scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-29 06:33:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 200

fix(model_prices): consolidate claude-haiku-5-5 over-100k pricing and capability flags (#45151)

Browse source 
Backport of #45151 to stable/1.103.x.
Cherry-picked from 46d440ae96 (main).
Adapted to the line: the model-catalog Rust crate is not on this line so its two files are dropped; tests live under tests/test_litellm; conflicts resolved by keeping the line's fields plus the over-100k fields this PR adds.
Prerequisite from #39861 ported minimally: the standard above-threshold loop skips *_batches keys, so a non-batch request over 100k is not billed at the batch tier. The batch long-context tier tests are dropped since this line's batch cost path has no long-context tiers, and the runtime profile test calls the line's private _is_adaptive_thinking_model.
This commit is contained in:
devin-ai-integration[bot] 2026-10-20 15:52:10 -07:00 • committed by Mrinal Chanshetty
parent 5944ba05f7
commit f02a05fb32
9 changed files with 604 additions and 84 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
litellm/litellm_core_utils/llm_cost_calc/utils.py
View file

@ -56,6 +56,8 @@ _VALID_DATA_RESIDENCIES: Final = frozenset(r.value for r in DataResidency)
_SERVICE_TIER_SUFFIXES: Final[tuple[str, ...]] = tuple(
sorted((f"_{st.value}" for st in ServiceTier), key=len, reverse=True)
)
_BATCH_KEY_SUFFIX: Final = "_batches"
_NON_STANDARD_THRESHOLD_SUFFIXES: Final = (*_SERVICE_TIER_SUFFIXES, _BATCH_KEY_SUFFIX)
_SERVICE_TIER_TO_COST_KEY_SUFFIX: Final[Mapping[str, str]] = MappingProxyType(
{
@ -576,7 +578,9 @@ def _get_token_base_cost(
# so that the threshold detection loop only processes standard keys. The
# service_tier-specific above-threshold key is resolved later via _get_service_tier_cost_key.
threshold_keys: Final = [
k for k in model_info if k.startswith("input_cost_per_token_above_") and not k.endswith(_SERVICE_TIER_SUFFIXES)
k
for k in model_info
if k.startswith("input_cost_per_token_above_") and not k.endswith(_NON_STANDARD_THRESHOLD_SUFFIXES)
]
# Only sort the threshold keys (typically 1-2 keys instead of 66+)

197
litellm/model_prices_and_context_window_backup.json
View file

@ -75042,6 +75042,10 @@
"supports_web_search": false
},
"claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens_batches": 2.5e-07,
"output_cost_per_token_above_100k_tokens_batches": 1.25e-06,
"cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07,
"cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08,
"supports_anthropic_compaction": true,
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_1hr": 2e-07,
@ -75081,8 +75085,8 @@
"us": 1.1
},
"supports_output_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://platform.claude.com/docs/en/models/haiku-5-5/overview",
"supports_web_search": true,
@ -75093,6 +75097,11 @@
"cache_read_input_token_cost_above_100k_tokens": 5e-08
},
"bedrock_mantle/anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5.5e-07,
"output_cost_per_token_above_100k_tokens": 2.75e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.375e-07,
"cache_creation_input_token_cost_above_1hr": 2.2e-07,
@ -75128,12 +75137,17 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html"
},
"bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 6e-07,
"output_cost_per_token_above_100k_tokens": 3e-06,
"cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
"cache_read_input_token_cost_above_100k_tokens": 6e-08,
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 1.5e-07,
@ -75147,8 +75161,8 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
@ -75170,6 +75184,11 @@
"source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html"
},
"anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5e-07,
"output_cost_per_token_above_100k_tokens": 2.5e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_1hr": 2e-07,
@ -75205,12 +75224,17 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"apac.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5.5e-07,
"output_cost_per_token_above_100k_tokens": 2.75e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
"bedrock_converse_supports_strict_tools": false,
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
@ -75236,8 +75260,8 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"cache_creation_input_token_cost_above_1hr": 2.2e-07,
"cache_creation_input_token_cost": 1.375e-07,
@ -75247,6 +75271,11 @@
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"au.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5.5e-07,
"output_cost_per_token_above_100k_tokens": 2.75e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.375e-07,
"cache_creation_input_token_cost_above_1hr": 2.2e-07,
@ -75282,12 +75311,17 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://aws.amazon.com/bedrock/pricing/"
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"azure_ai/claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5e-07,
"output_cost_per_token_above_100k_tokens": 2.5e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5e-08,
"supports_mid_conversation_system": true,
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_1hr": 2e-07,
@ -75318,12 +75352,17 @@
"supports_vision": true,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01"
"source": "https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide"
},
"bedrock/us-gov-east-1/anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 6e-07,
"output_cost_per_token_above_100k_tokens": 3e-06,
"cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
"cache_read_input_token_cost_above_100k_tokens": 6e-08,
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 1.5e-07,
@ -75337,9 +75376,10 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
@ -75359,6 +75399,11 @@
"supports_xhigh_reasoning_effort": true
},
"bedrock/us-gov-west-1/anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 6e-07,
"output_cost_per_token_above_100k_tokens": 3e-06,
"cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
"cache_read_input_token_cost_above_100k_tokens": 6e-08,
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 1.5e-07,
@ -75372,9 +75417,10 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
@ -75394,6 +75440,11 @@
"supports_xhigh_reasoning_effort": true
},
"eu.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5.5e-07,
"output_cost_per_token_above_100k_tokens": 2.75e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.375e-07,
"cache_creation_input_token_cost_above_1hr": 2.2e-07,
@ -75429,12 +75480,17 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://aws.amazon.com/bedrock/pricing/"
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"global.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5e-07,
"output_cost_per_token_above_100k_tokens": 2.5e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_1hr": 2e-07,
@ -75470,12 +75526,17 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://aws.amazon.com/bedrock/pricing/"
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"jp.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5.5e-07,
"output_cost_per_token_above_100k_tokens": 2.75e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.375e-07,
"cache_creation_input_token_cost_above_1hr": 2.2e-07,
@ -75511,10 +75572,10 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://aws.amazon.com/bedrock/pricing/"
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"perplexity/anthropic/claude-haiku-5-5": {
"litellm_provider": "perplexity",
@ -75528,6 +75589,11 @@
"source": "https://docs.perplexity.ai/docs/agent-api/models"
},
"us-gov.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 6e-07,
"output_cost_per_token_above_100k_tokens": 3e-06,
"cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
"cache_read_input_token_cost_above_100k_tokens": 6e-08,
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 1.5e-07,
@ -75541,10 +75607,10 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://aws.amazon.com/bedrock/pricing/",
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
@ -75564,6 +75630,11 @@
"supports_xhigh_reasoning_effort": true
},
"us.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5.5e-07,
"output_cost_per_token_above_100k_tokens": 2.75e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.375e-07,
"cache_creation_input_token_cost_above_1hr": 2.2e-07,
@ -75599,12 +75670,17 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://aws.amazon.com/bedrock/pricing/"
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"vertex_ai/claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5e-07,
"output_cost_per_token_above_100k_tokens": 2.5e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5e-08,
"regional_endpoint_uplift_multiplier": 1.1,
"supports_mid_conversation_system": true,
"cache_creation_input_token_cost": 1.25e-07,
@ -75639,12 +75715,17 @@
"supports_vision": true,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"vertex_ai/claude-haiku-5-5@default": {
"input_cost_per_token_above_100k_tokens": 5e-07,
"output_cost_per_token_above_100k_tokens": 2.5e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5e-08,
"regional_endpoint_uplift_multiplier": 1.1,
"supports_mid_conversation_system": true,
"cache_creation_input_token_cost": 1.25e-07,
@ -75679,9 +75760,43 @@
"supports_vision": true,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"openrouter/anthropic/claude-haiku-5.5": {
"input_cost_per_token": 1e-07,
"output_cost_per_token": 5e-07,
"cache_read_input_token_cost": 1e-08,
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_1hr": 2e-07,
"input_cost_per_token_above_100k_tokens": 5e-07,
"output_cost_per_token_above_100k_tokens": 2.5e-06,
"cache_read_input_token_cost_above_100k_tokens": 5e-08,
"cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://openrouter.ai/api/v1/models",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_web_search": true,
"supports_adaptive_thinking": true,
"prompt_cache_min_tokens": 512,
"supports_sampling_params": false
}
}

20
litellm/types/utils.py
View file

@ -246,6 +246,8 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
input_cost_per_token_ultrafast: ReadOnly[float | None] # OpenAI ultrafast service tier pricing
cache_creation_input_token_cost: float | None
cache_creation_input_token_cost_above_200k_tokens: float | None
cache_creation_input_token_cost_above_100k_tokens: ReadOnly[float | None]
cache_creation_input_token_cost_above_1hr_above_100k_tokens: ReadOnly[float | None]
cache_creation_input_token_cost_above_272k_tokens: float | None
cache_creation_input_token_cost_above_272k_tokens_priority: float | None
cache_creation_input_token_cost_above_272k_tokens_flex: float | None
@ -259,11 +261,14 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
cache_read_input_token_cost_priority: float | None # OpenAI priority service tier pricing
cache_read_input_token_cost_ultrafast: ReadOnly[float | None] # OpenAI ultrafast service tier pricing
cache_read_input_token_cost_above_200k_tokens: float | None
cache_read_input_token_cost_above_100k_tokens: ReadOnly[float | None]
cache_read_input_token_cost_above_200k_tokens_priority: float | None
cache_read_input_token_cost_above_272k_tokens: float | None
cache_read_input_token_cost_above_272k_tokens_priority: float | None
cache_read_input_token_cost_above_272k_tokens_flex: float | None
cache_read_input_token_cost_above_512k_tokens: float | None
cache_read_input_token_cost_above_100k_tokens_batches: ReadOnly[float | None]
cache_creation_input_token_cost_above_100k_tokens_batches: ReadOnly[float | None]
# Smallest prefix this model will actually cache, whatever caching mechanism its provider uses.
# Absent means the provider-agnostic default applies; see MINIMUM_PROMPT_CACHE_TOKEN_COUNT.
prompt_cache_min_tokens: int | None
@ -272,6 +277,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
input_cost_per_audio_token: float | None
input_cost_per_token_above_128k_tokens: float | None # only for vertex ai models
input_cost_per_token_above_200k_tokens: float | None # only for vertex ai gemini-2.5-pro models
input_cost_per_token_above_100k_tokens: ReadOnly[float | None]
input_cost_per_token_above_200k_tokens_priority: float | None
input_cost_per_token_above_272k_tokens: float | None # GPT-5.4/5.4-pro: prompts >272K priced at 2x input
input_cost_per_token_above_272k_tokens_priority: float | None
@ -289,7 +295,9 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
input_cost_per_second: float | None # for OpenAI Speech models
input_cost_per_token_batches: float | None
input_cost_per_video_token_batches: ReadOnly[float | None]
input_cost_per_token_above_100k_tokens_batches: ReadOnly[float | None]
output_cost_per_token_batches: float | None
output_cost_per_token_above_100k_tokens_batches: ReadOnly[float | None]
output_cost_per_token: Required[float | None]
output_cost_per_token_flex: float | None # OpenAI flex service tier pricing
output_cost_per_token_priority: float | None # OpenAI priority service tier pricing
@ -307,6 +315,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
output_cost_per_audio_token: float | None
output_cost_per_token_above_128k_tokens: float | None # only for vertex ai models
output_cost_per_token_above_200k_tokens: float | None # only for vertex ai gemini-2.5-pro models
output_cost_per_token_above_100k_tokens: ReadOnly[float | None]
output_cost_per_token_above_200k_tokens_priority: float | None
output_cost_per_token_above_272k_tokens: float | None # GPT-5.4/5.4-pro: prompts >272K priced at 1.5x output
output_cost_per_token_above_272k_tokens_priority: float | None
@ -3619,6 +3628,8 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
input_cost_per_token_priority: float | None = None
input_cost_per_token_ultrafast: float | None = None
cache_creation_input_token_cost_above_1hr: float | None = None
cache_creation_input_token_cost_above_100k_tokens: float | None = None
cache_creation_input_token_cost_above_1hr_above_100k_tokens: float | None = None
cache_creation_input_token_cost_above_200k_tokens: float | None = None
cache_creation_input_token_cost_above_272k_tokens: float | None = None
cache_creation_input_token_cost_above_272k_tokens_priority: float | None = None
@ -3630,19 +3641,24 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
cache_read_input_token_cost_flex: float | None = None
cache_read_input_token_cost_priority: float | None = None
cache_read_input_token_cost_ultrafast: float | None = None
cache_read_input_token_cost_above_100k_tokens: float | None = None
cache_read_input_token_cost_above_200k_tokens: float | None = None
cache_read_input_token_cost_above_200k_tokens_priority: float | None = None
cache_read_input_token_cost_above_272k_tokens_priority: float | None = None
cache_read_input_token_cost_above_272k_tokens_flex: float | None = None
cache_read_input_token_cost_above_100k_tokens_batches: float | None = None
cache_creation_input_token_cost_above_100k_tokens_batches: float | None = None
cache_read_input_audio_token_cost: float | None = None
input_cost_per_character_above_128k_tokens: float | None = None
input_cost_per_audio_token: float | None = None
input_cost_per_token_cache_hit: float | None = None
input_cost_per_token_above_128k_tokens: float | None = None
input_cost_per_token_above_100k_tokens: float | None = None
input_cost_per_token_above_200k_tokens: float | None = None
input_cost_per_token_above_200k_tokens_priority: float | None = None
input_cost_per_token_above_272k_tokens_priority: float | None = None
input_cost_per_token_above_272k_tokens_flex: float | None = None
input_cost_per_token_above_100k_tokens_batches: float | None = None
input_cost_per_query: float | None = None
input_cost_per_image: float | None = None
input_cost_per_image_above_128k_tokens: float | None = None
@ -3662,10 +3678,12 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
output_cost_per_token_ultrafast: float | None = None
output_cost_per_audio_token: float | None = None
output_cost_per_token_above_128k_tokens: float | None = None
output_cost_per_token_above_100k_tokens: float | None = None
output_cost_per_token_above_200k_tokens: float | None = None
output_cost_per_token_above_200k_tokens_priority: float | None = None
output_cost_per_token_above_272k_tokens_priority: float | None = None
output_cost_per_token_above_272k_tokens_flex: float | None = None
output_cost_per_token_above_100k_tokens_batches: float | None = None
output_cost_per_character_above_128k_tokens: float | None = None
output_cost_per_image: float | None = None
output_cost_per_image_token: float | None = None
@ -3728,7 +3746,7 @@ def shared_backend_model_info(model_info: dict[str, Any]) -> dict[str, Any]:
return {k: v for k, v in model_info.items() if k in SHARED_BACKEND_MODEL_INFO_FIELDS}
ABOVE_THRESHOLD_COST_KEY_PATTERN: Final = re.compile(r"_above_\d+k?_tokens$")
ABOVE_THRESHOLD_COST_KEY_PATTERN: Final = re.compile(r"_above_\d+k?_tokens(?:_batches)?$")
_PRICING_FIELD_EXEMPTIONS: Final[frozenset[str]] = frozenset({"output_vector_size"})

197
model_prices_and_context_window.json
View file

@ -75042,6 +75042,10 @@
"supports_web_search": false
},
"claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens_batches": 2.5e-07,
"output_cost_per_token_above_100k_tokens_batches": 1.25e-06,
"cache_creation_input_token_cost_above_100k_tokens_batches": 3.125e-07,
"cache_read_input_token_cost_above_100k_tokens_batches": 2.5e-08,
"supports_anthropic_compaction": true,
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_1hr": 2e-07,
@ -75081,8 +75085,8 @@
"us": 1.1
},
"supports_output_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://platform.claude.com/docs/en/models/haiku-5-5/overview",
"supports_web_search": true,
@ -75093,6 +75097,11 @@
"cache_read_input_token_cost_above_100k_tokens": 5e-08
},
"bedrock_mantle/anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5.5e-07,
"output_cost_per_token_above_100k_tokens": 2.75e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.375e-07,
"cache_creation_input_token_cost_above_1hr": 2.2e-07,
@ -75128,12 +75137,17 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html"
},
"bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 6e-07,
"output_cost_per_token_above_100k_tokens": 3e-06,
"cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
"cache_read_input_token_cost_above_100k_tokens": 6e-08,
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 1.5e-07,
@ -75147,8 +75161,8 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
@ -75170,6 +75184,11 @@
"source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.html"
},
"anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5e-07,
"output_cost_per_token_above_100k_tokens": 2.5e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_1hr": 2e-07,
@ -75205,12 +75224,17 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"apac.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5.5e-07,
"output_cost_per_token_above_100k_tokens": 2.75e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
"bedrock_converse_supports_strict_tools": false,
"litellm_provider": "bedrock_converse",
"supports_tool_search": true,
@ -75236,8 +75260,8 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"cache_creation_input_token_cost_above_1hr": 2.2e-07,
"cache_creation_input_token_cost": 1.375e-07,
@ -75247,6 +75271,11 @@
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"au.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5.5e-07,
"output_cost_per_token_above_100k_tokens": 2.75e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.375e-07,
"cache_creation_input_token_cost_above_1hr": 2.2e-07,
@ -75282,12 +75311,17 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://aws.amazon.com/bedrock/pricing/"
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"azure_ai/claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5e-07,
"output_cost_per_token_above_100k_tokens": 2.5e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5e-08,
"supports_mid_conversation_system": true,
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_1hr": 2e-07,
@ -75318,12 +75352,17 @@
"supports_vision": true,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://management.azure.com/subscriptions/c873328e-b572-4770-8dff-aaeb6f1f0e79/providers/Microsoft.CognitiveServices/locations/eastus2/models?api-version=2024-10-01"
"source": "https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide"
},
"bedrock/us-gov-east-1/anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 6e-07,
"output_cost_per_token_above_100k_tokens": 3e-06,
"cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
"cache_read_input_token_cost_above_100k_tokens": 6e-08,
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 1.5e-07,
@ -75337,9 +75376,10 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
@ -75359,6 +75399,11 @@
"supports_xhigh_reasoning_effort": true
},
"bedrock/us-gov-west-1/anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 6e-07,
"output_cost_per_token_above_100k_tokens": 3e-06,
"cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
"cache_read_input_token_cost_above_100k_tokens": 6e-08,
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 1.5e-07,
@ -75372,9 +75417,10 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
@ -75394,6 +75440,11 @@
"supports_xhigh_reasoning_effort": true
},
"eu.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5.5e-07,
"output_cost_per_token_above_100k_tokens": 2.75e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.375e-07,
"cache_creation_input_token_cost_above_1hr": 2.2e-07,
@ -75429,12 +75480,17 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://aws.amazon.com/bedrock/pricing/"
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"global.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5e-07,
"output_cost_per_token_above_100k_tokens": 2.5e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_1hr": 2e-07,
@ -75470,12 +75526,17 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://aws.amazon.com/bedrock/pricing/"
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"jp.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5.5e-07,
"output_cost_per_token_above_100k_tokens": 2.75e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.375e-07,
"cache_creation_input_token_cost_above_1hr": 2.2e-07,
@ -75511,10 +75572,10 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://aws.amazon.com/bedrock/pricing/"
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"perplexity/anthropic/claude-haiku-5-5": {
"litellm_provider": "perplexity",
@ -75528,6 +75589,11 @@
"source": "https://docs.perplexity.ai/docs/agent-api/models"
},
"us-gov.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 6e-07,
"output_cost_per_token_above_100k_tokens": 3e-06,
"cache_creation_input_token_cost_above_100k_tokens": 7.5e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.2e-06,
"cache_read_input_token_cost_above_100k_tokens": 6e-08,
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 1.5e-07,
@ -75541,10 +75607,10 @@
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 6e-07,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://aws.amazon.com/bedrock/pricing/",
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json",
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
@ -75564,6 +75630,11 @@
"supports_xhigh_reasoning_effort": true
},
"us.anthropic.claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5.5e-07,
"output_cost_per_token_above_100k_tokens": 2.75e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.875e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1.1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5.5e-08,
"bedrock_converse_supports_strict_tools": false,
"cache_creation_input_token_cost": 1.375e-07,
"cache_creation_input_token_cost_above_1hr": 2.2e-07,
@ -75599,12 +75670,17 @@
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://aws.amazon.com/bedrock/pricing/"
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json"
},
"vertex_ai/claude-haiku-5-5": {
"input_cost_per_token_above_100k_tokens": 5e-07,
"output_cost_per_token_above_100k_tokens": 2.5e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5e-08,
"regional_endpoint_uplift_multiplier": 1.1,
"supports_mid_conversation_system": true,
"cache_creation_input_token_cost": 1.25e-07,
@ -75639,12 +75715,17 @@
"supports_vision": true,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"vertex_ai/claude-haiku-5-5@default": {
"input_cost_per_token_above_100k_tokens": 5e-07,
"output_cost_per_token_above_100k_tokens": 2.5e-06,
"cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
"cache_read_input_token_cost_above_100k_tokens": 5e-08,
"regional_endpoint_uplift_multiplier": 1.1,
"supports_mid_conversation_system": true,
"cache_creation_input_token_cost": 1.25e-07,
@ -75679,9 +75760,43 @@
"supports_vision": true,
"supports_xhigh_reasoning_effort": true,
"supports_max_reasoning_effort": true,
"supports_forced_tool_use": false,
"thinking_always_on": true,
"supports_forced_tool_use": true,
"thinking_always_on": false,
"prompt_cache_min_tokens": 512,
"source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing"
},
"openrouter/anthropic/claude-haiku-5.5": {
"input_cost_per_token": 1e-07,
"output_cost_per_token": 5e-07,
"cache_read_input_token_cost": 1e-08,
"cache_creation_input_token_cost": 1.25e-07,
"cache_creation_input_token_cost_above_1hr": 2e-07,
"input_cost_per_token_above_100k_tokens": 5e-07,
"output_cost_per_token_above_100k_tokens": 2.5e-06,
"cache_read_input_token_cost_above_100k_tokens": 5e-08,
"cache_creation_input_token_cost_above_100k_tokens": 6.25e-07,
"cache_creation_input_token_cost_above_1hr_above_100k_tokens": 1e-06,
"litellm_provider": "openrouter",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"source": "https://openrouter.ai/api/v1/models",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_vision": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_web_search": true,
"supports_adaptive_thinking": true,
"prompt_cache_min_tokens": 512,
"supports_sampling_params": false
}
}

20
model_prices_and_context_window.schema.json
View file

@ -92,6 +92,11 @@
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"cache_creation_input_token_cost_above_100k_tokens_batches": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"cache_creation_input_token_cost_above_128k_tokens": {
"type": "number",
"minimum": 0,
@ -165,6 +170,11 @@
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"cache_read_input_token_cost_above_100k_tokens_batches": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"cache_read_input_token_cost_above_128k_tokens": {
"type": "number",
"minimum": 0,
@ -337,6 +347,11 @@
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"input_cost_per_token_above_100k_tokens_batches": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"input_cost_per_token_above_128k_tokens": {
"type": "number",
"minimum": 0,
@ -653,6 +668,11 @@
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"output_cost_per_token_above_100k_tokens_batches": {
"type": "number",
"minimum": 0,
"description": "Rate applied once the prompt exceeds the token threshold in the field name."
},
"output_cost_per_token_above_128k_tokens": {
"type": "number",
"minimum": 0,

80
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -3634,3 +3634,83 @@ def test_get_token_base_cost_resolves_missing_cache_write_rates_like_the_tiered_
assert creation == pytest.approx(expected_creation)
assert creation_1h == pytest.approx(expected_creation_1h)
# Per-token rates read 2026-10-07 from https://platform.claude.com/docs/en/about-claude/pricing (direct and
# azure_ai, which Microsoft bills at Anthropic's rates per
# https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/claude-models-billing) and from the
# AmazonBedrockFoundationModels price list at
# https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json (Bedrock)
@pytest.mark.parametrize(
("model", "custom_llm_provider", "prompt_tokens", "input_rate", "cache_read_rate", "output_rate"),
[
("claude-haiku-5-5", "anthropic", 100_000, 1e-07, 1e-08, 5e-07),
("claude-haiku-5-5", "anthropic", 100_001, 5e-07, 5e-08, 2.5e-06),
("azure_ai/claude-haiku-5-5", "azure_ai", 100_000, 1e-07, 1e-08, 5e-07),
("azure_ai/claude-haiku-5-5", "azure_ai", 100_001, 5e-07, 5e-08, 2.5e-06),
("global.anthropic.claude-haiku-5-5", "bedrock", 100_000, 1e-07, 1e-08, 5e-07),
("global.anthropic.claude-haiku-5-5", "bedrock", 100_001, 5e-07, 5e-08, 2.5e-06),
("us.anthropic.claude-haiku-5-5", "bedrock", 100_000, 1.1e-07, 1.1e-08, 5.5e-07),
("us.anthropic.claude-haiku-5-5", "bedrock", 100_001, 5.5e-07, 5.5e-08, 2.75e-06),
("us-gov.anthropic.claude-haiku-5-5", "bedrock", 100_000, 1.2e-07, 1.2e-08, 6e-07),
("us-gov.anthropic.claude-haiku-5-5", "bedrock", 100_001, 6e-07, 6e-08, 3e-06),
("bedrock_mantle/anthropic.claude-haiku-5-5", "bedrock_mantle", 100_001, 5.5e-07, 5.5e-08, 2.75e-06),
("bedrock/us-gov-west-1/anthropic.claude-haiku-5-5", "bedrock", 100_001, 6e-07, 6e-08, 3e-06),
("vertex_ai/claude-haiku-5-5", "vertex_ai", 100_000, 1e-07, 1e-08, 5e-07),
("vertex_ai/claude-haiku-5-5", "vertex_ai", 100_001, 5e-07, 5e-08, 2.5e-06),
],
)
def test_generic_cost_per_token_claude_haiku_5_5_prompt_length_tiers(
_local_model_cost_map: None,
model: str,
custom_llm_provider: str,
prompt_tokens: int,
input_rate: float,
cache_read_rate: float,
output_rate: float,
) -> None:
"""Claude Haiku 5.5 bills every token at 5x the base rates once the prompt is over 100,000 tokens."""
cached_tokens: Final = 10_000
completion_tokens: Final = 1_000
usage: Final = Usage(
prompt_tokens=prompt_tokens,
completion_tokens=completion_tokens,
total_tokens=prompt_tokens + completion_tokens,
prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=cached_tokens),
)
prompt_cost, completion_cost = generic_cost_per_token(
model=model,
usage=usage,
custom_llm_provider=custom_llm_provider,
)
assert prompt_cost == pytest.approx((prompt_tokens - cached_tokens) * input_rate + cached_tokens * cache_read_rate)
assert completion_cost == pytest.approx(completion_tokens * output_rate)
def test_vertex_regional_endpoint_uplift_scales_claude_haiku_5_5_over_100k_rates(
_local_model_cost_map: None,
) -> None:
"""Vertex regional endpoints bill 1.1x the global rate on all token types
(https://cloud.google.com/vertex-ai/generative-ai/pricing, 2026-10-07: regional
over-100K input is $0.55/MTok), so the uplift scales the over-100k rates too."""
cached_tokens: Final = 10_000
prompt_tokens: Final = 100_001
completion_tokens: Final = 1_000
usage: Final = Usage(
prompt_tokens=prompt_tokens,
completion_tokens=completion_tokens,
total_tokens=prompt_tokens + completion_tokens,
prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=cached_tokens),
)
prompt_cost, completion_cost = generic_cost_per_token(
model="vertex_ai/claude-haiku-5-5",
usage=usage,
custom_llm_provider="vertex_ai",
vertex_location="us-east5",
)
assert prompt_cost == pytest.approx((prompt_tokens - cached_tokens) * 5.5e-07 + cached_tokens * 5.5e-08)
assert completion_cost == pytest.approx(completion_tokens * 2.75e-06)

128
tests/test_litellm/test_claude_haiku_5_5_config.py Normal file
View file

@ -0,0 +1,128 @@
"""
Validate Claude Haiku 5.5 model configuration entries.
Haiku 5.5 ships with adaptive thinking on by default, but unlike Sonnet 5.5 /
Opus 5.5 thinking can still be turned off (``thinking: disabled`` at high
effort or below) and it accepts a forced ``tool_choice`` (``any`` or a named
tool). Its cost-map rows therefore carry ``thinking_always_on: false`` and
``supports_forced_tool_use: true``.
"""
import json
import os
from collections.abc import Iterator
from typing import Final, cast
import pytest
import litellm
from litellm.litellm_core_utils.get_model_cost_map import GetModelCostMap
from litellm.llms.anthropic.common_utils import AnthropicModelInfo
REPO_ROOT: Final = os.path.join(os.path.dirname(__file__), "../..")
GET_WEATHER_TOOL: Final = {
"type": "function",
"function": {
"name": "get_weather",
"description": "Get the weather",
"parameters": {
"type": "object",
"properties": {"city": {"type": "string"}},
},
},
}
@pytest.fixture(autouse=True)
def local_model_cost_map(monkeypatch: pytest.MonkeyPatch) -> Iterator[None]:
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
monkeypatch.setattr(litellm, "disable_aiohttp_transport", True)
litellm.get_model_info.cache_clear()
yield
litellm.get_model_info.cache_clear()
def _load_root_cost_map() -> dict[str, dict[str, object]]:
json_path: Final = os.path.join(REPO_ROOT, "model_prices_and_context_window.json")
with open(json_path) as f:
return cast(dict[str, dict[str, object]], json.load(f))
HAIKU_5_5_VARIANTS: Final = (
"claude-haiku-5-5",
"anthropic.claude-haiku-5-5",
"apac.anthropic.claude-haiku-5-5",
"au.anthropic.claude-haiku-5-5",
"eu.anthropic.claude-haiku-5-5",
"global.anthropic.claude-haiku-5-5",
"jp.anthropic.claude-haiku-5-5",
"us.anthropic.claude-haiku-5-5",
"us-gov.anthropic.claude-haiku-5-5",
"bedrock/us-gov-east-1/anthropic.claude-haiku-5-5",
"bedrock/us-gov-west-1/anthropic.claude-haiku-5-5",
"bedrock_mantle/anthropic.claude-haiku-5-5",
"bedrock_mantle/us-gov-west-1/anthropic.claude-haiku-5-5",
"vertex_ai/claude-haiku-5-5",
"vertex_ai/claude-haiku-5-5@default",
)
@pytest.mark.parametrize("model_name", HAIKU_5_5_VARIANTS)
def test_haiku_5_5_rows_allow_disabling_thinking_and_forced_tools(
model_name: str,
) -> None:
root: Final = _load_root_cost_map()
backup: Final = GetModelCostMap.load_local_model_cost_map()
assert model_name in root
row: Final = root[model_name]
# https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5 (2026-10-07):
# thinking can be disabled, forced tool_choice accepted
assert row["thinking_always_on"] is False
assert row["supports_forced_tool_use"] is True
assert backup[model_name] == row
@pytest.mark.parametrize(
("model", "provider"),
[
("claude-haiku-5-5", "anthropic"),
("anthropic/claude-haiku-5-5", "anthropic"),
("vertex_ai/claude-haiku-5-5", "vertex_ai"),
],
)
def test_haiku_5_5_runtime_profile(local_model_cost_map: None, model: str, provider: str) -> None:
assert AnthropicModelInfo._is_adaptive_thinking_model(model, provider) is True
assert AnthropicModelInfo._is_always_on_thinking_model(model, provider) is False
assert AnthropicModelInfo.forced_tool_use_unsupported(model.removeprefix("anthropic/")) is False
def test_haiku_5_5_anthropic_tool_choice_required_maps_to_any(
local_model_cost_map: None,
) -> None:
optional_params: Final = litellm.AnthropicConfig().map_openai_params(
non_default_params={
"tools": [dict(GET_WEATHER_TOOL)],
"tool_choice": "required",
},
optional_params={},
model="claude-haiku-5-5",
drop_params=False,
)
assert optional_params["tool_choice"] == {"type": "any"}
def test_haiku_5_5_bedrock_tool_choice_required_maps_to_any(
local_model_cost_map: None,
) -> None:
optional_params: Final = litellm.AmazonConverseConfig().map_openai_params(
non_default_params={
"tools": [dict(GET_WEATHER_TOOL)],
"tool_choice": "required",
},
optional_params={},
model="us.anthropic.claude-haiku-5-5",
drop_params=False,
)
assert optional_params["tool_choice"] == {"any": {}}

4
tests/test_litellm/test_utils.py
View file

@ -724,6 +724,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
"cache_creation_input_token_cost": {"type": "number"},
"cache_creation_input_token_cost_above_1hr": {"type": "number"},
"cache_creation_input_token_cost_above_100k_tokens": {"type": "number"},
"cache_creation_input_token_cost_above_100k_tokens_batches": {"type": "number"},
"cache_creation_input_token_cost_above_128k_tokens": {"type": "number"},
"cache_creation_input_token_cost_above_200k_tokens": {"type": "number"},
"cache_creation_input_token_cost_above_256k_tokens": {"type": "number"},
@ -736,6 +737,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
"cache_read_input_token_cost": {"type": "number"},
"cache_read_input_token_cost_batches": {"type": "number"},
"cache_read_input_token_cost_above_100k_tokens": {"type": "number"},
"cache_read_input_token_cost_above_100k_tokens_batches": {"type": "number"},
"cache_read_input_token_cost_above_128k_tokens": {"type": "number"},
"cache_read_input_token_cost_above_200k_tokens": {"type": "number"},
"cache_read_input_token_cost_above_256k_tokens": {"type": "number"},
@ -758,6 +760,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
"input_cost_per_image_above_128k_tokens": {"type": "number"},
"input_cost_per_video_token": {"type": "number"},
"input_cost_per_token_above_100k_tokens": {"type": "number"},
"input_cost_per_token_above_100k_tokens_batches": {"type": "number"},
"input_cost_per_token_above_200k_tokens": {"type": "number"},
"input_cost_per_token_above_256k_tokens": {"type": "number"},
"input_cost_per_token_above_272k_tokens": {"type": "number"},
@ -846,6 +849,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
"output_cost_per_second_4k": {"type": "number"},
"output_cost_per_token": {"type": "number"},
"output_cost_per_token_above_100k_tokens": {"type": "number"},
"output_cost_per_token_above_100k_tokens_batches": {"type": "number"},
"output_cost_per_token_above_128k_tokens": {"type": "number"},
"output_cost_per_token_above_200k_tokens": {"type": "number"},
"output_cost_per_token_above_256k_tokens": {"type": "number"},

36
ui/litellm-dashboard/src/lib/http/schema.d.ts generated vendored
View file

@ -30870,8 +30870,14 @@ export interface components {
cache_creation_input_audio_token_cost?: number | null;
/** Cache Creation Input Token Cost */
cache_creation_input_token_cost?: number | null;
/** Cache Creation Input Token Cost Above 100K Tokens */
cache_creation_input_token_cost_above_100k_tokens?: number | null;
/** Cache Creation Input Token Cost Above 100K Tokens Batches */
cache_creation_input_token_cost_above_100k_tokens_batches?: number | null;
/** Cache Creation Input Token Cost Above 1Hr */
cache_creation_input_token_cost_above_1hr?: number | null;
/** Cache Creation Input Token Cost Above 1Hr Above 100K Tokens */
cache_creation_input_token_cost_above_1hr_above_100k_tokens?: number | null;
/** Cache Creation Input Token Cost Above 200K Tokens */
cache_creation_input_token_cost_above_200k_tokens?: number | null;
/** Cache Creation Input Token Cost Above 272K Tokens */
@ -30890,6 +30896,10 @@ export interface components {
cache_read_input_audio_token_cost?: number | null;
/** Cache Read Input Token Cost */
cache_read_input_token_cost?: number | null;
/** Cache Read Input Token Cost Above 100K Tokens */
cache_read_input_token_cost_above_100k_tokens?: number | null;
/** Cache Read Input Token Cost Above 100K Tokens Batches */
cache_read_input_token_cost_above_100k_tokens_batches?: number | null;
/** Cache Read Input Token Cost Above 200K Tokens */
cache_read_input_token_cost_above_200k_tokens?: number | null;
/** Cache Read Input Token Cost Above 200K Tokens Priority */
@ -30962,6 +30972,10 @@ export interface components {
input_cost_per_second?: number | null;
/** Input Cost Per Token */
input_cost_per_token?: number | null;
/** Input Cost Per Token Above 100K Tokens */
input_cost_per_token_above_100k_tokens?: number | null;
/** Input Cost Per Token Above 100K Tokens Batches */
input_cost_per_token_above_100k_tokens_batches?: number | null;
/** Input Cost Per Token Above 128K Tokens */
input_cost_per_token_above_128k_tokens?: number | null;
/** Input Cost Per Token Above 200K Tokens */
@ -31073,6 +31087,10 @@ export interface components {
output_cost_per_second_720p?: number | null;
/** Output Cost Per Token */
output_cost_per_token?: number | null;
/** Output Cost Per Token Above 100K Tokens */
output_cost_per_token_above_100k_tokens?: number | null;
/** Output Cost Per Token Above 100K Tokens Batches */
output_cost_per_token_above_100k_tokens_batches?: number | null;
/** Output Cost Per Token Above 128K Tokens */
output_cost_per_token_above_128k_tokens?: number | null;
/** Output Cost Per Token Above 200K Tokens */
@ -41585,8 +41603,14 @@ export interface components {
cache_creation_input_audio_token_cost?: number | null;
/** Cache Creation Input Token Cost */
cache_creation_input_token_cost?: number | null;
/** Cache Creation Input Token Cost Above 100K Tokens */
cache_creation_input_token_cost_above_100k_tokens?: number | null;
/** Cache Creation Input Token Cost Above 100K Tokens Batches */
cache_creation_input_token_cost_above_100k_tokens_batches?: number | null;
/** Cache Creation Input Token Cost Above 1Hr */
cache_creation_input_token_cost_above_1hr?: number | null;
/** Cache Creation Input Token Cost Above 1Hr Above 100K Tokens */
cache_creation_input_token_cost_above_1hr_above_100k_tokens?: number | null;
/** Cache Creation Input Token Cost Above 200K Tokens */
cache_creation_input_token_cost_above_200k_tokens?: number | null;
/** Cache Creation Input Token Cost Above 272K Tokens */
@ -41605,6 +41629,10 @@ export interface components {
cache_read_input_audio_token_cost?: number | null;
/** Cache Read Input Token Cost */
cache_read_input_token_cost?: number | null;
/** Cache Read Input Token Cost Above 100K Tokens */
cache_read_input_token_cost_above_100k_tokens?: number | null;
/** Cache Read Input Token Cost Above 100K Tokens Batches */
cache_read_input_token_cost_above_100k_tokens_batches?: number | null;
/** Cache Read Input Token Cost Above 200K Tokens */
cache_read_input_token_cost_above_200k_tokens?: number | null;
/** Cache Read Input Token Cost Above 200K Tokens Priority */
@ -41677,6 +41705,10 @@ export interface components {
input_cost_per_second?: number | null;
/** Input Cost Per Token */
input_cost_per_token?: number | null;
/** Input Cost Per Token Above 100K Tokens */
input_cost_per_token_above_100k_tokens?: number | null;
/** Input Cost Per Token Above 100K Tokens Batches */
input_cost_per_token_above_100k_tokens_batches?: number | null;
/** Input Cost Per Token Above 128K Tokens */
input_cost_per_token_above_128k_tokens?: number | null;
/** Input Cost Per Token Above 200K Tokens */
@ -41788,6 +41820,10 @@ export interface components {
output_cost_per_second_720p?: number | null;
/** Output Cost Per Token */
output_cost_per_token?: number | null;
/** Output Cost Per Token Above 100K Tokens */
output_cost_per_token_above_100k_tokens?: number | null;
/** Output Cost Per Token Above 100K Tokens Batches */
output_cost_per_token_above_100k_tokens_batches?: number | null;
/** Output Cost Per Token Above 128K Tokens */
output_cost_per_token_above_128k_tokens?: number | null;
/** Output Cost Per Token Above 200K Tokens */