
},
"global.amazon.nova-2-lite-v1:0": {
"cache_read_input_token_cost": 7.5e-08,
"cache_creation_input_token_cost": 0.0,
"input_cost_per_token": 3e-07,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
@ -44626,6 +44660,8 @@
},
"us.amazon.nova-lite-v1:0": {
"input_cost_per_token": 6e-08,
"cache_read_input_token_cost": 1.5e-08,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 300000,
"max_output_tokens": 10000,
@ -44641,6 +44677,8 @@
},
"us.amazon.nova-micro-v1:0": {
"input_cost_per_token": 3.5e-08,
"cache_read_input_token_cost": 8.75e-09,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 128000,
"max_output_tokens": 10000,
@ -44655,6 +44693,8 @@
"us.amazon.nova-premier-v1:0": {
"deprecation_date": "2026-09-14",
"input_cost_per_token": 2.5e-06,
"cache_read_input_token_cost": 6.25e-07,
"supports_prompt_caching": true,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 10000,
@ -44663,12 +44703,13 @@
"output_cost_per_token": 1.25e-05,
"supports_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": false,
"supports_response_schema": true,
"supports_vision": true
},
"us.amazon.nova-pro-v1:0": {
"input_cost_per_token": 8e-07,
"cache_read_input_token_cost": 2e-07,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 300000,
"max_output_tokens": 10000,
@ -55604,65 +55645,84 @@
]
},
"gemini-flash-latest": {
"cache_read_input_token_cost": 3e-08,
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_flex": 3.75e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 3.75e-06,
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"rpm": 100000,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_audio_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"tpm": 8000000,
"input_cost_per_token_priority": 1.35e-06,
"output_cost_per_token_priority": 6.75e-06,
"cache_read_input_token_cost_priority": 1.35e-07,
"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",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini-flash-lite-latest": {
"cache_read_input_token_cost": 3e-08,
"cache_read_input_token_cost_flex": 2e-08,
"cache_read_input_token_cost_priority": 5e-08,
"input_cost_per_token": 3e-07,
"input_cost_per_token_batches": 1.5e-07,
"input_cost_per_token_flex": 1.5e-07,
"input_cost_per_token_priority": 5.4e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 2.5e-06,
"output_cost_per_token": 2.5e-06,
"rpm": 100000,
"source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_vision": true,
"supports_web_search": true,
"tpm": 8000000,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
},
"google_maps_grounding_cost_per_query": 0.025
},
"gemini-flash-lite-latest": {
"cache_read_input_token_cost": 1e-08,
"input_cost_per_audio_token": 3e-07,
"input_cost_per_token": 1e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"mode": "chat",
"output_cost_per_reasoning_token": 4e-07,
"output_cost_per_token": 4e-07,
"output_cost_per_token_batches": 1.25e-06,
"output_cost_per_token_flex": 1.25e-06,
"output_cost_per_token_priority": 4.5e-06,
"rpm": 15,
"source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -55677,6 +55737,7 @@
"supported_output_modalities": [
"text"
],
"supports_audio_input": true,
"supports_audio_output": false,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -55687,15 +55748,18 @@
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"tpm": 250000,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"google_maps_grounding_cost_per_query": 0.025
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini-pro-latest": {
"cache_read_input_token_cost": 1.25e-07,
@ -58083,7 +58147,13 @@
{
"name": "claude-adaptive-thinking",
"pattern": "claude-[a-z]+-(?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
"fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"],
"fill_missing_for_providers": [
"anthropic",
"azure_ai",
"bedrock",
"bedrock_converse",
"vertex_ai-anthropic_models"
],
"description": "Claude at version 4.6 or higher, in any id shape that contains claude-<family>-: minors 4.6 through 4.99, any later major-minor, and bare 5+ majors so a new family shaped like claude-fable-5 matches. Requiring the claude- prefix keeps non-Claude names such as team-sonnet-5-1 out. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Turns on adaptive thinking for new versions and new families with no code change.",
"model_info": {
"supports_adaptive_thinking": true
@ -58092,7 +58162,13 @@
{
"name": "claude-legacy-thinking",
"pattern": "claude-[a-z]+-4[-._]6(?!\\d)",
"fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"],
"fill_missing_for_providers": [
"anthropic",
"azure_ai",
"bedrock",
"bedrock_converse",
"vertex_ai-anthropic_models"
],
"description": "Claude at version 4.6 exactly, in any id shape that contains claude-<family>-4-6 (dotted and underscored minors included, dated releases such as claude-sonnet-4-6-20260219 too). The 4.6 family is adaptive-thinking yet still accepts legacy thinking.type=enabled with budget_tokens, so the caller's hard budget cap is forwarded verbatim instead of being rewritten to an uncapped output_config.effort. The lookahead keeps two-digit minors such as 4-60 from matching. 4.7+ and 5+ majors reject the legacy shape and stay on the adaptive translation.",
"model_info": {
"supports_legacy_thinking": true
@ -58109,7 +58185,13 @@
{
"name": "claude-mid-conversation-system",
"pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
"fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"],
"fill_missing_for_providers": [
"anthropic",
"azure_ai",
"bedrock",
"bedrock_converse",
"vertex_ai-anthropic_models"
],
"description": "Claude at version 4.8 or higher, in any id shape that contains claude-<family>-: minors 4.8 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic introduced mid-conversation system messages with Opus 4.8 and every newer Claude keeps them; 4.7 and below reject the system role inside messages.",
"model_info": {
"supports_mid_conversation_system": true
@ -58126,7 +58208,11 @@
{
"name": "openai-reasoning-family-baseline",
"pattern": "^(?!.*search-api)(?:[a-z0-9_.-]+/)*(?:ft:)?(?:o[1-9]\\d*(?![a-z0-9])|gpt-[5-9](?:\\.\\d+)?(?![0-9.])|(?:gpt-\\d+(?:\\.\\d+)?(?:-[a-z0-9]+)*-)?(?:codex|deep-research|chat-latest)(?![a-z0-9]))",
"fill_missing_for_providers": ["azure", "azure_ai", "openai"],
"fill_missing_for_providers": [
"azure",
"azure_ai",
"openai"
],
"description": "OpenAI reasoning families by id shape, under any provider namespace and with an optional ft: prefix: the o-series (o1, o3-pro, o4-mini), gpt-5 through gpt-9 majors including dotted minors and suffixed variants (gpt-5.5-cyber, gpt-6-astra), and the codex, deep-research and chat-latest lines when standalone or on a gpt base. gpt-5-search-api is excluded because it is a search-only surface. Every model here is a reasoning model, and the Responses API drops the caller's reasoning param for any mapped OpenAI model whose info lacks supports_reasoning, so an id the registry has not named yet keeps its reasoning settings instead of silently losing them. Rules lose to exact entries. Carries no mode and no pricing, so cost stays on the standard unpriced behavior.",
"model_info": {
"supports_reasoning": true

322
model_prices_and_context_window.json
View file

@ -354,6 +354,8 @@
},
"amazon.nova-lite-v1:0": {
"input_cost_per_token": 6e-08,
"cache_read_input_token_cost": 1.5e-08,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 300000,
"max_output_tokens": 10000,
@ -369,6 +371,7 @@
},
"amazon.nova-2-lite-v1:0": {
"cache_read_input_token_cost": 7.5e-08,
"cache_creation_input_token_cost": 0.0,
"input_cost_per_token": 3e-07,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
@ -407,6 +410,7 @@
},
"apac.amazon.nova-2-lite-v1:0": {
"cache_read_input_token_cost": 8.25e-08,
"cache_creation_input_token_cost": 0.0,
"input_cost_per_token": 3.3e-07,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
@ -445,6 +449,7 @@
},
"eu.amazon.nova-2-lite-v1:0": {
"cache_read_input_token_cost": 8.25e-08,
"cache_creation_input_token_cost": 0.0,
"input_cost_per_token": 3.3e-07,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
@ -483,6 +488,7 @@
},
"us.amazon.nova-2-lite-v1:0": {
"cache_read_input_token_cost": 8.25e-08,
"cache_creation_input_token_cost": 0.0,
"input_cost_per_token": 3.3e-07,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
@ -538,6 +544,8 @@
},
"amazon.nova-micro-v1:0": {
"input_cost_per_token": 3.5e-08,
"cache_read_input_token_cost": 8.75e-09,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 128000,
"max_output_tokens": 10000,
@ -551,6 +559,8 @@
},
"amazon.nova-pro-v1:0": {
"input_cost_per_token": 8e-07,
"cache_read_input_token_cost": 2e-07,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 300000,
"max_output_tokens": 10000,
@ -26391,16 +26401,82 @@
"supports_image_size": false
},
"gemini/gemini-flash-latest": {
"cache_read_input_token_cost": 3e-08,
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_flex": 3.75e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 3.75e-06,
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"rpm": 15,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_audio_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"tpm": 250000,
"input_cost_per_token_priority": 1.35e-06,
"output_cost_per_token_priority": 6.75e-06,
"cache_read_input_token_cost_priority": 1.35e-07,
"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",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini/gemini-flash-lite-latest": {
"cache_read_input_token_cost": 3e-08,
"cache_read_input_token_cost_flex": 2e-08,
"cache_read_input_token_cost_priority": 5e-08,
"input_cost_per_token": 3e-07,
"input_cost_per_token_batches": 1.5e-07,
"input_cost_per_token_flex": 1.5e-07,
"input_cost_per_token_priority": 5.4e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 2.5e-06,
"output_cost_per_token": 2.5e-06,
"output_cost_per_token_batches": 1.25e-06,
"output_cost_per_token_flex": 1.25e-06,
"output_cost_per_token_priority": 4.5e-06,
"rpm": 15,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
@ -26417,6 +26493,7 @@
"supported_output_modalities": [
"text"
],
"supports_audio_input": true,
"supports_audio_output": false,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -26427,62 +26504,18 @@
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"tpm": 250000,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"google_maps_grounding_cost_per_query": 0.025
},
"gemini/gemini-flash-lite-latest": {
"cache_read_input_token_cost": 1e-08,
"input_cost_per_audio_token": 3e-07,
"input_cost_per_token": 1e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"mode": "chat",
"output_cost_per_reasoning_token": 4e-07,
"output_cost_per_token": 4e-07,
"rpm": 15,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_vision": true,
"supports_web_search": true,
"tpm": 250000,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
},
"google_maps_grounding_cost_per_query": 0.025
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini/gemini-2.5-flash-lite-preview-06-17": {
"deprecation_date": "2025-11-18",
@ -29005,6 +29038,7 @@
},
"global.amazon.nova-2-lite-v1:0": {
"cache_read_input_token_cost": 7.5e-08,
"cache_creation_input_token_cost": 0.0,
"input_cost_per_token": 3e-07,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
@ -44626,6 +44660,8 @@
},
"us.amazon.nova-lite-v1:0": {
"input_cost_per_token": 6e-08,
"cache_read_input_token_cost": 1.5e-08,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 300000,
"max_output_tokens": 10000,
@ -44641,6 +44677,8 @@
},
"us.amazon.nova-micro-v1:0": {
"input_cost_per_token": 3.5e-08,
"cache_read_input_token_cost": 8.75e-09,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 128000,
"max_output_tokens": 10000,
@ -44655,6 +44693,8 @@
"us.amazon.nova-premier-v1:0": {
"deprecation_date": "2026-09-14",
"input_cost_per_token": 2.5e-06,
"cache_read_input_token_cost": 6.25e-07,
"supports_prompt_caching": true,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 10000,
@ -44663,12 +44703,13 @@
"output_cost_per_token": 1.25e-05,
"supports_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": false,
"supports_response_schema": true,
"supports_vision": true
},
"us.amazon.nova-pro-v1:0": {
"input_cost_per_token": 8e-07,
"cache_read_input_token_cost": 2e-07,
"cache_creation_input_token_cost": 0.0,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 300000,
"max_output_tokens": 10000,
@ -55604,65 +55645,84 @@
]
},
"gemini-flash-latest": {
"cache_read_input_token_cost": 3e-08,
"input_cost_per_audio_token": 1e-06,
"input_cost_per_token": 3e-07,
"prompt_cache_min_tokens": 4096,
"cache_read_input_token_cost": 7.5e-08,
"cache_read_input_token_cost_flex": 3.75e-08,
"input_cost_per_token": 7.5e-07,
"input_cost_per_token_batches": 3.75e-07,
"input_cost_per_token_flex": 3.75e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 3.75e-06,
"output_cost_per_token": 3.75e-06,
"output_cost_per_token_batches": 1.875e-06,
"output_cost_per_token_flex": 1.875e-06,
"rpm": 100000,
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_audio_input": true,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"tpm": 8000000,
"input_cost_per_token_priority": 1.35e-06,
"output_cost_per_token_priority": 6.75e-06,
"cache_read_input_token_cost_priority": 1.35e-07,
"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",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini-flash-lite-latest": {
"cache_read_input_token_cost": 3e-08,
"cache_read_input_token_cost_flex": 2e-08,
"cache_read_input_token_cost_priority": 5e-08,
"input_cost_per_token": 3e-07,
"input_cost_per_token_batches": 1.5e-07,
"input_cost_per_token_flex": 1.5e-07,
"input_cost_per_token_priority": 5.4e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65536,
"max_tokens": 65536,
"mode": "chat",
"output_cost_per_reasoning_token": 2.5e-06,
"output_cost_per_token": 2.5e-06,
"rpm": 100000,
"source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
"/v1/batch"
],
"supported_modalities": [
"text",
"image",
"audio",
"video"
],
"supported_output_modalities": [
"text"
],
"supports_audio_output": false,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_vision": true,
"supports_web_search": true,
"tpm": 8000000,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
},
"google_maps_grounding_cost_per_query": 0.025
},
"gemini-flash-lite-latest": {
"cache_read_input_token_cost": 1e-08,
"input_cost_per_audio_token": 3e-07,
"input_cost_per_token": 1e-07,
"litellm_provider": "gemini",
"max_input_tokens": 1048576,
"max_output_tokens": 65535,
"max_tokens": 65535,
"mode": "chat",
"output_cost_per_reasoning_token": 4e-07,
"output_cost_per_token": 4e-07,
"output_cost_per_token_batches": 1.25e-06,
"output_cost_per_token_flex": 1.25e-06,
"output_cost_per_token_priority": 4.5e-06,
"rpm": 15,
"source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite",
"source": "https://ai.google.dev/gemini-api/docs/pricing",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/completions",
@ -55677,6 +55737,7 @@
"supported_output_modalities": [
"text"
],
"supports_audio_input": true,
"supports_audio_output": false,
"supports_function_calling": true,
"supports_parallel_function_calling": true,
@ -55687,15 +55748,18 @@
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_url_context": true,
"supports_video_input": true,
"supports_vision": true,
"supports_web_search": true,
"supports_native_streaming": true,
"tpm": 250000,
"search_context_cost_per_query": {
"search_context_size_low": 0.035,
"search_context_size_medium": 0.035,
"search_context_size_high": 0.035
"search_context_size_low": 0.014,
"search_context_size_medium": 0.014,
"search_context_size_high": 0.014
},
"google_maps_grounding_cost_per_query": 0.025
"web_search_billing_unit": "per_query",
"google_maps_grounding_cost_per_query": 0.014
},
"gemini-pro-latest": {
"cache_read_input_token_cost": 1.25e-07,
@ -58083,7 +58147,13 @@
{
"name": "claude-adaptive-thinking",
"pattern": "claude-[a-z]+-(?:4[-._](?:[6-9]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
"fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"],
"fill_missing_for_providers": [
"anthropic",
"azure_ai",
"bedrock",
"bedrock_converse",
"vertex_ai-anthropic_models"
],
"description": "Claude at version 4.6 or higher, in any id shape that contains claude-<family>-: minors 4.6 through 4.99, any later major-minor, and bare 5+ majors so a new family shaped like claude-fable-5 matches. Requiring the claude- prefix keeps non-Claude names such as team-sonnet-5-1 out. The minor is capped at two digits so an 8-digit date suffix such as claude-opus-4-20250514 is never read as a >= 4.6 minor. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Turns on adaptive thinking for new versions and new families with no code change.",
"model_info": {
"supports_adaptive_thinking": true
@ -58092,7 +58162,13 @@
{
"name": "claude-legacy-thinking",
"pattern": "claude-[a-z]+-4[-._]6(?!\\d)",
"fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"],
"fill_missing_for_providers": [
"anthropic",
"azure_ai",
"bedrock",
"bedrock_converse",
"vertex_ai-anthropic_models"
],
"description": "Claude at version 4.6 exactly, in any id shape that contains claude-<family>-4-6 (dotted and underscored minors included, dated releases such as claude-sonnet-4-6-20260219 too). The 4.6 family is adaptive-thinking yet still accepts legacy thinking.type=enabled with budget_tokens, so the caller's hard budget cap is forwarded verbatim instead of being rewritten to an uncapped output_config.effort. The lookahead keeps two-digit minors such as 4-60 from matching. 4.7+ and 5+ majors reject the legacy shape and stay on the adaptive translation.",
"model_info": {
"supports_legacy_thinking": true
@ -58109,7 +58185,13 @@
{
"name": "claude-mid-conversation-system",
"pattern": "claude-[a-z]+-(?:4[-._](?:[89]|[1-9]\\d)(?!\\d)|[5-9](?!\\d)(?:[-._]\\d{1,2}(?!\\d))?)",
"fill_missing_for_providers": ["anthropic", "azure_ai", "bedrock", "bedrock_converse", "vertex_ai-anthropic_models"],
"fill_missing_for_providers": [
"anthropic",
"azure_ai",
"bedrock",
"bedrock_converse",
"vertex_ai-anthropic_models"
],
"description": "Claude at version 4.8 or higher, in any id shape that contains claude-<family>-: minors 4.8 through 4.99, any later major-minor, and bare 5+ majors so a new family like claude-fable-5 matches. Two-digit majors are deliberately not matched so ids like claude-opus-41 (4.1) are not read as major 41. Anthropic introduced mid-conversation system messages with Opus 4.8 and every newer Claude keeps them; 4.7 and below reject the system role inside messages.",
"model_info": {
"supports_mid_conversation_system": true
@ -58126,7 +58208,11 @@
{
"name": "openai-reasoning-family-baseline",
"pattern": "^(?!.*search-api)(?:[a-z0-9_.-]+/)*(?:ft:)?(?:o[1-9]\\d*(?![a-z0-9])|gpt-[5-9](?:\\.\\d+)?(?![0-9.])|(?:gpt-\\d+(?:\\.\\d+)?(?:-[a-z0-9]+)*-)?(?:codex|deep-research|chat-latest)(?![a-z0-9]))",
"fill_missing_for_providers": ["azure", "azure_ai", "openai"],
"fill_missing_for_providers": [
"azure",
"azure_ai",
"openai"
],
"description": "OpenAI reasoning families by id shape, under any provider namespace and with an optional ft: prefix: the o-series (o1, o3-pro, o4-mini), gpt-5 through gpt-9 majors including dotted minors and suffixed variants (gpt-5.5-cyber, gpt-6-astra), and the codex, deep-research and chat-latest lines when standalone or on a gpt base. gpt-5-search-api is excluded because it is a search-only surface. Every model here is a reasoning model, and the Responses API drops the caller's reasoning param for any mapped OpenAI model whose info lacks supports_reasoning, so an id the registry has not named yet keeps its reasoning settings instead of silently losing them. Rules lose to exact entries. Carries no mode and no pricing, so cost stays on the standard unpriced behavior.",
"model_info": {
"supports_reasoning": true

26
tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py
View file

@ -4,12 +4,10 @@ from typing import NamedTuple
import pytest
import litellm
from litellm.cost_calculator import completion_cost
from litellm.llms.bedrock.chat.converse_transformation import AmazonConverseConfig
from litellm.llms.bedrock.common_utils import BedrockModelInfo
from litellm.utils import _get_model_info_helper
from litellm.cost_calculator import completion_cost
from litellm.types.utils import (
Choices,
Message,
@ -17,6 +15,7 @@ from litellm.types.utils import (
PromptTokensDetailsWrapper,
Usage,
)
from litellm.utils import _get_model_info_helper
@pytest.fixture
@ -228,3 +227,24 @@ def test_bedrock_gpt_5_6_offers_tools_and_reasoning_effort_but_not_thinking(prof
assert "reasoning_effort" in supported
assert "thinking" not in supported
assert "output_config" not in supported
@pytest.mark.parametrize(
"model,expected_cache_read",
[
("amazon.nova-lite-v1:0", 1.5e-8),
("us.amazon.nova-lite-v1:0", 1.5e-8),
("amazon.nova-micro-v1:0", 8.75e-9),
("us.amazon.nova-micro-v1:0", 8.75e-9),
("amazon.nova-pro-v1:0", 2e-7),
("us.amazon.nova-pro-v1:0", 2e-7),
("us.amazon.nova-premier-v1:0", 6.25e-7),
],
)
def test_bedrock_nova_cache_read_prices(model, expected_cache_read, local_model_cost_map):
model_info = litellm.model_cost[model]
assert model_info["cache_read_input_token_cost"] == expected_cache_read
assert model_info["cache_read_input_token_cost"] == pytest.approx(
0.25 * model_info["input_cost_per_token"]
)

29
tests/test_litellm/llms/gemini/test_cost_calculator.py
View file

@ -1,5 +1,3 @@
import os
import pytest
import litellm
@ -455,8 +453,8 @@ def test_map_traffic_type_to_service_tier(
@pytest.mark.parametrize(
"model,custom_llm_provider,expected_cache_read_cost",
[
("gemini/gemini-flash-latest", "gemini", 3e-08),
("gemini/gemini-flash-lite-latest", "gemini", 1e-08),
("gemini/gemini-flash-latest", "gemini", 7.5e-08),
("gemini/gemini-flash-lite-latest", "gemini", 3e-08),
("gemini/gemini-2.5-flash-preview-09-2025", "gemini", 3e-08),
("gemini/gemini-2.5-flash-lite-preview-06-17", "gemini", 1e-08),
("vertex_ai/gemini-2.5-flash-preview-09-2025", "vertex_ai", 3e-08),
@ -479,6 +477,29 @@ def test_flash_alias_cache_read_is_ten_percent_of_input(
)
@pytest.mark.parametrize(
"alias,target",
[
("gemini/gemini-flash-latest", "gemini/gemini-3.8-flash"),
("gemini/gemini-flash-lite-latest", "gemini/gemini-3.5-flash-lite"),
],
)
def test_flash_latest_aliases_price_as_their_current_target(monkeypatch, alias, target):
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
alias_entry = litellm.model_cost[alias]
target_entry = litellm.model_cost[target]
for cost_key in (
"input_cost_per_token",
"output_cost_per_token",
"cache_read_input_token_cost",
"max_output_tokens",
):
assert alias_entry[cost_key] == target_entry[cost_key]
@pytest.mark.parametrize(
"prefixed,bare",
[