diff --git a/litellm-rust/crates/model-catalog/src/model_info.rs b/litellm-rust/crates/model-catalog/src/model_info.rs index 361cb56e9b1..9e9a4220e50 100644 --- a/litellm-rust/crates/model-catalog/src/model_info.rs +++ b/litellm-rust/crates/model-catalog/src/model_info.rs @@ -42,6 +42,9 @@ pub struct ModelInfo { pub cache_creation_input_token_cost_above_200k_tokens: Option, /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(skip_serializing_if = "Option::is_none")] + pub cache_creation_input_token_cost_above_200k_tokens_batches: Option, + /// Rate applied once the prompt exceeds the token threshold in the field name. + #[serde(skip_serializing_if = "Option::is_none")] pub cache_creation_input_token_cost_above_256k_tokens: Option, /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(skip_serializing_if = "Option::is_none")] @@ -78,6 +81,9 @@ pub struct ModelInfo { /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(skip_serializing_if = "Option::is_none")] pub cache_read_input_token_cost_above_200k_tokens: Option, + /// Rate applied once the prompt exceeds the token threshold in the field name. + #[serde(skip_serializing_if = "Option::is_none")] + pub cache_read_input_token_cost_above_200k_tokens_batches: Option, /// Priority service-tier rate for the same-named base field. #[serde(skip_serializing_if = "Option::is_none")] pub cache_read_input_token_cost_above_200k_tokens_priority: Option, @@ -113,6 +119,10 @@ pub struct ModelInfo { pub code_interpreter_cost_per_session: Option, #[serde(skip_serializing_if = "Option::is_none")] pub comment: Option, + #[serde(skip_serializing_if = "Option::is_none")] + pub computer_use_input_cost_per_1k_tokens: Option, + #[serde(skip_serializing_if = "Option::is_none")] + pub computer_use_output_cost_per_1k_tokens: Option, /// Reasoning effort the provider applies when the request omits reasoning_effort. Gates whether a non-default temperature or the top_p/logprobs sampling params are accepted, which hold only when the effort resolves to 'none'. #[serde(skip_serializing_if = "Option::is_none")] pub default_reasoning_effort: Option, @@ -120,6 +130,10 @@ pub struct ModelInfo { #[serde(skip_serializing_if = "Option::is_none")] pub deprecation_date: Option, #[serde(skip_serializing_if = "Option::is_none")] + pub file_search_cost_per_1k_calls: Option, + #[serde(skip_serializing_if = "Option::is_none")] + pub file_search_cost_per_gb_per_day: Option, + #[serde(skip_serializing_if = "Option::is_none")] pub gemini_audio_only_live: Option, #[serde(skip_serializing_if = "Option::is_none")] pub gemini_native_audio: Option, @@ -174,6 +188,9 @@ pub struct ModelInfo { /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(skip_serializing_if = "Option::is_none")] pub input_cost_per_token_above_200k_tokens: Option, + /// Rate applied once the prompt exceeds the token threshold in the field name. + #[serde(skip_serializing_if = "Option::is_none")] + pub input_cost_per_token_above_200k_tokens_batches: Option, /// Priority service-tier rate for the same-named base field. #[serde(skip_serializing_if = "Option::is_none")] pub input_cost_per_token_above_200k_tokens_priority: Option, @@ -265,6 +282,26 @@ pub struct ModelInfo { pub output_cost_per_image_1536: Option, #[serde(skip_serializing_if = "Option::is_none")] pub output_cost_per_image_512: Option, + #[serde( + rename = "output_cost_per_image_0.5K", + skip_serializing_if = "Option::is_none" + )] + pub output_cost_per_image_0_5k: Option, + #[serde( + rename = "output_cost_per_image_1K", + skip_serializing_if = "Option::is_none" + )] + pub output_cost_per_image_1k: Option, + #[serde( + rename = "output_cost_per_image_2K", + skip_serializing_if = "Option::is_none" + )] + pub output_cost_per_image_2k: Option, + #[serde( + rename = "output_cost_per_image_4K", + skip_serializing_if = "Option::is_none" + )] + pub output_cost_per_image_4k: Option, #[serde(skip_serializing_if = "Option::is_none")] pub output_cost_per_image_token: Option, #[serde(skip_serializing_if = "Option::is_none")] @@ -297,6 +334,9 @@ pub struct ModelInfo { /// Rate applied once the prompt exceeds the token threshold in the field name. #[serde(skip_serializing_if = "Option::is_none")] pub output_cost_per_token_above_200k_tokens: Option, + /// Rate applied once the prompt exceeds the token threshold in the field name. + #[serde(skip_serializing_if = "Option::is_none")] + pub output_cost_per_token_above_200k_tokens_batches: Option, /// Priority service-tier rate for the same-named base field. #[serde(skip_serializing_if = "Option::is_none")] pub output_cost_per_token_above_200k_tokens_priority: Option, @@ -357,6 +397,8 @@ pub struct ModelInfo { /// Provider default requests-per-minute limit. #[serde(skip_serializing_if = "Option::is_none")] pub rpm: Option, + #[serde(skip_serializing_if = "Option::is_none")] + pub rules: Option>, /// USD cost per web search query, keyed by search context size. #[serde(skip_serializing_if = "Option::is_none")] pub search_context_cost_per_query: Option, @@ -475,6 +517,8 @@ pub struct ModelInfo { #[serde(skip_serializing_if = "Option::is_none")] pub uses_embed_content: Option, #[serde(skip_serializing_if = "Option::is_none")] + pub vector_store_cost_per_gb_per_day: Option, + #[serde(skip_serializing_if = "Option::is_none")] pub vertex_ai_audio_api: Option, /// Whether web search is billed per query or per prompt. #[serde(skip_serializing_if = "Option::is_none")] diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py index 28d72702f3e..e955c0157c6 100644 --- a/litellm/litellm_core_utils/litellm_logging.py +++ b/litellm/litellm_core_utils/litellm_logging.py @@ -384,6 +384,7 @@ _DEPLOYMENT_PRICING_KEYS: Final = ( "cache_read_input_token_cost_above_200k_tokens_batches", "cache_read_input_token_cost_above_272k_tokens_batches", "cache_creation_input_token_cost_batches", + "cache_creation_input_token_cost_above_200k_tokens_batches", "cache_creation_input_token_cost_above_272k_tokens_batches", "ocr_cost_per_page", "ocr_cost_per_page_batches", diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 56129fef135..ec31039fee0 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -1279,8 +1279,11 @@ "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "anthropic.claude-mythos-preview": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "cache_creation_input_token_cost": 3.4375e-05, + "cache_creation_input_token_cost_above_1hr": 5.5e-05, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 2.75e-05, + "output_cost_per_token": 0.0001375, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -1289,10 +1292,11 @@ "thinking_always_on": true, "supports_function_calling": true, "supports_vision": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_output_config": true + "supports_output_config": true, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -7773,27 +7777,27 @@ "output_cost_per_token_above_272k_tokens_batches": 0.000135 }, "azure/gpt-5.6": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_creation_input_token_cost_priority": 1.25e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, - "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_priority": 4e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -8579,27 +8583,27 @@ "supports_web_search": true }, "azure/us/gpt-5.6": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05, - "cache_creation_input_token_cost_priority": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06, - "cache_read_input_token_cost_priority": 1.1e-06, - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2.2e-05, - "input_cost_per_token_priority": 1.1e-05, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_above_272k_tokens_priority": 9.9e-05, - "output_cost_per_token_priority": 6.6e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -8985,27 +8989,27 @@ "supports_web_search": true }, "azure/eu/gpt-5.6": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05, - "cache_creation_input_token_cost_priority": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06, - "cache_read_input_token_cost_priority": 1.1e-06, - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2.2e-05, - "input_cost_per_token_priority": 1.1e-05, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_above_272k_tokens_priority": 9.9e-05, - "output_cost_per_token_priority": 6.6e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14640,14 +14644,18 @@ "claude-haiku-4-5-20251001": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_structured_output": true, @@ -14663,14 +14671,18 @@ "claude-haiku-4-5": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_structured_output": true, @@ -14693,13 +14705,21 @@ "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_creation_input_token_cost_above_200k_tokens_batches": 3.75e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, + "input_cost_per_token_above_200k_tokens_batches": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_200k_tokens_batches": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14727,13 +14747,21 @@ "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_creation_input_token_cost_above_200k_tokens_batches": 3.75e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, + "input_cost_per_token_above_200k_tokens_batches": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_200k_tokens_batches": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14757,14 +14785,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14797,14 +14829,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14865,14 +14901,18 @@ "claude-opus-4-5-20251101": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14895,14 +14935,18 @@ "claude-opus-4-5": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14927,14 +14971,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14966,14 +15014,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15004,14 +15056,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15044,14 +15100,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15083,14 +15143,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15123,14 +15187,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15164,14 +15232,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15207,14 +15279,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15250,14 +15326,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15756,6 +15836,16 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "c4ai-aya-expanse-32b": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "source": "https://docs.cohere.com/docs/models" + }, "command-a-plus-05-2026": { "input_cost_per_token": 0.0, "litellm_provider": "cohere_chat", @@ -22145,11 +22235,11 @@ } }, "bing_grounding/search": { - "input_cost_per_query": 0.035, + "input_cost_per_query": 0.014, "litellm_provider": "bing_grounding", "mode": "search", "metadata": { - "notes": "Grounding with Bing Search (G1 SKU): $35 per 1,000 transactions. Tokens for the Foundry model deployment that runs the grounded search are billed separately on that deployment." + "notes": "Grounding with Bing Search (G1 SKU): $14 per 1,000 transactions. Tokens for the Foundry model deployment that runs the grounded search are billed separately on that deployment." } }, "tinyfish/search": { @@ -28036,6 +28126,7 @@ "tpm": 10000000 }, "gemini/gemini-3-pro-image-preview": { + "deprecation_date": "2026-06-25", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -28083,6 +28174,7 @@ "supports_reasoning": false }, "gemini/gemini-3.1-flash-image-preview": { + "deprecation_date": "2026-06-25", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", @@ -28130,6 +28222,7 @@ "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2026-05-25", "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, @@ -30551,7 +30644,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.6-luna": { "litellm_provider": "chatgpt", @@ -30567,7 +30664,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-5.6-sol": { "litellm_provider": "chatgpt", @@ -30583,7 +30684,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-5.6-terra": { "litellm_provider": "chatgpt", @@ -30599,7 +30704,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-5.4": { "litellm_provider": "chatgpt", @@ -30614,7 +30723,12 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.4-pro": { "litellm_provider": "chatgpt", @@ -30628,7 +30742,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.3-codex": { "litellm_provider": "chatgpt", @@ -30642,7 +30760,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false, + "supports_minimal_reasoning_effort": true }, "chatgpt/gpt-5.3-codex-spark": { "litellm_provider": "chatgpt", @@ -30686,7 +30808,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true }, "chatgpt/gpt-5.2-codex": { "litellm_provider": "chatgpt", @@ -30700,7 +30823,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true }, "chatgpt/gpt-5.2": { "litellm_provider": "chatgpt", @@ -30715,7 +30839,12 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.1-codex-max": { "litellm_provider": "chatgpt", @@ -30729,7 +30858,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true }, "chatgpt/gpt-5.1-codex-mini": { "litellm_provider": "chatgpt", @@ -30743,7 +30873,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true }, "gigachat/GigaChat-2": { "input_cost_per_token": 0.0, @@ -39214,6 +39345,17 @@ "supports_function_calling": true, "supports_reasoning": true }, + "nebius/deepseek-ai/DeepSeek-V4.1-Flash": { + "input_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://tokenfactory.nebius.com/endpoints?modals=endpoint-details&model-id=deepseek-ai/DeepSeek-V4.1-Flash", + "supports_vision": true + }, "nebius/MiniMaxAI/MiniMax-M2.5": { "max_tokens": 196608, "max_input_tokens": 196608, @@ -56230,7 +56372,7 @@ "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "realtime", @@ -56417,7 +56559,7 @@ "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "realtime", @@ -59653,14 +59795,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "prompt_cache_min_tokens": 512, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -59693,14 +59839,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -63000,6 +63150,22 @@ "image" ] }, + "xai/grok-imagine-image-pro": { + "input_cost_per_image": 0.05, + "litellm_provider": "xai", + "mode": "image_generation", + "source": "https://docs.x.ai/docs/models", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, "xai/grok-imagine-image-2.0": { "input_cost_per_image": 0.06, "litellm_provider": "xai", @@ -64006,6 +64172,55 @@ "supports_response_schema": true, "supports_vision": true }, + "azure_ai/deepseek-r1": { + "input_cost_per_token": 1.35e-06, + "output_cost_per_token": 5.4e-06, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/deepseek-v3-0324": { + "input_cost_per_token": 1.14e-06, + "output_cost_per_token": 4.56e-06, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/deepseek-v3.1": { + "input_cost_per_token": 1.23e-06, + "output_cost_per_token": 4.94e-06, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/grok-3": { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/grok-3-mini": { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.27e-06, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/grok-4-fast-non-reasoning": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/grok-4-fast-reasoning": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock", @@ -64834,6 +65049,131 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "bedrock_mantle/deepseek.v3.1": { + "input_cost_per_token": 5.8e-07, + "output_cost_per_token": 1.68e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html" + }, + "bedrock_mantle/moonshotai.kimi-k2-thinking": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" + }, + "bedrock_mantle/qwen.qwen3-235b-a22b-2507": { + "input_cost_per_token": 2.2e-07, + "output_cost_per_token": 8.8e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html" + }, + "bedrock_mantle/qwen.qwen3-32b": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 32000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-32b.html" + }, + "bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-30b-a3b-instruct.html" + }, + "bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct": { + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 1.8e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html" + }, + "bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct": { + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html" + }, + "bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct": { + "input_cost_per_token": 5.3e-07, + "output_cost_per_token": 2.66e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-vl-235b-a22b.html" + }, "azure/us-gov/gpt-5.1": { "cache_read_input_token_cost": 1.71875e-07, "default_reasoning_effort": "none", @@ -76578,6 +76918,23 @@ "supports_vision": true, "supports_web_search": false }, + "openrouter/perceptron/perceptron-mk1.5": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 36864, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, "vertex_ai/gemini-2.0-flash": { "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 1e-06, diff --git a/litellm/types/utils.py b/litellm/types/utils.py index cd336c9b989..2e518af4da4 100644 --- a/litellm/types/utils.py +++ b/litellm/types/utils.py @@ -302,6 +302,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): cache_read_input_token_cost_above_200k_tokens_batches: ReadOnly[float | None] cache_read_input_token_cost_above_272k_tokens_batches: ReadOnly[float | None] cache_creation_input_token_cost_batches: ReadOnly[float | None] + cache_creation_input_token_cost_above_200k_tokens_batches: ReadOnly[float | None] cache_creation_input_token_cost_above_272k_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. @@ -3735,6 +3736,7 @@ class CustomPricingLiteLLMParams(MirroredPricingParams): cache_read_input_token_cost_above_200k_tokens_batches: float | None = None cache_read_input_token_cost_above_272k_tokens_batches: float | None = None cache_creation_input_token_cost_batches: float | None = None + cache_creation_input_token_cost_above_200k_tokens_batches: float | None = None cache_creation_input_token_cost_above_272k_tokens_batches: float | None = None cache_read_input_audio_token_cost: float | None = None cache_read_input_image_token_cost: float | None = None diff --git a/litellm/utils.py b/litellm/utils.py index be4388802f9..42da2e2a7b7 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -6167,6 +6167,9 @@ def _get_model_info_helper( "cache_read_input_token_cost_above_272k_tokens_batches" ), cache_creation_input_token_cost_batches=_model_info.get("cache_creation_input_token_cost_batches"), + cache_creation_input_token_cost_above_200k_tokens_batches=_model_info.get( + "cache_creation_input_token_cost_above_200k_tokens_batches" + ), cache_creation_input_token_cost_above_272k_tokens_batches=_model_info.get( "cache_creation_input_token_cost_above_272k_tokens_batches" ), diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 56129fef135..ec31039fee0 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1279,8 +1279,11 @@ "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "anthropic.claude-mythos-preview": { - "input_cost_per_token": 0, - "output_cost_per_token": 0, + "cache_creation_input_token_cost": 3.4375e-05, + "cache_creation_input_token_cost_above_1hr": 5.5e-05, + "cache_read_input_token_cost": 2.75e-06, + "input_cost_per_token": 2.75e-05, + "output_cost_per_token": 0.0001375, "litellm_provider": "bedrock", "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -1289,10 +1292,11 @@ "thinking_always_on": true, "supports_function_calling": true, "supports_vision": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_output_config": true + "supports_output_config": true, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json" }, "global.anthropic.claude-opus-4-7": { "bedrock_converse_supports_strict_tools": false, @@ -7773,27 +7777,27 @@ "output_cost_per_token_above_272k_tokens_batches": 0.000135 }, "azure/gpt-5.6": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.25e-05, - "cache_creation_input_token_cost_priority": 1.25e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.5e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, - "input_cost_per_token": 5e-06, - "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-05, - "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, - "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_priority": 4e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -8579,27 +8583,27 @@ "supports_web_search": true }, "azure/us/gpt-5.6": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05, - "cache_creation_input_token_cost_priority": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06, - "cache_read_input_token_cost_priority": 1.1e-06, - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2.2e-05, - "input_cost_per_token_priority": 1.1e-05, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_above_272k_tokens_priority": 9.9e-05, - "output_cost_per_token_priority": 6.6e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -8985,27 +8989,27 @@ "supports_web_search": true }, "azure/eu/gpt-5.6": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens_priority": 2.75e-05, - "cache_creation_input_token_cost_priority": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens_priority": 2.2e-06, - "cache_read_input_token_cost_priority": 1.1e-06, - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "input_cost_per_token_above_272k_tokens_priority": 2.2e-05, - "input_cost_per_token_priority": 1.1e-05, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2.2e-05, + "cache_creation_input_token_cost_priority": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.76e-06, + "cache_read_input_token_cost_priority": 8.8e-07, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.76e-05, + "input_cost_per_token_priority": 8.8e-06, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, - "output_cost_per_token_above_272k_tokens_priority": 9.9e-05, - "output_cost_per_token_priority": 6.6e-05, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, + "output_cost_per_token_above_272k_tokens_priority": 6.6e-05, + "output_cost_per_token_priority": 4.4e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14640,14 +14644,18 @@ "claude-haiku-4-5-20251001": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_structured_output": true, @@ -14663,14 +14671,18 @@ "claude-haiku-4-5": { "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_native_structured_output": true, @@ -14693,13 +14705,21 @@ "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_creation_input_token_cost_above_200k_tokens_batches": 3.75e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, + "input_cost_per_token_above_200k_tokens_batches": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_200k_tokens_batches": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14727,13 +14747,21 @@ "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_creation_input_token_cost_above_200k_tokens_batches": 3.75e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_read_input_token_cost_above_200k_tokens_batches": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, + "input_cost_per_token_above_200k_tokens_batches": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_200k_tokens_batches": 1.125e-05, + "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14757,14 +14785,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_1hr": 4e-06, + "cache_creation_input_token_cost_batches": 1.25e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14797,14 +14829,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.875e-06, "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14865,14 +14901,18 @@ "claude-opus-4-5-20251101": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14895,14 +14935,18 @@ "claude-opus-4-5": { "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14927,14 +14971,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -14966,14 +15014,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15004,14 +15056,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15044,14 +15100,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15083,14 +15143,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15123,14 +15187,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15164,14 +15232,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15207,14 +15279,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15250,14 +15326,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -15756,6 +15836,16 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "c4ai-aya-expanse-32b": { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 4000, + "max_tokens": 4000, + "mode": "chat", + "source": "https://docs.cohere.com/docs/models" + }, "command-a-plus-05-2026": { "input_cost_per_token": 0.0, "litellm_provider": "cohere_chat", @@ -22145,11 +22235,11 @@ } }, "bing_grounding/search": { - "input_cost_per_query": 0.035, + "input_cost_per_query": 0.014, "litellm_provider": "bing_grounding", "mode": "search", "metadata": { - "notes": "Grounding with Bing Search (G1 SKU): $35 per 1,000 transactions. Tokens for the Foundry model deployment that runs the grounded search are billed separately on that deployment." + "notes": "Grounding with Bing Search (G1 SKU): $14 per 1,000 transactions. Tokens for the Foundry model deployment that runs the grounded search are billed separately on that deployment." } }, "tinyfish/search": { @@ -28036,6 +28126,7 @@ "tpm": 10000000 }, "gemini/gemini-3-pro-image-preview": { + "deprecation_date": "2026-06-25", "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, @@ -28083,6 +28174,7 @@ "supports_reasoning": false }, "gemini/gemini-3.1-flash-image-preview": { + "deprecation_date": "2026-06-25", "input_cost_per_token": 5e-07, "input_cost_per_token_batches": 2.5e-07, "litellm_provider": "gemini", @@ -28130,6 +28222,7 @@ "cache_read_input_token_cost_batches": 1.25e-08, "cache_read_input_token_cost_flex": 1.25e-08, "cache_read_input_token_cost_priority": 4.5e-08, + "deprecation_date": "2026-05-25", "input_cost_per_audio_token": 5e-07, "input_cost_per_token": 2.5e-07, "input_cost_per_token_batches": 1.25e-07, @@ -30551,7 +30644,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.6-luna": { "litellm_provider": "chatgpt", @@ -30567,7 +30664,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-5.6-sol": { "litellm_provider": "chatgpt", @@ -30583,7 +30684,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-5.6-terra": { "litellm_provider": "chatgpt", @@ -30599,7 +30704,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_minimal_reasoning_effort": false, + "supports_none_reasoning_effort": true, + "supports_reasoning": true, + "supports_xhigh_reasoning_effort": true }, "chatgpt/gpt-5.4": { "litellm_provider": "chatgpt", @@ -30614,7 +30723,12 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.4-pro": { "litellm_provider": "chatgpt", @@ -30628,7 +30742,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.3-codex": { "litellm_provider": "chatgpt", @@ -30642,7 +30760,11 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false, + "supports_minimal_reasoning_effort": true }, "chatgpt/gpt-5.3-codex-spark": { "litellm_provider": "chatgpt", @@ -30686,7 +30808,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true }, "chatgpt/gpt-5.2-codex": { "litellm_provider": "chatgpt", @@ -30700,7 +30823,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true }, "chatgpt/gpt-5.2": { "litellm_provider": "chatgpt", @@ -30715,7 +30839,12 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true, + "supports_none_reasoning_effort": true, + "default_reasoning_effort": "none", + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false }, "chatgpt/gpt-5.1-codex-max": { "litellm_provider": "chatgpt", @@ -30729,7 +30858,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true }, "chatgpt/gpt-5.1-codex-mini": { "litellm_provider": "chatgpt", @@ -30743,7 +30873,8 @@ "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "supports_reasoning": true }, "gigachat/GigaChat-2": { "input_cost_per_token": 0.0, @@ -39214,6 +39345,17 @@ "supports_function_calling": true, "supports_reasoning": true }, + "nebius/deepseek-ai/DeepSeek-V4.1-Flash": { + "input_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_output_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://tokenfactory.nebius.com/endpoints?modals=endpoint-details&model-id=deepseek-ai/DeepSeek-V4.1-Flash", + "supports_vision": true + }, "nebius/MiniMaxAI/MiniMax-M2.5": { "max_tokens": 196608, "max_input_tokens": 196608, @@ -56230,7 +56372,7 @@ "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "realtime", @@ -56417,7 +56559,7 @@ "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "realtime", @@ -59653,14 +59795,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "prompt_cache_min_tokens": 512, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -59693,14 +59839,18 @@ "supports_anthropic_compaction": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 5e-06, "litellm_provider": "anthropic", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -63000,6 +63150,22 @@ "image" ] }, + "xai/grok-imagine-image-pro": { + "input_cost_per_image": 0.05, + "litellm_provider": "xai", + "mode": "image_generation", + "source": "https://docs.x.ai/docs/models", + "supported_endpoints": [ + "/v1/images/generations" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "image" + ] + }, "xai/grok-imagine-image-2.0": { "input_cost_per_image": 0.06, "litellm_provider": "xai", @@ -64006,6 +64172,55 @@ "supports_response_schema": true, "supports_vision": true }, + "azure_ai/deepseek-r1": { + "input_cost_per_token": 1.35e-06, + "output_cost_per_token": 5.4e-06, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/deepseek-v3-0324": { + "input_cost_per_token": 1.14e-06, + "output_cost_per_token": 4.56e-06, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/deepseek-v3.1": { + "input_cost_per_token": 1.23e-06, + "output_cost_per_token": 4.94e-06, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/grok-3": { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/grok-3-mini": { + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 1.27e-06, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/grok-4-fast-non-reasoning": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, + "azure_ai/grok-4-fast-reasoning": { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 5e-07, + "litellm_provider": "azure_ai", + "mode": "chat", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + }, "bedrock/us-gov-west-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, "litellm_provider": "bedrock", @@ -64834,6 +65049,131 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "bedrock_mantle/deepseek.v3.1": { + "input_cost_per_token": 5.8e-07, + "output_cost_per_token": 1.68e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-deepseek-deepseek-v3-1.html" + }, + "bedrock_mantle/moonshotai.kimi-k2-thinking": { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 2.5e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-moonshot-ai-kimi-k2-thinking.html" + }, + "bedrock_mantle/qwen.qwen3-235b-a22b-2507": { + "input_cost_per_token": 2.2e-07, + "output_cost_per_token": 8.8e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-235b-a22b-2507.html" + }, + "bedrock_mantle/qwen.qwen3-32b": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 32000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-32b.html" + }, + "bedrock_mantle/qwen.qwen3-coder-30b-a3b-instruct": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-30b-a3b-instruct.html" + }, + "bedrock_mantle/qwen.qwen3-coder-480b-a35b-instruct": { + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 1.8e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 128000, + "max_output_tokens": 16000, + "max_tokens": 16000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-coder-480b-a35b-instruct.html" + }, + "bedrock_mantle/qwen.qwen3-next-80b-a3b-instruct": { + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 1.2e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-next-80b-a3b.html" + }, + "bedrock_mantle/qwen.qwen3-vl-235b-a22b-instruct": { + "input_cost_per_token": 5.3e-07, + "output_cost_per_token": 2.66e-06, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 256000, + "max_output_tokens": 8000, + "max_tokens": 8000, + "mode": "chat", + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-qwen-qwen3-vl-235b-a22b.html" + }, "azure/us-gov/gpt-5.1": { "cache_read_input_token_cost": 1.71875e-07, "default_reasoning_effort": "none", @@ -76578,6 +76918,23 @@ "supports_vision": true, "supports_web_search": false }, + "openrouter/perceptron/perceptron-mk1.5": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 36864, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true + }, "vertex_ai/gemini-2.0-flash": { "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 1e-06, diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json index fa1828c780a..c4048cac905 100644 --- a/model_prices_and_context_window.schema.json +++ b/model_prices_and_context_window.schema.json @@ -103,6 +103,11 @@ "minimum": 0, "description": "Rate applied once the prompt exceeds the token threshold in the field name." }, + "cache_creation_input_token_cost_above_200k_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_256k_tokens": { "type": "number", "minimum": 0, diff --git a/tests/local_testing/test_get_model_info.py b/tests/local_testing/test_get_model_info.py index dbe1fc3b69b..79f6739a423 100644 --- a/tests/local_testing/test_get_model_info.py +++ b/tests/local_testing/test_get_model_info.py @@ -320,6 +320,33 @@ def test_get_model_info_bedrock_cross_region_capability_parity(): assert checked > 0, "no cross-region bedrock profiles found - the filter is inert" + +def test_get_model_info_bedrock_priced_cross_region_profile_has_priced_base(): + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + + prefixes = ("us.", "eu.", "apac.", "us-gov.", "au.", "global.") + checked = 0 + + for k, v in litellm.model_cost.items(): + if not str(v.get("litellm_provider", "")).startswith("bedrock"): + continue + base_model_key = next( + (k[len(p) :] for p in prefixes if k.startswith(p)), + None, + ) + if base_model_key is None or base_model_key not in litellm.model_cost: + continue + checked += 1 + base = litellm.model_cost[base_model_key] + for cost_key in ("input_cost_per_token", "output_cost_per_token"): + if (v.get(cost_key) or 0) > 0: + assert ( + base.get(cost_key) or 0 + ) > 0, f"{k} charges {cost_key} but its base {base_model_key} is free" + + assert checked > 0, "no cross-region bedrock profiles found - the filter is inert" + def test_get_model_info_huggingface_models(monkeypatch): from litellm import Router from litellm.types.router import ModelGroupInfo diff --git a/tests/search_tests/test_bing_grounding_search.py b/tests/search_tests/test_bing_grounding_search.py index f532158e462..6ea79076370 100644 --- a/tests/search_tests/test_bing_grounding_search.py +++ b/tests/search_tests/test_bing_grounding_search.py @@ -196,4 +196,5 @@ class TestBingGroundingSearchTransformation: ): response = litellm.search(query="pricing check", search_provider="bing_grounding") - assert response._hidden_params["response_cost"] == pytest.approx(0.035) + # Grounding with Bing Search (G1 SKU): $14 per 1,000 transactions, https://www.microsoft.com/en-us/bing/apis, checked 2026-09-24 + assert response._hidden_params["response_cost"] == pytest.approx(0.014) diff --git a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 781a3a7c4ed..0afd989272e 100644 --- a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -3789,3 +3789,15 @@ def test_azure_gpt_6_foundry_price_sheet(_local_model_cost_map, model_base): assert azure_ai_info[field] == base assert azure_us_info[field] == pytest.approx(1.1 * base) assert azure_eu_info[field] == pytest.approx(1.2 * base) + + +@pytest.mark.parametrize("region_prefix", ["azure/", "azure/us/", "azure/eu/"]) +def test_azure_gpt_5_6_alias_matches_sol_pricing(_local_model_cost_map, region_prefix): + """The bare gpt-5.6 alias routes to GPT-5.6 Sol, so every Azure region must bill the + alias exactly like the Sol entry (including the Sept 2026 $4/$20 promo).""" + alias = litellm.model_cost[f"{region_prefix}gpt-5.6"] + sol = litellm.model_cost[f"{region_prefix}gpt-5.6-sol"] + shared_cost_fields = [f for f in alias if "cost" in f and f in sol and not isinstance(alias[f], dict)] + assert shared_cost_fields + for field in shared_cost_fields: + assert alias[field] == sol[field], field diff --git a/tests/unit/litellm_core_utils/test_litellm_logging.py b/tests/unit/litellm_core_utils/test_litellm_logging.py index d717718cba2..cb1e281e356 100644 --- a/tests/unit/litellm_core_utils/test_litellm_logging.py +++ b/tests/unit/litellm_core_utils/test_litellm_logging.py @@ -7969,6 +7969,29 @@ def test_deployment_pricing_model_info_honors_a_tier_only_batch_override_over_th assert {key: info[key] for key in carried_keys} == {key: _PUBLISHED_BATCH_RATES[key] for key in carried_keys} +@pytest.mark.parametrize( + "override_key", + ( + "output_cost_per_token_above_200k_tokens_batches", + "cache_read_input_token_cost_above_200k_tokens_batches", + "cache_creation_input_token_cost_above_200k_tokens_batches", + ), +) +def test_deployment_pricing_model_info_honors_a_200k_tier_batch_override( + _published_batch_model: None, override_key: str +) -> None: + from litellm.litellm_core_utils.litellm_logging import deployment_pricing_model_info + + info: Final = deployment_pricing_model_info(_batch_deployment_id({override_key: 1e-3}), _PUBLISHED_BATCH_DEPLOYMENT) + carried_keys: Final = tuple( + key for key in (*_PUBLISHED_INPUT_BATCH_KEYS, *_PUBLISHED_OUTPUT_BATCH_KEYS) if key != override_key + ) + + assert info is not None + assert info[override_key] == 1e-3 + assert {key: info[key] for key in carried_keys} == {key: _PUBLISHED_BATCH_RATES[key] for key in carried_keys} + + def test_get_status_fields_ranks_guardrail_flagged_between_success_and_intervened(): """LIT-6894: a non-blocking flagged verdict must outrank success in the request-level guardrail_status but never mask an intervention.""" diff --git a/tests/unit/test_model_prices_schema.py b/tests/unit/test_model_prices_schema.py index 052278631e2..a05c345b5cd 100644 --- a/tests/unit/test_model_prices_schema.py +++ b/tests/unit/test_model_prices_schema.py @@ -266,6 +266,61 @@ def test_openai_reasoning_family_entries_carry_supports_reasoning(prices: dict): ) +_ABSENT: Final = object() + +REASONING_ANNOTATION_KEYS: Final = ( + "supports_reasoning", + "supports_minimal_reasoning_effort", + "supports_none_reasoning_effort", + "supports_xhigh_reasoning_effort", + "default_reasoning_effort", +) + + +def chatgpt_openai_twins(prices: dict) -> list[tuple[str, str]]: + """`chatgpt/` rows paired with the bare `` row served by the openai provider. + + Scoped to openai twins on purpose. `ChatGPTConfig` and `ChatGPTResponsesAPIConfig` subclass + their openai counterparts, so a chatgpt row's reasoning behaviour is whatever the openai row + describes. The azure rows are a separate registry that already diverges from openai here, and + pinning them to each other would assert something this repository does not control. + """ + pairs = [] + for name, entry in prices.items(): + if not isinstance(entry, dict) or not name.startswith("chatgpt/"): + continue + bare = name.split("/", 1)[1] + twin = prices.get(bare) + if isinstance(twin, dict) and twin.get("litellm_provider") == "openai": + pairs.append((name, bare)) + return pairs + + +def test_chatgpt_rows_carry_their_openai_twin_reasoning_annotations(prices: dict): + """A chatgpt row must not silently drop the reasoning annotations of the model it proxies. + + `litellm.utils._get_model_info_from_generalization` refuses to fall back when an exact cost-map + key exists, so an unannotated `chatgpt/` row wins over its annotated twin and + `/model/info` reports the model as non-reasoning. + """ + twins = chatgpt_openai_twins(prices) + assert twins, "no chatgpt/* row has an openai twin any more; this guard has stopped guarding" + + mismatched = [] + for name, bare in twins: + for key in REASONING_ANNOTATION_KEYS: + if prices[name].get(key, _ABSENT) != prices[bare].get(key, _ABSENT): + mismatched.append( + f"{name}.{key} is {prices[name].get(key)!r}, {bare}.{key} is {prices[bare].get(key)!r}" + ) + + assert mismatched == [], ( + "chatgpt/* entries proxy their openai twin through ChatGPTConfig, so they must carry the " + "same reasoning annotations; an exact cost-map key blocks the generalization fallback, so " + "a missing flag here is reported to callers as 'not a reasoning model':\n" + "\n".join(mismatched) + ) + + def test_chat_latest_declares_the_one_effort_openai_accepts(prices: dict): """OpenAI rejects every reasoning.effort on chat-latest except medium, and a reasoning entry with no declared levels resolves to None, which lets /model_group/info and the dashboard offer diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py index 0cdc52c9a93..5b327305e31 100644 --- a/tests/unit/test_utils.py +++ b/tests/unit/test_utils.py @@ -766,6 +766,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "cache_creation_input_token_cost_above_272k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_272k_tokens_flex": {"type": "number"}, "cache_creation_input_token_cost_above_272k_tokens_priority": {"type": "number"}, + "cache_creation_input_token_cost_above_200k_tokens_batches": {"type": "number"}, "cache_creation_input_token_cost_above_272k_tokens_batches": {"type": "number"}, "cache_creation_input_token_cost_batches": {"type": "number"}, "cache_creation_input_token_cost_flex": {"type": "number"}, diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts index 1e0aed46923..6d46af04730 100644 --- a/ui/litellm-dashboard/src/lib/http/schema.d.ts +++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts @@ -32957,6 +32957,8 @@ export interface components { cache_creation_input_token_cost_above_1hr?: 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 200K Tokens Batches */ + cache_creation_input_token_cost_above_200k_tokens_batches?: number | null; /** Cache Creation Input Token Cost Above 272K Tokens */ cache_creation_input_token_cost_above_272k_tokens?: number | null; /** Cache Creation Input Token Cost Above 272K Tokens Batches */ @@ -46750,6 +46752,8 @@ export interface components { cache_creation_input_token_cost_above_1hr?: 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 200K Tokens Batches */ + cache_creation_input_token_cost_above_200k_tokens_batches?: number | null; /** Cache Creation Input Token Cost Above 272K Tokens */ cache_creation_input_token_cost_above_272k_tokens?: number | null; /** Cache Creation Input Token Cost Above 272K Tokens Batches */