diff --git a/mise.toml b/mise.toml index b9a8a03e..35c4d071 100644 --- a/mise.toml +++ b/mise.toml @@ -1,3 +1,4 @@ [tools] +node = "20" pnpm = "10.26.2" python = "3.10" diff --git a/packages/proxy/schema/model_list.json b/packages/proxy/schema/model_list.json index 568cb6fd..749ad12e 100644 --- a/packages/proxy/schema/model_list.json +++ b/packages/proxy/schema/model_list.json @@ -9,7 +9,11 @@ "displayName": "GPT-5 mini", "reasoning": true, "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5-mini-2025-08-07": { "format": "openai", @@ -22,7 +26,11 @@ "reasoning": true, "parent": "gpt-5-mini", "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5": { "format": "openai", @@ -34,7 +42,11 @@ "displayName": "GPT-5", "reasoning": true, "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5-2025-08-07": { "format": "openai", @@ -47,7 +59,11 @@ "reasoning": true, "parent": "gpt-5", "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5-pro": { "format": "openai", @@ -58,7 +74,11 @@ "displayName": "GPT-5 Pro", "reasoning": true, "max_input_tokens": 128000, - "max_output_tokens": 272000 + "max_output_tokens": 272000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5-pro-2025-10-06": { "format": "openai", @@ -69,7 +89,11 @@ "reasoning": true, "parent": "gpt-5-pro", "max_input_tokens": 128000, - "max_output_tokens": 272000 + "max_output_tokens": 272000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5-codex": { "format": "openai", @@ -81,7 +105,11 @@ "displayName": "GPT-5 Codex", "reasoning": true, "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5-nano": { "format": "openai", @@ -93,7 +121,11 @@ "displayName": "GPT-5 nano", "reasoning": true, "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5-nano-2025-08-07": { "format": "openai", @@ -106,7 +138,11 @@ "reasoning": true, "parent": "gpt-5-nano", "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5-chat-latest": { "format": "openai", @@ -118,7 +154,11 @@ "displayName": "GPT-5 chat", "reasoning": true, "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4o": { "format": "openai", @@ -129,7 +169,11 @@ "input_cache_read_cost_per_mil_tokens": 1.25, "displayName": "GPT-4o", "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4o-2024-11-20": { "format": "openai", @@ -140,7 +184,11 @@ "input_cache_read_cost_per_mil_tokens": 1.25, "parent": "gpt-4o", "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4o-2024-08-06": { "format": "openai", @@ -151,7 +199,11 @@ "input_cache_read_cost_per_mil_tokens": 1.25, "parent": "gpt-4o", "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4o-2024-05-13": { "format": "openai", @@ -161,7 +213,11 @@ "output_cost_per_mil_tokens": 15, "parent": "gpt-4o", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4.1": { "format": "openai", @@ -172,7 +228,11 @@ "input_cache_read_cost_per_mil_tokens": 0.5, "displayName": "GPT-4.1", "max_input_tokens": 1047576, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4.1-2025-04-14": { "format": "openai", @@ -183,7 +243,11 @@ "input_cache_read_cost_per_mil_tokens": 0.5, "parent": "gpt-4.1", "max_input_tokens": 1047576, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4o-mini": { "format": "openai", @@ -194,7 +258,11 @@ "input_cache_read_cost_per_mil_tokens": 0.075, "displayName": "GPT-4o mini", "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4o-mini-2024-07-18": { "format": "openai", @@ -205,7 +273,11 @@ "input_cache_read_cost_per_mil_tokens": 0.075, "parent": "gpt-4o-mini", "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4.1-mini": { "format": "openai", @@ -216,7 +288,11 @@ "input_cache_read_cost_per_mil_tokens": 0.1, "displayName": "GPT-4.1 mini", "max_input_tokens": 1047576, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4.1-mini-2025-04-14": { "format": "openai", @@ -227,7 +303,11 @@ "input_cache_read_cost_per_mil_tokens": 0.1, "parent": "gpt-4.1-mini", "max_input_tokens": 1047576, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4.1-nano": { "format": "openai", @@ -238,7 +318,11 @@ "input_cache_read_cost_per_mil_tokens": 0.025, "displayName": "GPT-4.1 nano", "max_input_tokens": 1047576, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4.1-nano-2025-04-14": { "format": "openai", @@ -249,7 +333,11 @@ "input_cache_read_cost_per_mil_tokens": 0.025, "parent": "gpt-4.1-nano", "max_input_tokens": 1047576, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "openai", + "azure" + ] }, "o4-mini": { "format": "openai", @@ -260,7 +348,11 @@ "input_cache_read_cost_per_mil_tokens": 0.275, "reasoning": true, "max_input_tokens": 200000, - "max_output_tokens": 100000 + "max_output_tokens": 100000, + "available_providers": [ + "openai", + "azure" + ] }, "o4-mini-2025-04-16": { "format": "openai", @@ -272,7 +364,11 @@ "reasoning": true, "parent": "o4-mini", "max_input_tokens": 200000, - "max_output_tokens": 100000 + "max_output_tokens": 100000, + "available_providers": [ + "openai", + "azure" + ] }, "o3-mini": { "format": "openai", @@ -283,7 +379,11 @@ "input_cache_read_cost_per_mil_tokens": 0.55, "reasoning": true, "max_input_tokens": 200000, - "max_output_tokens": 100000 + "max_output_tokens": 100000, + "available_providers": [ + "openai", + "azure" + ] }, "o3-mini-2025-01-31": { "format": "openai", @@ -295,7 +395,11 @@ "reasoning": true, "parent": "o3-mini", "max_input_tokens": 200000, - "max_output_tokens": 100000 + "max_output_tokens": 100000, + "available_providers": [ + "openai", + "azure" + ] }, "o3-pro": { "format": "openai", @@ -306,7 +410,11 @@ "displayName": "o3 Pro", "reasoning": true, "max_input_tokens": 200000, - "max_output_tokens": 100000 + "max_output_tokens": 100000, + "available_providers": [ + "openai", + "azure" + ] }, "o3-pro-2025-06-10": { "format": "openai", @@ -317,7 +425,11 @@ "reasoning": true, "parent": "o3-pro", "max_input_tokens": 200000, - "max_output_tokens": 100000 + "max_output_tokens": 100000, + "available_providers": [ + "openai", + "azure" + ] }, "o3": { "format": "openai", @@ -328,7 +440,11 @@ "input_cache_read_cost_per_mil_tokens": 0.5, "reasoning": true, "max_input_tokens": 200000, - "max_output_tokens": 100000 + "max_output_tokens": 100000, + "available_providers": [ + "openai", + "azure" + ] }, "o3-2025-04-16": { "format": "openai", @@ -340,7 +456,11 @@ "reasoning": true, "parent": "o3", "max_input_tokens": 200000, - "max_output_tokens": 100000 + "max_output_tokens": 100000, + "available_providers": [ + "openai", + "azure" + ] }, "o1": { "format": "openai", @@ -351,7 +471,11 @@ "input_cache_read_cost_per_mil_tokens": 7.5, "reasoning": true, "max_input_tokens": 200000, - "max_output_tokens": 100000 + "max_output_tokens": 100000, + "available_providers": [ + "openai", + "azure" + ] }, "o1-2024-12-17": { "format": "openai", @@ -363,7 +487,11 @@ "reasoning": true, "parent": "o1", "max_input_tokens": 200000, - "max_output_tokens": 100000 + "max_output_tokens": 100000, + "available_providers": [ + "openai", + "azure" + ] }, "o1-mini": { "format": "openai", @@ -374,7 +502,11 @@ "input_cache_read_cost_per_mil_tokens": 0.55, "reasoning": true, "max_input_tokens": 128000, - "max_output_tokens": 65536 + "max_output_tokens": 65536, + "available_providers": [ + "openai", + "azure" + ] }, "o1-mini-2024-09-12": { "format": "openai", @@ -387,7 +519,11 @@ "deprecation_date": "2025-10-27", "parent": "o1-mini", "max_input_tokens": 128000, - "max_output_tokens": 65536 + "max_output_tokens": 65536, + "available_providers": [ + "openai", + "azure" + ] }, "o1-pro": { "format": "openai", @@ -397,7 +533,11 @@ "output_cost_per_mil_tokens": 600, "reasoning": true, "max_input_tokens": 200000, - "max_output_tokens": 100000 + "max_output_tokens": 100000, + "available_providers": [ + "openai", + "azure" + ] }, "o1-pro-2025-03-19": { "format": "openai", @@ -408,7 +548,11 @@ "reasoning": true, "parent": "o1-pro", "max_input_tokens": 200000, - "max_output_tokens": 100000 + "max_output_tokens": 100000, + "available_providers": [ + "openai", + "azure" + ] }, "chatgpt-4o-latest": { "format": "openai", @@ -418,7 +562,11 @@ "output_cost_per_mil_tokens": 15, "displayName": "ChatGPT-4o", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4-turbo": { "format": "openai", @@ -428,7 +576,11 @@ "output_cost_per_mil_tokens": 30, "displayName": "GPT-4 Turbo", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4-turbo-2024-04-09": { "format": "openai", @@ -438,7 +590,11 @@ "output_cost_per_mil_tokens": 30, "parent": "gpt-4-turbo", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4-turbo-preview": { "format": "openai", @@ -447,7 +603,11 @@ "output_cost_per_mil_tokens": 30, "parent": "gpt-4-turbo", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4": { "format": "openai", @@ -456,7 +616,11 @@ "output_cost_per_mil_tokens": 60, "displayName": "GPT-4", "max_input_tokens": 8192, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4-0125-preview": { "format": "openai", @@ -467,7 +631,11 @@ "deprecation_date": "2026-03-26", "parent": "gpt-4", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4-1106-preview": { "format": "openai", @@ -478,7 +646,11 @@ "deprecation_date": "2026-03-26", "parent": "gpt-4", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4-0613": { "format": "openai", @@ -488,7 +660,11 @@ "deprecation_date": "2025-06-06", "parent": "gpt-4", "max_input_tokens": 8192, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4-0314": { "format": "openai", @@ -497,7 +673,11 @@ "output_cost_per_mil_tokens": 60, "parent": "gpt-4", "max_input_tokens": 8192, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4.5-preview": { "format": "openai", @@ -509,7 +689,11 @@ "displayName": "GPT-4.5", "experimental": true, "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4.5-preview-2025-02-27": { "format": "openai", @@ -522,7 +706,11 @@ "deprecation_date": "2025-07-14", "parent": "gpt-4.5-preview", "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "o1-preview": { "format": "openai", @@ -535,7 +723,11 @@ "experimental": true, "parent": "o1", "max_input_tokens": 128000, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "openai", + "azure" + ] }, "o1-preview-2024-09-12": { "format": "openai", @@ -548,7 +740,11 @@ "experimental": true, "parent": "o1", "max_input_tokens": 128000, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4o-search-preview": { "format": "openai", @@ -560,7 +756,11 @@ "displayName": "GPT-4o Search Preview", "experimental": true, "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4o-search-preview-2025-03-11": { "format": "openai", @@ -572,7 +772,11 @@ "experimental": true, "parent": "gpt-4o-search-preview", "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4o-mini-search-preview": { "format": "openai", @@ -584,7 +788,11 @@ "displayName": "GPT-4o mini Search Preview", "experimental": true, "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4o-mini-search-preview-2025-03-11": { "format": "openai", @@ -596,7 +804,11 @@ "experimental": true, "parent": "gpt-4o-mini-search-preview", "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-3.5-turbo-0125": { "format": "openai", @@ -606,7 +818,11 @@ "displayName": "GPT 3.5T 0125", "deprecated": true, "max_input_tokens": 16385, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-3.5-turbo": { "format": "openai", @@ -616,7 +832,11 @@ "displayName": "GPT 3.5T", "deprecated": true, "max_input_tokens": 16385, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-35-turbo": { "format": "openai", @@ -635,7 +855,11 @@ "deprecated": true, "deprecation_date": "2026-09-28", "max_input_tokens": 16385, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-3.5-turbo-instruct": { "format": "openai", @@ -645,7 +869,11 @@ "displayName": "GPT 3.5T Instruct", "deprecated": true, "max_input_tokens": 8192, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-3.5-turbo-instruct-0914": { "format": "openai", @@ -655,7 +883,11 @@ "displayName": "GPT 3.5T Instruct 0914", "deprecated": true, "max_input_tokens": 8192, - "max_output_tokens": 4097 + "max_output_tokens": 4097, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4-32k": { "format": "openai", @@ -665,7 +897,11 @@ "displayName": "GPT 4 32k", "deprecated": true, "max_input_tokens": 32768, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4-32k-0613": { "format": "openai", @@ -675,7 +911,11 @@ "displayName": "GPT 4 32k 0613", "deprecated": true, "max_input_tokens": 32768, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4-32k-0314": { "format": "openai", @@ -685,7 +925,11 @@ "displayName": "GPT 4 32k 0314", "deprecated": true, "max_input_tokens": 32768, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4-vision-preview": { "format": "openai", @@ -697,7 +941,11 @@ "deprecated": true, "deprecation_date": "2024-12-06", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-4-1106-vision-preview": { "format": "openai", @@ -709,7 +957,11 @@ "deprecated": true, "deprecation_date": "2024-12-06", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-3.5-turbo-16k": { "format": "openai", @@ -719,7 +971,11 @@ "displayName": "GPT 3.5T 16k", "deprecated": true, "max_input_tokens": 16385, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-35-turbo-16k": { "format": "openai", @@ -737,7 +993,11 @@ "displayName": "GPT 3.5T 16k 0613", "deprecated": true, "max_input_tokens": 16385, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-3.5-turbo-0613": { "format": "openai", @@ -747,7 +1007,11 @@ "displayName": "GPT 3.5T 0613", "deprecated": true, "max_input_tokens": 4097, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-3.5-turbo-0301": { "format": "openai", @@ -757,7 +1021,11 @@ "displayName": "GPT 3.5T 0301", "deprecated": true, "max_input_tokens": 4097, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "openai", + "azure" + ] }, "text-davinci-003": { "format": "openai", @@ -779,7 +1047,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "anthropic" + ] }, "claude-sonnet-4-5": { "format": "anthropic", @@ -793,7 +1064,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "anthropic" + ] }, "claude-sonnet-4-5-20250929": { "format": "anthropic", @@ -807,7 +1081,10 @@ "reasoning_budget": true, "parent": "claude-sonnet-4-5", "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "anthropic" + ] }, "claude-sonnet-4-20250514": { "format": "anthropic", @@ -822,7 +1099,10 @@ "reasoning_budget": true, "deprecation_date": "2026-05-14", "max_input_tokens": 1000000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "anthropic" + ] }, "claude-4-sonnet-20250514": { "format": "anthropic", @@ -835,7 +1115,10 @@ "displayName": "Claude 4 Sonnet (old naming format)", "deprecated": true, "max_input_tokens": 1000000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "anthropic" + ] }, "claude-3-7-sonnet-latest": { "format": "anthropic", @@ -850,7 +1133,10 @@ "reasoning_budget": true, "deprecation_date": "2025-06-01", "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "anthropic" + ] }, "claude-3-7-sonnet-20250219": { "format": "anthropic", @@ -865,7 +1151,10 @@ "deprecation_date": "2026-02-19", "parent": "claude-3-7-sonnet-latest", "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "anthropic" + ] }, "claude-haiku-4-5": { "format": "anthropic", @@ -879,7 +1168,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "anthropic" + ] }, "claude-haiku-4-5-20251001": { "format": "anthropic", @@ -893,7 +1185,10 @@ "reasoning_budget": true, "parent": "claude-haiku-4-5-latest", "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "anthropic" + ] }, "claude-3-5-haiku-latest": { "format": "anthropic", @@ -906,7 +1201,10 @@ "displayName": "Claude 3.5 Haiku", "deprecation_date": "2025-10-01", "max_input_tokens": 200000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "anthropic" + ] }, "claude-3-5-haiku-20241022": { "format": "anthropic", @@ -919,7 +1217,10 @@ "deprecation_date": "2025-10-01", "parent": "claude-3-5-haiku-latest", "max_input_tokens": 200000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "anthropic" + ] }, "claude-3-5-sonnet-latest": { "format": "anthropic", @@ -933,7 +1234,10 @@ "deprecated": true, "deprecation_date": "2025-06-01", "max_input_tokens": 200000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "anthropic" + ] }, "claude-3-5-sonnet-20241022": { "format": "anthropic", @@ -947,7 +1251,10 @@ "deprecation_date": "2025-10-01", "parent": "claude-3-5-sonnet-latest", "max_input_tokens": 200000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "anthropic" + ] }, "claude-3-5-sonnet-20240620": { "format": "anthropic", @@ -961,7 +1268,10 @@ "deprecation_date": "2025-06-01", "parent": "claude-3-5-sonnet-latest", "max_input_tokens": 200000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "anthropic" + ] }, "claude-opus-4-6": { "format": "anthropic", @@ -975,7 +1285,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 1000000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "anthropic" + ] }, "claude-opus-4-5": { "format": "anthropic", @@ -989,7 +1302,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "anthropic" + ] }, "claude-opus-4-5-20251101": { "format": "anthropic", @@ -1003,7 +1319,10 @@ "reasoning_budget": true, "parent": "claude-opus-4-5", "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "anthropic" + ] }, "claude-opus-4-1-20250805": { "format": "anthropic", @@ -1018,7 +1337,10 @@ "reasoning_budget": true, "deprecation_date": "2026-08-05", "max_input_tokens": 200000, - "max_output_tokens": 32000 + "max_output_tokens": 32000, + "available_providers": [ + "anthropic" + ] }, "claude-opus-4-20250514": { "format": "anthropic", @@ -1033,7 +1355,10 @@ "reasoning_budget": true, "deprecation_date": "2026-05-14", "max_input_tokens": 200000, - "max_output_tokens": 32000 + "max_output_tokens": 32000, + "available_providers": [ + "anthropic" + ] }, "claude-4-opus-20250514": { "format": "anthropic", @@ -1046,7 +1371,10 @@ "displayName": "Claude 4 Opus (old naming format)", "deprecated": true, "max_input_tokens": 200000, - "max_output_tokens": 32000 + "max_output_tokens": 32000, + "available_providers": [ + "anthropic" + ] }, "claude-3-opus-latest": { "format": "anthropic", @@ -1059,7 +1387,10 @@ "displayName": "Claude 3 Opus", "deprecation_date": "2025-03-01", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "anthropic" + ] }, "claude-3-opus-20240229": { "format": "anthropic", @@ -1072,7 +1403,10 @@ "deprecation_date": "2026-05-01", "parent": "claude-3-opus-latest", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "anthropic" + ] }, "claude-3-sonnet-20240229": { "format": "anthropic", @@ -1094,7 +1428,10 @@ "input_cache_write_cost_per_mil_tokens": 0.3, "displayName": "Claude 3 Haiku", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "anthropic" + ] }, "claude-instant-1.2": { "format": "anthropic", @@ -1149,16 +1486,28 @@ "flavor": "chat", "input_cost_per_mil_tokens": 0.15, "output_cost_per_mil_tokens": 0.6, + "input_cache_read_cost_per_mil_tokens": 0.075, "displayName": "OpenAI GPT-OSS (120B)", - "reasoning": true + "reasoning": true, + "max_input_tokens": 131072, + "max_output_tokens": 32766, + "available_providers": [ + "groq" + ] }, "openai/gpt-oss-20b": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.1, - "output_cost_per_mil_tokens": 0.5, + "input_cost_per_mil_tokens": 0.075, + "output_cost_per_mil_tokens": 0.3, + "input_cache_read_cost_per_mil_tokens": 0.0375, "displayName": "OpenAI GPT-OSS (20B)", - "reasoning": true + "reasoning": true, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "available_providers": [ + "groq" + ] }, "accounts/fireworks/models/gpt-oss-120b": { "format": "openai", @@ -1179,10 +1528,15 @@ "gpt-oss-120b": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.25, - "output_cost_per_mil_tokens": 0.69, + "input_cost_per_mil_tokens": 0.35, + "output_cost_per_mil_tokens": 0.75, "displayName": "OpenAI GPT-OSS (120B)", - "reasoning": true + "reasoning": true, + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "available_providers": [ + "cerebras" + ] }, "meta/llama-2-70b-chat": { "format": "openai", @@ -1209,28 +1563,45 @@ "flavor": "chat", "input_cost_per_mil_tokens": 1, "output_cost_per_mil_tokens": 1, - "displayName": "Sonar" + "displayName": "Sonar", + "max_input_tokens": 128000, + "available_providers": [ + "perplexity" + ] }, "sonar-pro": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 3, "output_cost_per_mil_tokens": 15, - "displayName": "Sonar Pro" + "displayName": "Sonar Pro", + "max_input_tokens": 200000, + "max_output_tokens": 8000, + "available_providers": [ + "perplexity" + ] }, "sonar-reasoning": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 1, "output_cost_per_mil_tokens": 5, - "displayName": "Sonar Reasoning" + "displayName": "Sonar Reasoning", + "max_input_tokens": 128000, + "available_providers": [ + "perplexity" + ] }, "sonar-reasoning-pro": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 2, "output_cost_per_mil_tokens": 8, - "displayName": "Sonar Reasoning Pro" + "displayName": "Sonar Reasoning Pro", + "max_input_tokens": 128000, + "available_providers": [ + "perplexity" + ] }, "r1-1776": { "format": "openai", @@ -1243,26 +1614,42 @@ "format": "openai", "flavor": "chat", "multimodal": true, - "displayName": "Llama 4 Maverick Instruct (17Bx128E)" + "input_cost_per_mil_tokens": 0.27, + "output_cost_per_mil_tokens": 0.85, + "displayName": "Llama 4 Maverick Instruct (17Bx128E)", + "available_providers": [ + "together" + ] }, "meta-llama/Llama-4-Scout-17B-16E-Instruct": { "format": "openai", "flavor": "chat", - "displayName": "Llama 4 Scout Instruct (17Bx16E)" + "input_cost_per_mil_tokens": 0.18, + "output_cost_per_mil_tokens": 0.59, + "displayName": "Llama 4 Scout Instruct (17Bx16E)", + "available_providers": [ + "together" + ] }, "meta-llama/Llama-3.3-70B-Instruct-Turbo": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.88, "output_cost_per_mil_tokens": 0.88, - "displayName": "Llama 3.3 70B Instruct Turbo" + "displayName": "Llama 3.3 70B Instruct Turbo", + "available_providers": [ + "together" + ] }, "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0, "output_cost_per_mil_tokens": 0, - "displayName": "Llama 3.3 70B Instruct Turbo Free" + "displayName": "Llama 3.3 70B Instruct Turbo Free", + "available_providers": [ + "together" + ] }, "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo": { "format": "openai", @@ -1293,28 +1680,40 @@ "flavor": "chat", "input_cost_per_mil_tokens": 0.06, "output_cost_per_mil_tokens": 0.06, - "displayName": "Llama 3.2 3B Instruct Turbo" + "displayName": "Llama 3.2 3B Instruct Turbo", + "available_providers": [ + "together" + ] }, "meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 3.5, "output_cost_per_mil_tokens": 3.5, - "displayName": "Llama 3.1 405B Instruct Turbo" + "displayName": "Llama 3.1 405B Instruct Turbo", + "available_providers": [ + "together" + ] }, "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.88, "output_cost_per_mil_tokens": 0.88, - "displayName": "Llama 3.1 70B Instruct Turbo" + "displayName": "Llama 3.1 70B Instruct Turbo", + "available_providers": [ + "together" + ] }, "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.18, "output_cost_per_mil_tokens": 0.18, - "displayName": "Llama 3.1 8B Instruct Turbo" + "displayName": "Llama 3.1 8B Instruct Turbo", + "available_providers": [ + "together" + ] }, "meta-llama/Llama-3-70b-chat-hf": { "format": "openai", @@ -1386,7 +1785,10 @@ "flavor": "chat", "input_cost_per_mil_tokens": 0.8, "output_cost_per_mil_tokens": 0.8, - "displayName": "Mistral Small (24B) Instruct 25.01" + "displayName": "Mistral Small (24B) Instruct 25.01", + "available_providers": [ + "together" + ] }, "mistralai/Mistral-7B-Instruct-v0.3": { "format": "openai", @@ -1407,7 +1809,10 @@ "flavor": "chat", "input_cost_per_mil_tokens": 0.2, "output_cost_per_mil_tokens": 0.2, - "displayName": "Mistral (7B) Instruct" + "displayName": "Mistral (7B) Instruct", + "available_providers": [ + "together" + ] }, "mistralai/Mixtral-8x22B-Instruct-v0.1": { "format": "openai", @@ -1421,21 +1826,34 @@ "flavor": "chat", "input_cost_per_mil_tokens": 0.6, "output_cost_per_mil_tokens": 0.6, - "displayName": "Mixtral 8x7B Instruct v0.1" + "displayName": "Mixtral 8x7B Instruct v0.1", + "available_providers": [ + "together" + ] }, "deepseek-ai/DeepSeek-V3": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 1.25, "output_cost_per_mil_tokens": 1.25, - "displayName": "DeepSeek V3" + "displayName": "DeepSeek V3", + "max_input_tokens": 65536, + "max_output_tokens": 8192, + "available_providers": [ + "together" + ] }, "deepseek-ai/DeepSeek-R1": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 7, + "input_cost_per_mil_tokens": 3, "output_cost_per_mil_tokens": 7, - "displayName": "DeepSeek R1" + "displayName": "DeepSeek R1", + "max_input_tokens": 128000, + "max_output_tokens": 20480, + "available_providers": [ + "together" + ] }, "deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { "format": "openai", @@ -1477,14 +1895,20 @@ "flavor": "chat", "input_cost_per_mil_tokens": 1.2, "output_cost_per_mil_tokens": 1.2, - "displayName": "Qwen 2.5 72B Instruct Turbo" + "displayName": "Qwen 2.5 72B Instruct Turbo", + "available_providers": [ + "together" + ] }, "Qwen/Qwen2.5-7B-Instruct-Turbo": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.3, "output_cost_per_mil_tokens": 0.3, - "displayName": "Qwen 2.5 7B Instruct Turbo" + "displayName": "Qwen 2.5 7B Instruct Turbo", + "available_providers": [ + "together" + ] }, "Qwen/Qwen2.5-Coder-32B-Instruct": { "format": "openai", @@ -1610,8 +2034,11 @@ "input_cost_per_mil_tokens": 2, "output_cost_per_mil_tokens": 5, "displayName": "Magistral Medium Latest", - "max_input_tokens": 40960, - "max_output_tokens": 40000 + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "available_providers": [ + "mistral" + ] }, "magistral-medium-2506": { "format": "openai", @@ -1619,8 +2046,11 @@ "input_cost_per_mil_tokens": 2, "output_cost_per_mil_tokens": 5, "parent": "magistral-medium-latest", - "max_input_tokens": 40960, - "max_output_tokens": 40000 + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "available_providers": [ + "mistral" + ] }, "magistral-small-latest": { "format": "openai", @@ -1629,7 +2059,10 @@ "output_cost_per_mil_tokens": 1.5, "displayName": "Magistral Small Latest", "max_input_tokens": 40000, - "max_output_tokens": 40000 + "max_output_tokens": 40000, + "available_providers": [ + "mistral" + ] }, "magistral-small-2506": { "format": "openai", @@ -1638,7 +2071,10 @@ "output_cost_per_mil_tokens": 1.5, "parent": "magistral-small-latest", "max_input_tokens": 40000, - "max_output_tokens": 40000 + "max_output_tokens": 40000, + "available_providers": [ + "mistral" + ] }, "mistralai/mixtral-8x7b-32kseqlen": { "format": "openai", @@ -1670,8 +2106,11 @@ "input_cost_per_mil_tokens": 0.1, "output_cost_per_mil_tokens": 0.3, "displayName": "Devstral Small Latest", - "max_input_tokens": 128000, - "max_output_tokens": 128000 + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "available_providers": [ + "mistral" + ] }, "devstral-small-2507": { "format": "openai", @@ -1680,21 +2119,34 @@ "output_cost_per_mil_tokens": 0.3, "parent": "devstral-small-latest", "max_input_tokens": 128000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "mistral" + ] }, "mistral-large-latest": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 2, - "output_cost_per_mil_tokens": 6, - "displayName": "Mistral Large" + "input_cost_per_mil_tokens": 0.5, + "output_cost_per_mil_tokens": 1.5, + "displayName": "Mistral Large", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "available_providers": [ + "mistral" + ] }, "mistral-large-2411": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 2, "output_cost_per_mil_tokens": 6, - "parent": "mistral-large-latest" + "parent": "mistral-large-latest", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "available_providers": [ + "mistral" + ] }, "pixtral-large-latest": { "format": "openai", @@ -1702,7 +2154,12 @@ "multimodal": true, "input_cost_per_mil_tokens": 2, "output_cost_per_mil_tokens": 6, - "displayName": "Pixtral Large" + "displayName": "Pixtral Large", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "available_providers": [ + "mistral" + ] }, "pixtral-large-2411": { "format": "openai", @@ -1710,7 +2167,12 @@ "multimodal": true, "input_cost_per_mil_tokens": 2, "output_cost_per_mil_tokens": 6, - "parent": "pixtral-large-latest" + "parent": "pixtral-large-latest", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "available_providers": [ + "mistral" + ] }, "mistral-medium-latest": { "format": "openai", @@ -1718,7 +2180,12 @@ "multimodal": true, "input_cost_per_mil_tokens": 0.4, "output_cost_per_mil_tokens": 2, - "displayName": "Mistral Medium 3" + "displayName": "Mistral Medium 3", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "available_providers": [ + "mistral" + ] }, "mistral-medium-2505": { "format": "openai", @@ -1726,14 +2193,24 @@ "multimodal": true, "input_cost_per_mil_tokens": 0.4, "output_cost_per_mil_tokens": 2, - "parent": "mistral-medium-latest" + "parent": "mistral-medium-latest", + "max_input_tokens": 131072, + "max_output_tokens": 8191, + "available_providers": [ + "mistral" + ] }, "mistral-small-latest": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.1, - "output_cost_per_mil_tokens": 0.3, - "displayName": "Mistral Small" + "input_cost_per_mil_tokens": 0.06, + "output_cost_per_mil_tokens": 0.18, + "displayName": "Mistral Small", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "available_providers": [ + "mistral" + ] }, "mistral-small-2501": { "format": "openai", @@ -1745,9 +2222,14 @@ "codestral-latest": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.3, - "output_cost_per_mil_tokens": 0.9, - "displayName": "Codestral" + "input_cost_per_mil_tokens": 1, + "output_cost_per_mil_tokens": 3, + "displayName": "Codestral", + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "available_providers": [ + "mistral" + ] }, "codestral-2501": { "format": "openai", @@ -1804,27 +2286,47 @@ "multimodal": true, "input_cost_per_mil_tokens": 0.15, "output_cost_per_mil_tokens": 0.15, - "displayName": "Pixtral 12B" + "displayName": "Pixtral 12B", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "available_providers": [ + "mistral" + ] }, "open-mistral-nemo": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.15, - "output_cost_per_mil_tokens": 0.15, - "displayName": "Mistral NeMo" + "input_cost_per_mil_tokens": 0.3, + "output_cost_per_mil_tokens": 0.3, + "displayName": "Mistral NeMo", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "available_providers": [ + "mistral" + ] }, "open-mistral-nemo-2407": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.15, - "output_cost_per_mil_tokens": 0.15 + "input_cost_per_mil_tokens": 0.3, + "output_cost_per_mil_tokens": 0.3, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "available_providers": [ + "mistral" + ] }, "open-codestral-mamba": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.6, - "output_cost_per_mil_tokens": 0.6, - "displayName": "Codestral Mamba" + "input_cost_per_mil_tokens": 0.25, + "output_cost_per_mil_tokens": 0.25, + "displayName": "Codestral Mamba", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "available_providers": [ + "mistral" + ] }, "open-mixtral-8x22b": { "format": "openai", @@ -1832,45 +2334,75 @@ "input_cost_per_mil_tokens": 2, "output_cost_per_mil_tokens": 6, "displayName": "Mixtral 8x22B", - "deprecated": true + "deprecated": true, + "max_input_tokens": 65336, + "max_output_tokens": 8191, + "available_providers": [ + "mistral" + ] }, "mistral-tiny": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.15, - "output_cost_per_mil_tokens": 0.46, + "input_cost_per_mil_tokens": 0.25, + "output_cost_per_mil_tokens": 0.25, "displayName": "Mistral Tiny", - "deprecated": true + "deprecated": true, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "available_providers": [ + "mistral" + ] }, "mistral-small": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 1, - "output_cost_per_mil_tokens": 3, + "input_cost_per_mil_tokens": 0.1, + "output_cost_per_mil_tokens": 0.3, "displayName": "Mistral Small", - "deprecated": true + "deprecated": true, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "available_providers": [ + "mistral" + ] }, "mistral-medium": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 2.75, + "input_cost_per_mil_tokens": 2.7, "output_cost_per_mil_tokens": 8.1, "displayName": "Mistral Medium", - "deprecated": true + "deprecated": true, + "max_input_tokens": 32000, + "max_output_tokens": 8191, + "available_providers": [ + "mistral" + ] }, "llama-3.3-70b-versatile": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.59, "output_cost_per_mil_tokens": 0.79, - "displayName": "Llama 3.3 70B Versatile 128k" + "displayName": "Llama 3.3 70B Versatile 128k", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "available_providers": [ + "groq" + ] }, "llama-3.1-8b-instant": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.05, "output_cost_per_mil_tokens": 0.08, - "displayName": "Llama 3.1 8B Instant 128k" + "displayName": "Llama 3.1 8B Instant 128k", + "max_input_tokens": 128000, + "max_output_tokens": 8192, + "available_providers": [ + "groq" + ] }, "llama3-70b-8192": { "format": "openai", @@ -1904,10 +2436,15 @@ "format": "openai", "flavor": "chat", "multimodal": true, - "input_cost_per_mil_tokens": 0.5, - "output_cost_per_mil_tokens": 0.77, + "input_cost_per_mil_tokens": 0.2, + "output_cost_per_mil_tokens": 0.6, "displayName": "Llama 4 Maverick (17Bx128E)", - "experimental": true + "experimental": true, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "available_providers": [ + "groq" + ] }, "meta-llama/llama-4-scout-17b-16e-instruct": { "format": "openai", @@ -1915,7 +2452,12 @@ "input_cost_per_mil_tokens": 0.11, "output_cost_per_mil_tokens": 0.34, "displayName": "Llama 4 Scout (17Bx16E)", - "experimental": true + "experimental": true, + "max_input_tokens": 131072, + "max_output_tokens": 8192, + "available_providers": [ + "groq" + ] }, "llama-3.3-70b-specdec": { "format": "openai", @@ -1999,8 +2541,11 @@ "displayName": "Qwen3-32B", "reasoning": true, "experimental": true, - "max_input_tokens": 131072, - "max_output_tokens": 40960 + "max_input_tokens": 131000, + "max_output_tokens": 131000, + "available_providers": [ + "groq" + ] }, "moonshotai/kimi-k2-instruct-0905": { "format": "openai", @@ -2011,7 +2556,10 @@ "displayName": "Kimi K2 0905", "experimental": true, "max_input_tokens": 262144, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "groq" + ] }, "qwen-2.5-32b": { "format": "openai", @@ -2040,10 +2588,15 @@ "gemma-7b-it": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.1, - "output_cost_per_mil_tokens": 0.1, + "input_cost_per_mil_tokens": 0.05, + "output_cost_per_mil_tokens": 0.08, "displayName": "Gemma 7b IT", - "deprecated": true + "deprecated": true, + "max_input_tokens": 8192, + "max_output_tokens": 8192, + "available_providers": [ + "groq" + ] }, "llama-3.1-70b-versatile": { "format": "openai", @@ -2351,7 +2904,12 @@ "flavor": "chat", "input_cost_per_mil_tokens": 0.1, "output_cost_per_mil_tokens": 0.1, - "displayName": "Llama 3.1 8B" + "displayName": "Llama 3.1 8B", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "available_providers": [ + "cerebras" + ] }, "gemini-3.1-pro-preview": { "format": "google", @@ -2364,7 +2922,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 1048576, - "max_output_tokens": 65536 + "max_output_tokens": 65536, + "available_providers": [ + "vertex" + ] }, "gemini-3.1-pro-preview-customtools": { "format": "google", @@ -2377,20 +2938,26 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 1048576, - "max_output_tokens": 65536 + "max_output_tokens": 65536, + "available_providers": [ + "vertex" + ] }, "gemini-3.1-flash-lite-preview": { "format": "google", "flavor": "chat", "multimodal": true, "input_cost_per_mil_tokens": 0.25, - "output_cost_per_mil_tokens": 1.50, + "output_cost_per_mil_tokens": 1.5, "input_cache_read_cost_per_mil_tokens": 0.025, "displayName": "Gemini 3.1 Flash-Lite (Preview)", "reasoning": true, "reasoning_budget": true, "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65536, + "available_providers": [ + "vertex" + ] }, "gemini-3-pro-preview": { "format": "google", @@ -2404,7 +2971,10 @@ "reasoning_budget": true, "deprecation_date": "2026-03-26", "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-3-flash-preview": { "format": "google", @@ -2417,7 +2987,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "google" + ] }, "gemini-2.5-flash": { "format": "google", @@ -2430,7 +3003,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-2.5-pro": { "format": "google", @@ -2443,7 +3019,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-2.5-flash-preview-09-2025": { "format": "google", @@ -2457,7 +3036,10 @@ "experimental": false, "parent": "gemini-2.5-flash", "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-2.5-flash-preview-05-20": { "format": "google", @@ -2473,7 +3055,10 @@ "deprecation_date": "2025-11-18", "parent": "gemini-2.5-flash", "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-2.5-flash-preview-04-17": { "format": "google", @@ -2488,7 +3073,10 @@ "deprecated": true, "parent": "gemini-2.5-flash", "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-2.5-pro-preview-06-05": { "format": "google", @@ -2503,7 +3091,10 @@ "deprecated": true, "parent": "gemini-2.5-pro", "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-2.5-pro-preview-05-06": { "format": "google", @@ -2519,7 +3110,10 @@ "deprecation_date": "2025-12-02", "parent": "gemini-2.5-pro", "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-2.5-pro-preview-03-25": { "format": "google", @@ -2535,7 +3129,10 @@ "deprecation_date": "2025-12-02", "parent": "gemini-2.5-pro", "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-2.5-pro-exp-03-25": { "format": "google", @@ -2548,7 +3145,10 @@ "experimental": true, "parent": "gemini-2.5-pro", "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-2.5-flash-lite-preview-09-2025": { "format": "google", @@ -2562,7 +3162,10 @@ "experimental": true, "parent": "gemini-2.5-flash-lite", "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-2.5-flash-lite-preview-06-17": { "format": "google", @@ -2578,7 +3181,10 @@ "deprecation_date": "2025-11-18", "parent": "gemini-2.5-flash-lite", "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-2.5-flash-lite": { "format": "google", @@ -2591,7 +3197,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 1048576, - "max_output_tokens": 65535 + "max_output_tokens": 65535, + "available_providers": [ + "vertex" + ] }, "gemini-2.0-flash": { "format": "google", @@ -2603,7 +3212,10 @@ "displayName": "Gemini 2.0 Flash Latest", "deprecation_date": "2026-06-01", "max_input_tokens": 1048576, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-2.0-flash-001": { "format": "google", @@ -2615,7 +3227,10 @@ "deprecation_date": "2026-06-01", "parent": "gemini-2.0-flash", "max_input_tokens": 1048576, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-2.0-flash-lite": { "format": "google", @@ -2627,7 +3242,10 @@ "displayName": "Gemini 2.0 Flash-Lite", "deprecation_date": "2026-06-01", "max_input_tokens": 1048576, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-2.0-flash-lite-001": { "format": "google", @@ -2639,7 +3257,10 @@ "deprecation_date": "2026-06-01", "parent": "gemini-2.0-flash-lite", "max_input_tokens": 1048576, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-3-pro-image-preview": { "format": "google", @@ -2649,7 +3270,10 @@ "output_cost_per_mil_tokens": 12, "displayName": "Gemini 3 Pro Image Preview", "max_input_tokens": 65536, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "vertex" + ] }, "gemini-1.5-flash": { "format": "google", @@ -2660,7 +3284,10 @@ "displayName": "Gemini 1.5 Flash", "deprecation_date": "2025-09-29", "max_input_tokens": 1000000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-1.5-flash-latest": { "format": "google", @@ -2671,7 +3298,10 @@ "deprecation_date": "2025-09-29", "parent": "gemini-1.5-flash", "max_input_tokens": 1048576, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "google" + ] }, "gemini-1.5-flash-001": { "format": "google", @@ -2684,7 +3314,10 @@ "deprecation_date": "2025-05-24", "parent": "gemini-1.5-flash", "max_input_tokens": 1000000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-1.5-flash-002": { "format": "google", @@ -2697,7 +3330,10 @@ "deprecation_date": "2025-09-24", "parent": "gemini-1.5-flash", "max_input_tokens": 1048576, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-1.5-flash-8b": { "format": "google", @@ -2708,7 +3344,10 @@ "displayName": "Gemini 1.5 Flash-8B", "deprecation_date": "2025-09-29", "max_input_tokens": 1048576, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "google" + ] }, "gemini-1.5-flash-8b-latest": { "format": "google", @@ -2735,7 +3374,10 @@ "displayName": "Gemini 1.5 Pro", "deprecation_date": "2025-09-29", "max_input_tokens": 2097152, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-1.5-pro-latest": { "format": "google", @@ -2746,7 +3388,10 @@ "deprecation_date": "2025-09-29", "parent": "gemini-1.5-pro", "max_input_tokens": 1048576, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "google" + ] }, "gemini-1.5-pro-001": { "format": "google", @@ -2757,7 +3402,10 @@ "deprecation_date": "2025-05-24", "parent": "gemini-1.5-pro", "max_input_tokens": 1000000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-1.5-pro-002": { "format": "google", @@ -2768,7 +3416,10 @@ "deprecation_date": "2025-09-24", "parent": "gemini-1.5-pro", "max_input_tokens": 2097152, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-2.0-pro-exp-02-05": { "format": "google", @@ -2781,7 +3432,10 @@ "deprecated": true, "parent": "gemini-2.5-pro", "max_input_tokens": 2097152, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-2.0-flash-exp": { "format": "google", @@ -2793,7 +3447,10 @@ "experimental": true, "parent": "gemini-2.0-flash", "max_input_tokens": 1048576, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-2.0-flash-thinking-exp-01-21": { "format": "google", @@ -2809,7 +3466,10 @@ "deprecation_date": "2025-12-02", "parent": "gemini-2.0-flash", "max_input_tokens": 1048576, - "max_output_tokens": 65536 + "max_output_tokens": 65536, + "available_providers": [ + "vertex" + ] }, "learnlm-1.5-pro-experimental": { "format": "google", @@ -2819,7 +3479,10 @@ "output_cost_per_mil_tokens": 0, "experimental": true, "max_input_tokens": 32767, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "google" + ] }, "gemini-exp-1206": { "format": "google", @@ -2830,7 +3493,10 @@ "experimental": true, "deprecated": true, "max_input_tokens": 2097152, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "google" + ] }, "gemini-1.0-pro": { "format": "google", @@ -2840,7 +3506,10 @@ "displayName": "Gemini 1.0 Pro", "deprecated": true, "max_input_tokens": 32760, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "gemini-pro": { "format": "google", @@ -2850,7 +3519,10 @@ "displayName": "Gemini Pro", "deprecated": true, "max_input_tokens": 32760, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "vertex" + ] }, "grok-4-1-fast-reasoning-latest": { "format": "openai", @@ -2861,7 +3533,10 @@ "input_cache_read_cost_per_mil_tokens": 0.05, "displayName": "Grok 4.1 Fast", "max_input_tokens": 2000000, - "max_output_tokens": 2000000 + "max_output_tokens": 2000000, + "available_providers": [ + "xAI" + ] }, "grok-4-1-fast-reasoning": { "format": "openai", @@ -2872,7 +3547,10 @@ "input_cache_read_cost_per_mil_tokens": 0.05, "parent": "grok-4-1-fast-reasoning-latest", "max_input_tokens": 2000000, - "max_output_tokens": 2000000 + "max_output_tokens": 2000000, + "available_providers": [ + "xAI" + ] }, "grok-4-1-fast": { "format": "openai", @@ -2883,7 +3561,10 @@ "input_cache_read_cost_per_mil_tokens": 0.05, "parent": "grok-4-1-fast", "max_input_tokens": 2000000, - "max_output_tokens": 2000000 + "max_output_tokens": 2000000, + "available_providers": [ + "xAI" + ] }, "grok-4-1-fast-non-reasoning-latest": { "format": "openai", @@ -2894,7 +3575,10 @@ "input_cache_read_cost_per_mil_tokens": 0.05, "displayName": "Grok 4.1 Fast (Non-Reasoning)", "max_input_tokens": 2000000, - "max_output_tokens": 2000000 + "max_output_tokens": 2000000, + "available_providers": [ + "xAI" + ] }, "grok-4-1-fast-non-reasoning": { "format": "openai", @@ -2905,7 +3589,10 @@ "input_cache_read_cost_per_mil_tokens": 0.05, "parent": "grok-4-1-fast-non-reasoning-latest", "max_input_tokens": 2000000, - "max_output_tokens": 2000000 + "max_output_tokens": 2000000, + "available_providers": [ + "xAI" + ] }, "grok-4-fast-reasoning": { "format": "openai", @@ -2916,7 +3603,10 @@ "input_cache_read_cost_per_mil_tokens": 0.05, "parent": "grok-4-fast-reasoning-latest", "max_input_tokens": 2000000, - "max_output_tokens": 2000000 + "max_output_tokens": 2000000, + "available_providers": [ + "xAI" + ] }, "grok-4-fast-reasoning-latest": { "format": "openai", @@ -2938,7 +3628,10 @@ "input_cache_read_cost_per_mil_tokens": 0.05, "parent": "grok-4-fast-non-reasoning-latest", "max_input_tokens": 2000000, - "max_output_tokens": 2000000 + "max_output_tokens": 2000000, + "available_providers": [ + "xAI" + ] }, "grok-4-fast-non-reasoning-latest": { "format": "openai", @@ -2959,7 +3652,10 @@ "output_cost_per_mil_tokens": 15, "displayName": "Grok 4", "max_input_tokens": 256000, - "max_output_tokens": 256000 + "max_output_tokens": 256000, + "available_providers": [ + "xAI" + ] }, "grok-4-latest": { "format": "openai", @@ -2969,7 +3665,10 @@ "output_cost_per_mil_tokens": 15, "parent": "grok-4", "max_input_tokens": 256000, - "max_output_tokens": 256000 + "max_output_tokens": 256000, + "available_providers": [ + "xAI" + ] }, "grok-4-0709": { "format": "openai", @@ -2979,7 +3678,10 @@ "output_cost_per_mil_tokens": 15, "parent": "grok-4", "max_input_tokens": 256000, - "max_output_tokens": 256000 + "max_output_tokens": 256000, + "available_providers": [ + "xAI" + ] }, "grok-3": { "format": "openai", @@ -2988,7 +3690,10 @@ "output_cost_per_mil_tokens": 15, "input_cache_read_cost_per_mil_tokens": 0.75, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-3-latest": { "format": "openai", @@ -2997,7 +3702,10 @@ "output_cost_per_mil_tokens": 15, "input_cache_read_cost_per_mil_tokens": 0.75, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-3-beta": { "format": "openai", @@ -3006,7 +3714,10 @@ "output_cost_per_mil_tokens": 15, "input_cache_read_cost_per_mil_tokens": 0.75, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-3-mini": { "format": "openai", @@ -3017,7 +3728,10 @@ "reasoning": true, "deprecation_date": "2026-02-28", "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-3-mini-latest": { "format": "openai", @@ -3027,7 +3741,10 @@ "input_cache_read_cost_per_mil_tokens": 0.075, "reasoning": true, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-3-mini-beta": { "format": "openai", @@ -3038,7 +3755,10 @@ "reasoning": true, "deprecation_date": "2026-02-28", "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-3-mini-fast": { "format": "openai", @@ -3048,7 +3768,10 @@ "input_cache_read_cost_per_mil_tokens": 0.15, "reasoning": true, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-3-mini-fast-latest": { "format": "openai", @@ -3058,7 +3781,10 @@ "input_cache_read_cost_per_mil_tokens": 0.15, "reasoning": true, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-3-mini-fast-beta": { "format": "openai", @@ -3068,7 +3794,10 @@ "input_cache_read_cost_per_mil_tokens": 0.15, "reasoning": true, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-3-fast-beta": { "format": "openai", @@ -3077,7 +3806,10 @@ "output_cost_per_mil_tokens": 25, "input_cache_read_cost_per_mil_tokens": 1.25, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-3-fast-latest": { "format": "openai", @@ -3086,7 +3818,10 @@ "output_cost_per_mil_tokens": 25, "input_cache_read_cost_per_mil_tokens": 1.25, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-2-vision": { "format": "openai", @@ -3096,7 +3831,10 @@ "output_cost_per_mil_tokens": 10, "displayName": "Grok 2 Vision", "max_input_tokens": 32768, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "xAI" + ] }, "grok-2-vision-latest": { "format": "openai", @@ -3106,7 +3844,10 @@ "output_cost_per_mil_tokens": 10, "parent": "grok-2-vision", "max_input_tokens": 32768, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "xAI" + ] }, "grok-2-vision-1212": { "format": "openai", @@ -3117,7 +3858,10 @@ "deprecation_date": "2026-02-28", "parent": "grok-2-vision", "max_input_tokens": 32768, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "xAI" + ] }, "grok-2": { "format": "openai", @@ -3126,7 +3870,10 @@ "output_cost_per_mil_tokens": 10, "displayName": "Grok 2", "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-2-latest": { "format": "openai", @@ -3135,7 +3882,10 @@ "output_cost_per_mil_tokens": 10, "parent": "grok-2", "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-2-1212": { "format": "openai", @@ -3144,7 +3894,10 @@ "output_cost_per_mil_tokens": 10, "parent": "grok-2", "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "grok-vision-beta": { "format": "openai", @@ -3153,7 +3906,10 @@ "input_cost_per_mil_tokens": 5, "output_cost_per_mil_tokens": 15, "max_input_tokens": 8192, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "xAI" + ] }, "grok-beta": { "format": "openai", @@ -3161,7 +3917,10 @@ "input_cost_per_mil_tokens": 5, "output_cost_per_mil_tokens": 15, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "xAI" + ] }, "amazon.nova-pro-v1:0": { "format": "converse", @@ -3171,7 +3930,10 @@ "output_cost_per_mil_tokens": 3.2, "displayName": "Nova Pro", "max_input_tokens": 300000, - "max_output_tokens": 10000 + "max_output_tokens": 10000, + "available_providers": [ + "bedrock" + ] }, "us.amazon.nova-pro-v1:0": { "format": "converse", @@ -3182,7 +3944,10 @@ "displayName": "US Nova Pro", "parent": "amazon.nova-pro-v1:0", "max_input_tokens": 300000, - "max_output_tokens": 10000 + "max_output_tokens": 10000, + "available_providers": [ + "bedrock" + ] }, "amazon.nova-micro-v1:0": { "format": "converse", @@ -3191,7 +3956,10 @@ "output_cost_per_mil_tokens": 0.14, "displayName": "Nova Micro", "max_input_tokens": 128000, - "max_output_tokens": 10000 + "max_output_tokens": 10000, + "available_providers": [ + "bedrock" + ] }, "us.amazon.nova-micro-v1:0": { "format": "converse", @@ -3201,7 +3969,10 @@ "displayName": "US Nova Micro", "parent": "amazon.nova-micro-v1:0", "max_input_tokens": 128000, - "max_output_tokens": 10000 + "max_output_tokens": 10000, + "available_providers": [ + "bedrock" + ] }, "amazon.nova-lite-v1:0": { "format": "converse", @@ -3211,7 +3982,10 @@ "output_cost_per_mil_tokens": 0.24, "displayName": "Nova Lite", "max_input_tokens": 300000, - "max_output_tokens": 10000 + "max_output_tokens": 10000, + "available_providers": [ + "bedrock" + ] }, "us.amazon.nova-lite-v1:0": { "format": "converse", @@ -3222,7 +3996,10 @@ "displayName": "US Nova Lite", "parent": "amazon.nova-lite-v1:0", "max_input_tokens": 300000, - "max_output_tokens": 10000 + "max_output_tokens": 10000, + "available_providers": [ + "bedrock" + ] }, "amazon.titan-text-premier-v1:0": { "format": "converse", @@ -3231,7 +4008,10 @@ "output_cost_per_mil_tokens": 1.5, "displayName": "Titan Text Premier", "max_input_tokens": 42000, - "max_output_tokens": 32000 + "max_output_tokens": 32000, + "available_providers": [ + "bedrock" + ] }, "amazon.titan-text-express-v1": { "format": "converse", @@ -3240,7 +4020,10 @@ "output_cost_per_mil_tokens": 1.7, "displayName": "Titan Text Express", "max_input_tokens": 42000, - "max_output_tokens": 8000 + "max_output_tokens": 8000, + "available_providers": [ + "bedrock" + ] }, "amazon.titan-text-lite-v1": { "format": "converse", @@ -3249,7 +4032,10 @@ "output_cost_per_mil_tokens": 0.4, "displayName": "Titan Text Lite", "max_input_tokens": 42000, - "max_output_tokens": 4000 + "max_output_tokens": 4000, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-sonnet-4-6": { "format": "anthropic", @@ -3264,7 +4050,10 @@ "reasoning_budget": true, "parent": "anthropic.claude-sonnet-4-6", "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-sonnet-4-6": { "format": "anthropic", @@ -3278,7 +4067,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-sonnet-4-5-20250929-v1:0": { "format": "anthropic", @@ -3292,7 +4084,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { "format": "anthropic", @@ -3307,7 +4102,10 @@ "reasoning_budget": true, "parent": "anthropic.claude-sonnet-4-5-20250929-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-sonnet-4-20250514-v1:0": { "format": "anthropic", @@ -3321,7 +4119,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 1000000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-sonnet-4-20250514-v1:0": { "format": "anthropic", @@ -3336,7 +4137,10 @@ "reasoning_budget": true, "parent": "anthropic.claude-sonnet-4-20250514-v1:0", "max_input_tokens": 1000000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-3-7-sonnet-20250219-v1:0": { "format": "anthropic", @@ -3351,7 +4155,10 @@ "reasoning_budget": true, "deprecation_date": "2026-02-19", "max_input_tokens": 200000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-3-7-sonnet-20250219-v1:0": { "format": "anthropic", @@ -3367,7 +4174,10 @@ "deprecation_date": "2026-02-19", "parent": "anthropic.claude-3-7-sonnet-20250219-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-haiku-4-5-20251001-v1:0": { "format": "anthropic", @@ -3381,7 +4191,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-haiku-4-5-20251001-v1:0": { "format": "anthropic", @@ -3396,7 +4209,10 @@ "reasoning_budget": true, "parent": "anthropic.claude-haiku-4-5-20251001-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-3-5-haiku-20241022-v1:0": { "format": "anthropic", @@ -3409,7 +4225,10 @@ "displayName": "Claude 3.5 Haiku", "deprecation_date": "2026-02-19", "max_input_tokens": 200000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-3-5-haiku-20241022-v1:0": { "format": "anthropic", @@ -3423,7 +4242,10 @@ "deprecation_date": "2026-02-19", "parent": "anthropic.claude-3-5-haiku-20241022-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-3-5-sonnet-20241022-v2:0": { "format": "anthropic", @@ -3435,7 +4257,10 @@ "input_cache_write_cost_per_mil_tokens": 3.75, "displayName": "Claude 3.5 Sonnet v2", "max_input_tokens": 1000000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { "format": "anthropic", @@ -3448,7 +4273,10 @@ "displayName": "US Claude 3.5 Sonnet v2", "parent": "anthropic.claude-3-5-sonnet-20241022-v2:0", "max_input_tokens": 200000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "bedrock" + ] }, "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { "format": "anthropic", @@ -3461,7 +4289,10 @@ "displayName": "APAC Claude 3.5 Sonnet v2", "parent": "anthropic.claude-3-5-sonnet-20241022-v2:0", "max_input_tokens": 200000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-3-5-sonnet-20240620-v1:0": { "format": "anthropic", @@ -3473,7 +4304,10 @@ "input_cache_write_cost_per_mil_tokens": 3.75, "displayName": "Claude 3.5 Sonnet", "max_input_tokens": 1000000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-3-5-sonnet-20240620-v1:0": { "format": "anthropic", @@ -3486,7 +4320,10 @@ "displayName": "US Claude 3.5 Sonnet", "parent": "anthropic.claude-3-5-sonnet-20240620-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": { "format": "anthropic", @@ -3499,7 +4336,10 @@ "displayName": "APAC Claude 3.5 Sonnet", "parent": "anthropic.claude-3-5-sonnet-20240620-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "eu.anthropic.claude-3-5-sonnet-20240620-v1:0": { "format": "anthropic", @@ -3512,7 +4352,10 @@ "displayName": "EU Claude 3.5 Sonnet", "parent": "anthropic.claude-3-5-sonnet-20240620-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-opus-4-5-20251101-v1:0": { "format": "anthropic", @@ -3525,7 +4368,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-opus-4-6-v1:0": { "format": "anthropic", @@ -3566,7 +4412,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 200000, - "max_output_tokens": 64000 + "max_output_tokens": 64000, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-opus-4-1-20250805-v1:0": { "format": "anthropic", @@ -3580,7 +4429,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 200000, - "max_output_tokens": 32000 + "max_output_tokens": 32000, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-opus-4-1-20250805-v1:0": { "format": "anthropic", @@ -3595,7 +4447,10 @@ "reasoning_budget": true, "parent": "anthropic.claude-opus-4-1-20250805-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 32000 + "max_output_tokens": 32000, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-opus-4-20250514-v1:0": { "format": "anthropic", @@ -3609,7 +4464,10 @@ "reasoning": true, "reasoning_budget": true, "max_input_tokens": 200000, - "max_output_tokens": 32000 + "max_output_tokens": 32000, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-opus-4-20250514-v1:0": { "format": "anthropic", @@ -3624,7 +4482,10 @@ "reasoning_budget": true, "parent": "anthropic.claude-opus-4-20250514-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 32000 + "max_output_tokens": 32000, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-3-opus-20240229-v1:0": { "format": "anthropic", @@ -3636,7 +4497,10 @@ "input_cache_write_cost_per_mil_tokens": 18.75, "displayName": "Claude 3 Opus", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-3-opus-20240229-v1:0": { "format": "anthropic", @@ -3649,7 +4513,10 @@ "displayName": "US Claude 3 Opus", "parent": "anthropic.claude-3-opus-20240229-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-3-sonnet-20240229-v1:0": { "format": "anthropic", @@ -3661,7 +4528,10 @@ "input_cache_write_cost_per_mil_tokens": 3.75, "displayName": "Claude 3 Sonnet", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-3-sonnet-20240229-v1:0": { "format": "anthropic", @@ -3674,7 +4544,10 @@ "displayName": "US Claude 3 Sonnet", "parent": "anthropic.claude-3-sonnet-20240229-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "apac.anthropic.claude-3-sonnet-20240229-v1:0": { "format": "anthropic", @@ -3687,7 +4560,10 @@ "displayName": "APAC Claude 3 Sonnet", "parent": "anthropic.claude-3-sonnet-20240229-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "eu.anthropic.claude-3-sonnet-20240229-v1:0": { "format": "anthropic", @@ -3700,7 +4576,10 @@ "displayName": "EU Claude 3 Sonnet", "parent": "anthropic.claude-3-sonnet-20240229-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "anthropic.claude-3-haiku-20240307-v1:0": { "format": "anthropic", @@ -3712,7 +4591,10 @@ "input_cache_write_cost_per_mil_tokens": 0.3125, "displayName": "Claude 3 Haiku", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "us.anthropic.claude-3-haiku-20240307-v1:0": { "format": "anthropic", @@ -3725,7 +4607,10 @@ "displayName": "US Claude 3 Haiku", "parent": "anthropic.claude-3-haiku-20240307-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "apac.anthropic.claude-3-haiku-20240307-v1:0": { "format": "anthropic", @@ -3738,7 +4623,10 @@ "displayName": "APAC Claude 3 Haiku", "parent": "anthropic.claude-3-haiku-20240307-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "eu.anthropic.claude-3-haiku-20240307-v1:0": { "format": "anthropic", @@ -3751,7 +4639,10 @@ "displayName": "EU Claude 3 Haiku", "parent": "anthropic.claude-3-haiku-20240307-v1:0", "max_input_tokens": 200000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "meta.llama3-3-70b-instruct-v1:0": { "format": "converse", @@ -3760,7 +4651,10 @@ "output_cost_per_mil_tokens": 0.72, "displayName": "Llama 3.3 70B Instruct", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "us.meta.llama3-3-70b-instruct-v1:0": { "format": "converse", @@ -3770,7 +4664,10 @@ "displayName": "US Llama 3.3 70B Instruct", "parent": "meta.llama3-3-70b-instruct-v1:0", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "meta.llama3-2-90b-instruct-v1:0": { "format": "converse", @@ -3780,7 +4677,10 @@ "output_cost_per_mil_tokens": 2, "displayName": "Llama 3.2 90B Vision Instruct", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "us.meta.llama3-2-90b-instruct-v1:0": { "format": "converse", @@ -3791,7 +4691,10 @@ "displayName": "US Llama 3.2 90B Vision Instruct", "parent": "meta.llama3-2-90b-instruct-v1:0", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "meta.llama3-2-11b-instruct-v1:0": { "format": "converse", @@ -3801,7 +4704,10 @@ "output_cost_per_mil_tokens": 0.35, "displayName": "Llama 3.2 11B Vision Instruct", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "us.meta.llama3-2-11b-instruct-v1:0": { "format": "converse", @@ -3812,7 +4718,10 @@ "displayName": "US Llama 3.2 11B Vision Instruct", "parent": "meta.llama3-2-11b-instruct-v1:0", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "meta.llama3-2-3b-instruct-v1:0": { "format": "converse", @@ -3821,7 +4730,10 @@ "output_cost_per_mil_tokens": 0.15, "displayName": "Llama 3.2 3B Instruct", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "us.meta.llama3-2-3b-instruct-v1:0": { "format": "converse", @@ -3831,7 +4743,10 @@ "displayName": "US Llama 3.2 3B Instruct", "parent": "meta.llama3-2-3b-instruct-v1:0", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "eu.meta.llama3-2-3b-instruct-v1:0": { "format": "converse", @@ -3841,7 +4756,10 @@ "displayName": "EU Llama 3.2 3B Instruct", "parent": "meta.llama3-2-3b-instruct-v1:0", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "meta.llama3-2-1b-instruct-v1:0": { "format": "converse", @@ -3850,7 +4768,10 @@ "output_cost_per_mil_tokens": 0.1, "displayName": "Llama 3.2 1B Instruct", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "us.meta.llama3-2-1b-instruct-v1:0": { "format": "converse", @@ -3860,7 +4781,10 @@ "displayName": "US Llama 3.2 1B Instruct", "parent": "meta.llama3-2-1b-instruct-v1:0", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "eu.meta.llama3-2-1b-instruct-v1:0": { "format": "converse", @@ -3870,7 +4794,10 @@ "displayName": "EU Llama 3.2 1B Instruct", "parent": "meta.llama3-2-1b-instruct-v1:0", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "meta.llama3-1-405b-instruct-v1:0": { "format": "converse", @@ -3879,7 +4806,10 @@ "output_cost_per_mil_tokens": 16, "displayName": "Llama 3.1 405B Instruct", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "us.meta.llama3-1-405b-instruct-v1:0": { "format": "converse", @@ -3889,7 +4819,10 @@ "displayName": "US Llama 3.1 405B Instruct", "parent": "meta.llama3-1-405b-instruct-v1:0", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "meta.llama3-1-70b-instruct-v1:0": { "format": "converse", @@ -3898,7 +4831,10 @@ "output_cost_per_mil_tokens": 0.99, "displayName": "Llama 3.1 70B Instruct", "max_input_tokens": 128000, - "max_output_tokens": 2048 + "max_output_tokens": 2048, + "available_providers": [ + "bedrock" + ] }, "us.meta.llama3-1-70b-instruct-v1:0": { "format": "converse", @@ -3908,7 +4844,10 @@ "displayName": "US Llama 3.1 70B Instruct", "parent": "meta.llama3-1-70b-instruct-v1:0", "max_input_tokens": 128000, - "max_output_tokens": 2048 + "max_output_tokens": 2048, + "available_providers": [ + "bedrock" + ] }, "meta.llama3-1-8b-instruct-v1:0": { "format": "converse", @@ -3917,7 +4856,10 @@ "output_cost_per_mil_tokens": 0.22, "displayName": "Llama 3.1 8B Instruct", "max_input_tokens": 128000, - "max_output_tokens": 2048 + "max_output_tokens": 2048, + "available_providers": [ + "bedrock" + ] }, "us.meta.llama3-1-8b-instruct-v1:0": { "format": "converse", @@ -3927,7 +4869,10 @@ "displayName": "US Llama 3.1 8B Instruct", "parent": "meta.llama3-1-8b-instruct-v1:0", "max_input_tokens": 128000, - "max_output_tokens": 2048 + "max_output_tokens": 2048, + "available_providers": [ + "bedrock" + ] }, "meta.llama3-70b-instruct-v1:0": { "format": "converse", @@ -3936,7 +4881,10 @@ "output_cost_per_mil_tokens": 3.5, "displayName": "Llama 3 70B Instruct", "max_input_tokens": 8192, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "bedrock" + ] }, "meta.llama3-8b-instruct-v1:0": { "format": "converse", @@ -3945,7 +4893,10 @@ "output_cost_per_mil_tokens": 0.6, "displayName": "Llama 3 8B Instruct", "max_input_tokens": 8192, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "bedrock" + ] }, "mistral.mistral-large-2402-v1:0": { "format": "converse", @@ -3954,7 +4905,10 @@ "output_cost_per_mil_tokens": 24, "displayName": "Mistral Large 24.02", "max_input_tokens": 32000, - "max_output_tokens": 8191 + "max_output_tokens": 8191, + "available_providers": [ + "bedrock" + ] }, "mistral.mistral-small-2402-v1:0": { "format": "converse", @@ -3963,7 +4917,10 @@ "output_cost_per_mil_tokens": 3, "displayName": "Mistral Small 24.02", "max_input_tokens": 32000, - "max_output_tokens": 8191 + "max_output_tokens": 8191, + "available_providers": [ + "bedrock" + ] }, "mistral.mixtral-8x7b-instruct-v0:1": { "format": "converse", @@ -3972,7 +4929,10 @@ "output_cost_per_mil_tokens": 0.7, "displayName": "Mixtral 8x7B", "max_input_tokens": 32000, - "max_output_tokens": 8191 + "max_output_tokens": 8191, + "available_providers": [ + "bedrock" + ] }, "mistral.mistral-7b-instruct-v0:2": { "format": "converse", @@ -3981,7 +4941,10 @@ "output_cost_per_mil_tokens": 0.2, "displayName": "Mistral 7B", "max_input_tokens": 32000, - "max_output_tokens": 8191 + "max_output_tokens": 8191, + "available_providers": [ + "bedrock" + ] }, "cohere.command-r-plus-v1:0": { "format": "converse", @@ -3990,7 +4953,10 @@ "output_cost_per_mil_tokens": 15, "displayName": "Command R+", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "cohere.command-r-v1:0": { "format": "converse", @@ -3999,7 +4965,10 @@ "output_cost_per_mil_tokens": 1.5, "displayName": "Command R", "max_input_tokens": 128000, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "cohere.command-text-v14": { "format": "converse", @@ -4008,7 +4977,10 @@ "output_cost_per_mil_tokens": 2, "displayName": "Command", "max_input_tokens": 4096, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "cohere.command-light-text-v14": { "format": "converse", @@ -4017,7 +4989,10 @@ "output_cost_per_mil_tokens": 0.6, "displayName": "Command Light", "max_input_tokens": 4096, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "bedrock" + ] }, "publishers/google/models/gemini-3.1-pro-preview": { "format": "google", @@ -4029,7 +5004,9 @@ "displayName": "Gemini 3.1 Pro Preview", "reasoning": true, "reasoning_budget": true, - "locations": ["global"], + "locations": [ + "global" + ], "max_input_tokens": 1048576, "max_output_tokens": 65536 }, @@ -4043,7 +5020,9 @@ "displayName": "Gemini 3.1 Pro Custom Tools Preview", "reasoning": true, "reasoning_budget": true, - "locations": ["global"], + "locations": [ + "global" + ], "max_input_tokens": 1048576, "max_output_tokens": 65536 }, @@ -4052,12 +5031,14 @@ "flavor": "chat", "multimodal": true, "input_cost_per_mil_tokens": 0.25, - "output_cost_per_mil_tokens": 1.50, + "output_cost_per_mil_tokens": 1.5, "input_cache_read_cost_per_mil_tokens": 0.025, "displayName": "Gemini 3.1 Flash-Lite (Preview)", "reasoning": true, "reasoning_budget": true, - "locations": ["global"], + "locations": [ + "global" + ], "max_input_tokens": 1048576, "max_output_tokens": 65535 }, @@ -4648,25 +5629,53 @@ "format": "openai", "flavor": "chat", "multimodal": true, + "input_cost_per_mil_tokens": 2.99999, + "output_cost_per_mil_tokens": 15.00002, "displayName": "Claude 3.7 Sonnet", "reasoning": true, "reasoning_budget": true, - "deprecation_date": "2026-02-19" + "deprecation_date": "2026-02-19", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "available_providers": [ + "databricks" + ] }, "databricks-meta-llama-3-3-70b-instruct": { "format": "openai", "flavor": "chat", - "displayName": "Llama 3.3 70B Instruct" + "input_cost_per_mil_tokens": 0.50001, + "output_cost_per_mil_tokens": 1.50003, + "displayName": "Llama 3.3 70B Instruct", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "available_providers": [ + "databricks" + ] }, "databricks-meta-llama-3-1-405b-instruct": { "format": "openai", "flavor": "chat", - "displayName": "Llama 3.1 405B Instruct" + "input_cost_per_mil_tokens": 5.00003, + "output_cost_per_mil_tokens": 15.00002, + "displayName": "Llama 3.1 405B Instruct", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "available_providers": [ + "databricks" + ] }, "databricks-meta-llama-3-1-8b-instruct": { "format": "openai", "flavor": "chat", - "displayName": "Llama 3.1 8B Instruct" + "input_cost_per_mil_tokens": 0.15001, + "output_cost_per_mil_tokens": 0.45003, + "displayName": "Llama 3.1 8B Instruct", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "available_providers": [ + "databricks" + ] }, "Qwen3-Coder-480B-A35B-Instruct": { "format": "openai", @@ -4678,9 +5687,12 @@ "moonshotai/Kimi-K2-Instruct": { "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.6, - "output_cost_per_mil_tokens": 2.5, - "displayName": "Kimi K2 Instruct" + "input_cost_per_mil_tokens": 1, + "output_cost_per_mil_tokens": 3, + "displayName": "Kimi K2 Instruct", + "available_providers": [ + "together" + ] }, "deepseek-ai/DeepSeek-V3-0324": { "format": "openai", @@ -4702,7 +5714,10 @@ "input_cache_read_cost_per_mil_tokens": 0.02, "reasoning": true, "max_input_tokens": 256000, - "max_output_tokens": 256000 + "max_output_tokens": 256000, + "available_providers": [ + "xAI" + ] }, "grok-code-fast-1": { "format": "openai", @@ -4712,7 +5727,10 @@ "input_cache_read_cost_per_mil_tokens": 0.02, "reasoning": true, "max_input_tokens": 256000, - "max_output_tokens": 256000 + "max_output_tokens": 256000, + "available_providers": [ + "xAI" + ] }, "grok-code-fast-1-0825": { "format": "openai", @@ -4722,7 +5740,10 @@ "input_cache_read_cost_per_mil_tokens": 0.02, "reasoning": true, "max_input_tokens": 256000, - "max_output_tokens": 256000 + "max_output_tokens": 256000, + "available_providers": [ + "xAI" + ] }, "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct": { "format": "openai", @@ -4730,7 +5751,10 @@ "input_cost_per_mil_tokens": 1.2, "output_cost_per_mil_tokens": 1.2, "max_input_tokens": 65536, - "max_output_tokens": 65536 + "max_output_tokens": 65536, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/deepseek-r1": { "format": "openai", @@ -4738,7 +5762,10 @@ "input_cost_per_mil_tokens": 3, "output_cost_per_mil_tokens": 8, "max_input_tokens": 128000, - "max_output_tokens": 20480 + "max_output_tokens": 20480, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528": { "format": "openai", @@ -4746,7 +5773,10 @@ "input_cost_per_mil_tokens": 3, "output_cost_per_mil_tokens": 8, "max_input_tokens": 160000, - "max_output_tokens": 160000 + "max_output_tokens": 160000, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/deepseek-r1-basic": { "format": "openai", @@ -4754,7 +5784,10 @@ "input_cost_per_mil_tokens": 0.55, "output_cost_per_mil_tokens": 2.19, "max_input_tokens": 128000, - "max_output_tokens": 20480 + "max_output_tokens": 20480, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/deepseek-v3": { "format": "openai", @@ -4762,7 +5795,10 @@ "input_cost_per_mil_tokens": 0.9, "output_cost_per_mil_tokens": 0.9, "max_input_tokens": 128000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/deepseek-v3-0324": { "format": "openai", @@ -4770,7 +5806,10 @@ "input_cost_per_mil_tokens": 0.9, "output_cost_per_mil_tokens": 0.9, "max_input_tokens": 163840, - "max_output_tokens": 163840 + "max_output_tokens": 163840, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/deepseek-v3p1": { "format": "openai", @@ -4778,7 +5817,10 @@ "input_cost_per_mil_tokens": 0.56, "output_cost_per_mil_tokens": 1.68, "max_input_tokens": 128000, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/firefunction-v2": { "format": "openai", @@ -4786,7 +5828,10 @@ "input_cost_per_mil_tokens": 0.9, "output_cost_per_mil_tokens": 0.9, "max_input_tokens": 8192, - "max_output_tokens": 8192 + "max_output_tokens": 8192, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/glm-4p5": { "format": "openai", @@ -4794,7 +5839,10 @@ "input_cost_per_mil_tokens": 0.55, "output_cost_per_mil_tokens": 2.19, "max_input_tokens": 128000, - "max_output_tokens": 96000 + "max_output_tokens": 96000, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/glm-4p5-air": { "format": "openai", @@ -4802,7 +5850,10 @@ "input_cost_per_mil_tokens": 0.22, "output_cost_per_mil_tokens": 0.88, "max_input_tokens": 128000, - "max_output_tokens": 96000 + "max_output_tokens": 96000, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": { "format": "openai", @@ -4811,7 +5862,10 @@ "output_cost_per_mil_tokens": 0.6, "reasoning": true, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/gpt-oss-20b": { "format": "openai", @@ -4820,7 +5874,10 @@ "output_cost_per_mil_tokens": 0.2, "reasoning": true, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "fireworks" + ] }, "accounts/fireworks/models/kimi-k2p5": { "format": "openai", @@ -4839,7 +5896,10 @@ "input_cost_per_mil_tokens": 0.6, "output_cost_per_mil_tokens": 2.5, "max_input_tokens": 131072, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-405b-instruct": { "format": "openai", @@ -4847,7 +5907,10 @@ "input_cost_per_mil_tokens": 3, "output_cost_per_mil_tokens": 3, "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/llama-v3p1-8b-instruct": { "format": "openai", @@ -4855,7 +5918,10 @@ "input_cost_per_mil_tokens": 0.1, "output_cost_per_mil_tokens": 0.1, "max_input_tokens": 16384, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-11b-vision-instruct": { "format": "openai", @@ -4864,7 +5930,10 @@ "input_cost_per_mil_tokens": 0.2, "output_cost_per_mil_tokens": 0.2, "max_input_tokens": 16384, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-1b-instruct": { "format": "openai", @@ -4872,7 +5941,10 @@ "input_cost_per_mil_tokens": 0.1, "output_cost_per_mil_tokens": 0.1, "max_input_tokens": 16384, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-3b-instruct": { "format": "openai", @@ -4880,7 +5952,10 @@ "input_cost_per_mil_tokens": 0.1, "output_cost_per_mil_tokens": 0.1, "max_input_tokens": 16384, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/llama-v3p2-90b-vision-instruct": { "format": "openai", @@ -4889,7 +5964,10 @@ "input_cost_per_mil_tokens": 0.9, "output_cost_per_mil_tokens": 0.9, "max_input_tokens": 16384, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/llama4-maverick-instruct-basic": { "format": "openai", @@ -4897,7 +5975,10 @@ "input_cost_per_mil_tokens": 0.22, "output_cost_per_mil_tokens": 0.88, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/llama4-scout-instruct-basic": { "format": "openai", @@ -4905,7 +5986,10 @@ "input_cost_per_mil_tokens": 0.15, "output_cost_per_mil_tokens": 0.6, "max_input_tokens": 131072, - "max_output_tokens": 131072 + "max_output_tokens": 131072, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { "format": "openai", @@ -4913,7 +5997,10 @@ "input_cost_per_mil_tokens": 1.2, "output_cost_per_mil_tokens": 1.2, "max_input_tokens": 65536, - "max_output_tokens": 65536 + "max_output_tokens": 65536, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/qwen2-72b-instruct": { "format": "openai", @@ -4921,7 +6008,10 @@ "input_cost_per_mil_tokens": 0.9, "output_cost_per_mil_tokens": 0.9, "max_input_tokens": 32768, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct": { "format": "openai", @@ -4929,7 +6019,10 @@ "input_cost_per_mil_tokens": 0.9, "output_cost_per_mil_tokens": 0.9, "max_input_tokens": 4096, - "max_output_tokens": 4096 + "max_output_tokens": 4096, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/accounts/fireworks/models/yi-large": { "format": "openai", @@ -4937,90 +6030,132 @@ "input_cost_per_mil_tokens": 3, "output_cost_per_mil_tokens": 3, "max_input_tokens": 32768, - "max_output_tokens": 32768 + "max_output_tokens": 32768, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/nomic-ai/nomic-embed-text-v1": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.008, "output_cost_per_mil_tokens": 0, - "max_input_tokens": 8192 + "max_input_tokens": 8192, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/nomic-ai/nomic-embed-text-v1.5": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.008, "output_cost_per_mil_tokens": 0, - "max_input_tokens": 8192 + "max_input_tokens": 8192, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/thenlper/gte-base": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.008, "output_cost_per_mil_tokens": 0, - "max_input_tokens": 512 + "max_input_tokens": 512, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/thenlper/gte-large": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.016, "output_cost_per_mil_tokens": 0, - "max_input_tokens": 512 + "max_input_tokens": 512, + "available_providers": [ + "fireworks" + ] }, "fireworks_ai/WhereIsAI/UAE-Large-V1": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.016, "output_cost_per_mil_tokens": 0, - "max_input_tokens": 512 + "max_input_tokens": 512, + "available_providers": [ + "fireworks" + ] }, "fireworks-ai-4.1b-to-16b": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.2, - "output_cost_per_mil_tokens": 0.2 + "output_cost_per_mil_tokens": 0.2, + "available_providers": [ + "fireworks" + ] }, "fireworks-ai-56b-to-176b": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 1.2, - "output_cost_per_mil_tokens": 1.2 + "output_cost_per_mil_tokens": 1.2, + "available_providers": [ + "fireworks" + ] }, "fireworks-ai-above-16b": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.9, - "output_cost_per_mil_tokens": 0.9 + "output_cost_per_mil_tokens": 0.9, + "available_providers": [ + "fireworks" + ] }, "fireworks-ai-default": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0, - "output_cost_per_mil_tokens": 0 + "output_cost_per_mil_tokens": 0, + "available_providers": [ + "fireworks" + ] }, "fireworks-ai-embedding-150m-to-350m": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.016, - "output_cost_per_mil_tokens": 0 + "output_cost_per_mil_tokens": 0, + "available_providers": [ + "fireworks" + ] }, "fireworks-ai-embedding-up-to-150m": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.008, - "output_cost_per_mil_tokens": 0 + "output_cost_per_mil_tokens": 0, + "available_providers": [ + "fireworks" + ] }, "fireworks-ai-moe-up-to-56b": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.5, - "output_cost_per_mil_tokens": 0.5 + "output_cost_per_mil_tokens": 0.5, + "available_providers": [ + "fireworks" + ] }, "fireworks-ai-up-to-4b": { "format": "openai", "flavor": "chat", "input_cost_per_mil_tokens": 0.2, - "output_cost_per_mil_tokens": 0.2 + "output_cost_per_mil_tokens": 0.2, + "available_providers": [ + "fireworks" + ] }, "gpt-5.4": { "format": "openai", @@ -5031,7 +6166,12 @@ "input_cache_read_cost_per_mil_tokens": 0.25, "displayName": "GPT-5.4", "reasoning": true, - "max_input_tokens": 272000 + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5.4-pro": { "format": "openai", @@ -5039,9 +6179,15 @@ "multimodal": true, "input_cost_per_mil_tokens": 30, "output_cost_per_mil_tokens": 180, + "input_cache_read_cost_per_mil_tokens": 3, "displayName": "GPT-5.4 Pro", "reasoning": true, - "max_input_tokens": 272000 + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5.3-chat-latest": { "format": "openai", @@ -5053,7 +6199,11 @@ "displayName": "GPT-5.3 chat", "reasoning": true, "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5.2-chat-latest": { "format": "openai", @@ -5065,7 +6215,11 @@ "displayName": "GPT-5.2 chat", "reasoning": true, "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5-chat": { "format": "openai", @@ -5076,7 +6230,11 @@ "input_cache_read_cost_per_mil_tokens": 0.125, "reasoning": true, "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5.2": { "format": "openai", @@ -5088,7 +6246,11 @@ "displayName": "GPT-5.2", "reasoning": true, "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5.2-2025-12-11": { "format": "openai", @@ -5099,7 +6261,11 @@ "input_cache_read_cost_per_mil_tokens": 0.175, "reasoning": true, "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5.1": { "format": "openai", @@ -5111,7 +6277,11 @@ "displayName": "GPT-5.1", "reasoning": true, "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5.1-2025-11-13": { "format": "openai", @@ -5122,7 +6292,11 @@ "input_cache_read_cost_per_mil_tokens": 0.125, "reasoning": true, "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5.1-chat-latest": { "format": "openai", @@ -5134,7 +6308,11 @@ "displayName": "GPT-5.1 chat", "reasoning": true, "max_input_tokens": 128000, - "max_output_tokens": 16384 + "max_output_tokens": 16384, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5.1-codex": { "format": "openai", @@ -5146,7 +6324,11 @@ "displayName": "GPT-5.1 Codex", "reasoning": true, "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5.1-codex-mini": { "format": "openai", @@ -5158,7 +6340,11 @@ "displayName": "GPT-5.1 Codex Mini", "reasoning": true, "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5.2-codex": { "format": "openai", @@ -5170,7 +6356,11 @@ "displayName": "GPT-5.2 Codex", "reasoning": true, "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "gpt-5.3-codex": { "format": "openai", @@ -5182,7 +6372,11 @@ "displayName": "GPT-5.3 Codex", "reasoning": true, "max_input_tokens": 272000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "available_providers": [ + "openai", + "azure" + ] }, "accounts/fireworks/models/qwen3-coder-480b-a35b-instruct": { "format": "openai", diff --git a/packages/proxy/schema/models.ts b/packages/proxy/schema/models.ts index 792c4855..59b53d98 100644 --- a/packages/proxy/schema/models.ts +++ b/packages/proxy/schema/models.ts @@ -90,6 +90,7 @@ export const ModelSchema = z.object({ .number() .nullish() .describe("The model supports a maximum output token limit."), + available_providers: z.array(z.enum(ModelEndpointType)).nullish(), }); export type ModelSpec = z.infer; diff --git a/packages/proxy/scripts/sync_models.ts b/packages/proxy/scripts/sync_models.ts index b5a44dbd..07918215 100644 --- a/packages/proxy/scripts/sync_models.ts +++ b/packages/proxy/scripts/sync_models.ts @@ -6,7 +6,7 @@ import yargs from "yargs"; import { hideBin } from "yargs/helpers"; import { exec, spawn } from "child_process"; import { promisify } from "util"; -import { ModelSchema, ModelSpec } from "../schema/models"; +import { ModelEndpointType, ModelSchema, ModelSpec } from "../schema/models"; const execAsync = promisify(exec); @@ -59,6 +59,7 @@ const liteLLMModelDetailSchema = z "ocr", "vector_store", "image_edit", + "realtime", ]) .optional(), supports_function_calling: z.boolean().optional(), @@ -159,8 +160,19 @@ async function readLocalModels(filePath: string): Promise { } function translateToBraintrust(modelName: string, provider?: string): string { - if (provider === "xai" && modelName.startsWith("xai/")) { - return modelName.substring(4); // "xai/" + for (const p of [ + "gemini", + "xai", + "groq", + "together_ai", + "cerebras", + "mistral", + "perplexity", + "databricks", + ]) { + if (provider === p && modelName.startsWith(p + "/")) { + return modelName.substring(p.length + 1); + } } if (provider === "gemini") { @@ -170,9 +182,6 @@ function translateToBraintrust(modelName: string, provider?: string): string { if (modelName.startsWith("gemini/gemma-")) { return "google/" + modelName.substring(7); } - if (modelName.startsWith("gemini/")) { - return modelName.substring(7); - } } if (modelName.startsWith("google/")) { @@ -200,7 +209,7 @@ function getProviderMappingForModel( return ["anthropic"]; } if (lowerProvider === "openai" || lowerProvider.includes("openai")) { - return ["openai"]; + return ["openai", "azure"]; } if ( lowerProvider === "google" || @@ -231,6 +240,12 @@ function getProviderMappingForModel( ) { return ["perplexity"]; } + if ( + lowerProvider === "databricks" || + lowerProvider.includes("databricks") + ) { + return ["databricks"]; + } if (lowerProvider === "lepton" || lowerProvider.includes("lepton")) { return ["lepton"]; } @@ -240,6 +255,12 @@ function getProviderMappingForModel( if (lowerProvider === "baseten" || lowerProvider.includes("baseten")) { return ["baseten"]; } + if (lowerProvider === "bedrock" || lowerProvider.includes("bedrock")) { + return ["bedrock"]; + } + if (lowerProvider === "vertex_ai" || lowerProvider.includes("vertex")) { + return ["vertex"]; + } return []; }; @@ -363,6 +384,12 @@ function convertRemoteToLocalModel( baseModel.deprecation_date = remoteModel.deprecation_date; } + const providers = getProviderMappingForModel(remoteModelName, remoteModel); + if (providers.length > 0) { + baseModel.available_providers = + providers as ModelSpec["available_providers"]; + } + return baseModel as ModelSpec; } @@ -1161,6 +1188,36 @@ async function updateModelsCommand(argv: any) { localDeprecationDate, remoteDeprecationDate, ); + + // Set available_providers from remote + const remoteProviders = getProviderMappingForModel( + originalRemoteModelName, + remoteModelDetail, + ); + if (remoteProviders.length > 0) { + const currentProviders = (modelInUpdatedList as any) + .available_providers; + const same = + Array.isArray(currentProviders) && + currentProviders.length === remoteProviders.length && + currentProviders.every( + (p: string, i: number) => p === remoteProviders[i], + ); + if (!same) { + (modelInUpdatedList as any).available_providers = remoteProviders; + discrepanciesFound++; + madeChanges = true; + if (!modelReportedThisIteration) { + console.log( + `\n[WRITE] Updating model for: ${localModelName} (Remote: ${originalRemoteModelName})`, + ); + modelReportedThisIteration = true; + } + console.log( + ` [WRITE] Updated available_providers to: ${JSON.stringify(remoteProviders)}`, + ); + } + } } if (argv.write) { @@ -1331,9 +1388,9 @@ async function addModelsCommand(argv: any) { // Convert remote models to local format const modelsToAdd = missingInLocal.map( - ({ translatedName, remoteModel }) => ({ + ({ remoteModelName, translatedName, remoteModel }) => ({ name: translatedName, - model: convertRemoteToLocalModel(translatedName, remoteModel), + model: convertRemoteToLocalModel(remoteModelName, remoteModel), }), );