diff --git a/packages/proxy/schema/index.ts b/packages/proxy/schema/index.ts index 91eeb57a..9cc2e649 100644 --- a/packages/proxy/schema/index.ts +++ b/packages/proxy/schema/index.ts @@ -689,6 +689,7 @@ export const AvailableEndpointTypes: { [name: string]: ModelEndpointType[] } = { "Qwen/Qwen3.6-Plus": ["together"], "zai-org/GLM-5.1": ["baseten", "together"], "zai-org/GLM-5.2": ["baseten", "together"], + "zai-org/GLM-5.2-Fast": ["baseten"], "MiniMaxAI/MiniMax-M2.7": ["together"], "MiniMaxAI/MiniMax-M3": ["together"], "mistral-medium-2508": ["mistral"], diff --git a/packages/proxy/schema/model_list.json b/packages/proxy/schema/model_list.json index 8f7ea3ba..6de3d62b 100644 --- a/packages/proxy/schema/model_list.json +++ b/packages/proxy/schema/model_list.json @@ -6093,40 +6093,40 @@ "groq" ] }, - "publishers/google/models/gemini-3.5-flash": { + "publishers/google/models/gemini-3.6-flash": { "format": "google", "flavor": "chat", "multimodal": true, "input_cost_per_mil_tokens": 1.5, - "output_cost_per_mil_tokens": 9, + "output_cost_per_mil_tokens": 7.5, "input_cache_read_cost_per_mil_tokens": 0.15, - "displayName": "Gemini 3.5 Flash", + "displayName": "Gemini 3.6 Flash", "reasoning": true, "reasoning_budget": true, "locations": [ "global" ], "max_input_tokens": 1048576, - "max_output_tokens": 65535, + "max_output_tokens": 65536, "available_providers": [ "vertex" ] }, - "publishers/google/models/gemini-3.6-flash": { + "publishers/google/models/gemini-3.5-flash": { "format": "google", "flavor": "chat", "multimodal": true, "input_cost_per_mil_tokens": 1.5, - "output_cost_per_mil_tokens": 7.5, + "output_cost_per_mil_tokens": 9, "input_cache_read_cost_per_mil_tokens": 0.15, - "displayName": "Gemini 3.6 Flash", + "displayName": "Gemini 3.5 Flash", "reasoning": true, "reasoning_budget": true, "locations": [ "global" ], "max_input_tokens": 1048576, - "max_output_tokens": 65536, + "max_output_tokens": 65535, "available_providers": [ "vertex" ] @@ -7047,7 +7047,7 @@ "vertex" ] }, - "publishers/anthropic/models/claude-opus-4-8": { + "publishers/anthropic/models/claude-opus-5": { "format": "anthropic", "flavor": "chat", "multimodal": true, @@ -7055,7 +7055,7 @@ "output_cost_per_mil_tokens": 25, "input_cache_read_cost_per_mil_tokens": 0.5, "input_cache_write_cost_per_mil_tokens": 6.25, - "displayName": "Claude Opus 4.8", + "displayName": "Claude Opus 5", "reasoning": true, "reasoning_budget": true, "max_input_tokens": 1000000, @@ -7064,7 +7064,7 @@ "vertex" ] }, - "publishers/anthropic/models/claude-opus-5": { + "publishers/anthropic/models/claude-opus-4-8": { "format": "anthropic", "flavor": "chat", "multimodal": true, @@ -7072,7 +7072,7 @@ "output_cost_per_mil_tokens": 25, "input_cache_read_cost_per_mil_tokens": 0.5, "input_cache_write_cost_per_mil_tokens": 6.25, - "displayName": "Claude Opus 5", + "displayName": "Claude Opus 4.8", "reasoning": true, "reasoning_budget": true, "max_input_tokens": 1000000, @@ -7984,16 +7984,6 @@ "output_cost_per_mil_tokens": 0.07, "displayName": "WizardLM-2 7B" }, - "wizardlm-2-8x22b": { - "format": "openai", - "flavor": "chat", - "input_cost_per_mil_tokens": 1, - "output_cost_per_mil_tokens": 1, - "displayName": "WizardLM-2 8x22B", - "available_providers": [ - "openrouter" - ] - }, "dolphin-mixtral-8x7b": { "format": "openai", "flavor": "chat", @@ -8064,6 +8054,16 @@ "max_input_tokens": 1000000, "max_output_tokens": 8000 }, + "wizardlm-2-8x22b": { + "format": "openai", + "flavor": "chat", + "input_cost_per_mil_tokens": 1, + "output_cost_per_mil_tokens": 1, + "displayName": "WizardLM-2 8x22B", + "available_providers": [ + "openrouter" + ] + }, "claude-fable-5": { "format": "anthropic", "flavor": "chat", @@ -8088,31 +8088,6 @@ "anthropic" ] }, - "claude-opus-4-8": { - "format": "anthropic", - "flavor": "chat", - "multimodal": true, - "input_cost_per_mil_tokens": 5, - "output_cost_per_mil_tokens": 25, - "input_cache_read_cost_per_mil_tokens": 0.5, - "input_cache_write_cost_per_mil_tokens": 6.25, - "input_cache_write_5m_cost_per_mil_tokens": 6.25, - "input_cache_write_1h_cost_per_mil_tokens": 10, - "displayName": "Claude Opus 4.8", - "reasoning": true, - "reasoning_budget": true, - "fallback_models": [ - "anthropic.claude-opus-4-8", - "global.anthropic.claude-opus-4-8", - "publishers/anthropic/models/claude-opus-4-8", - "us.anthropic.claude-opus-4-8" - ], - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "available_providers": [ - "anthropic" - ] - }, "claude-opus-5": { "format": "anthropic", "flavor": "chat", @@ -8128,11 +8103,10 @@ "reasoning_budget": true, "fallback_models": [ "anthropic.claude-opus-5", + "eu.anthropic.claude-opus-5", "global.anthropic.claude-opus-5", "publishers/anthropic/models/claude-opus-5", - "us.anthropic.claude-opus-5", - "eu.anthropic.claude-opus-5", - "au.anthropic.claude-opus-5" + "us.anthropic.claude-opus-5" ], "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -8207,7 +8181,7 @@ "anthropic" ] }, - "claude-opus-4-7": { + "claude-opus-4-8": { "format": "anthropic", "flavor": "chat", "multimodal": true, @@ -8217,14 +8191,14 @@ "input_cache_write_cost_per_mil_tokens": 6.25, "input_cache_write_5m_cost_per_mil_tokens": 6.25, "input_cache_write_1h_cost_per_mil_tokens": 10, - "displayName": "Claude Opus 4.7", + "displayName": "Claude Opus 4.8", "reasoning": true, "reasoning_budget": true, "fallback_models": [ - "anthropic.claude-opus-4-7", - "global.anthropic.claude-opus-4-7", - "publishers/anthropic/models/claude-opus-4-7", - "us.anthropic.claude-opus-4-7" + "anthropic.claude-opus-4-8", + "global.anthropic.claude-opus-4-8", + "publishers/anthropic/models/claude-opus-4-8", + "us.anthropic.claude-opus-4-8" ], "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -8257,7 +8231,7 @@ "anthropic" ] }, - "claude-opus-4-6": { + "claude-opus-4-7": { "format": "anthropic", "flavor": "chat", "multimodal": true, @@ -8267,11 +8241,14 @@ "input_cache_write_cost_per_mil_tokens": 6.25, "input_cache_write_5m_cost_per_mil_tokens": 6.25, "input_cache_write_1h_cost_per_mil_tokens": 10, - "displayName": "Claude Opus 4.6", + "displayName": "Claude Opus 4.7", "reasoning": true, "reasoning_budget": true, "fallback_models": [ - "publishers/anthropic/models/claude-opus-4-6" + "anthropic.claude-opus-4-7", + "global.anthropic.claude-opus-4-7", + "publishers/anthropic/models/claude-opus-4-7", + "us.anthropic.claude-opus-4-7" ], "max_input_tokens": 1000000, "max_output_tokens": 128000, @@ -8321,6 +8298,28 @@ "anthropic" ] }, + "claude-opus-4-6": { + "format": "anthropic", + "flavor": "chat", + "multimodal": true, + "input_cost_per_mil_tokens": 5, + "output_cost_per_mil_tokens": 25, + "input_cache_read_cost_per_mil_tokens": 0.5, + "input_cache_write_cost_per_mil_tokens": 6.25, + "input_cache_write_5m_cost_per_mil_tokens": 6.25, + "input_cache_write_1h_cost_per_mil_tokens": 10, + "displayName": "Claude Opus 4.6", + "reasoning": true, + "reasoning_budget": true, + "fallback_models": [ + "publishers/anthropic/models/claude-opus-4-6" + ], + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "available_providers": [ + "anthropic" + ] + }, "claude-opus-4-5": { "format": "anthropic", "flavor": "chat", @@ -8416,23 +8415,6 @@ "bedrock" ] }, - "anthropic.claude-opus-4-8": { - "format": "anthropic", - "flavor": "chat", - "multimodal": true, - "input_cost_per_mil_tokens": 5, - "output_cost_per_mil_tokens": 25, - "input_cache_read_cost_per_mil_tokens": 0.5, - "input_cache_write_cost_per_mil_tokens": 6.25, - "displayName": "Claude Opus 4.8", - "reasoning": true, - "reasoning_budget": true, - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "available_providers": [ - "bedrock" - ] - }, "anthropic.claude-opus-5": { "format": "anthropic", "flavor": "chat", @@ -8450,7 +8432,7 @@ "bedrock" ] }, - "global.anthropic.claude-opus-5": { + "anthropic.claude-opus-4-8": { "format": "anthropic", "flavor": "chat", "multimodal": true, @@ -8458,64 +8440,9 @@ "output_cost_per_mil_tokens": 25, "input_cache_read_cost_per_mil_tokens": 0.5, "input_cache_write_cost_per_mil_tokens": 6.25, - "displayName": "Global Claude Opus 5", - "reasoning": true, - "reasoning_budget": true, - "parent": "anthropic.claude-opus-5", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "available_providers": [ - "bedrock" - ] - }, - "us.anthropic.claude-opus-5": { - "format": "anthropic", - "flavor": "chat", - "multimodal": true, - "input_cost_per_mil_tokens": 5.5, - "output_cost_per_mil_tokens": 27.5, - "input_cache_read_cost_per_mil_tokens": 0.55, - "input_cache_write_cost_per_mil_tokens": 6.875, - "displayName": "US Claude Opus 5", - "reasoning": true, - "reasoning_budget": true, - "parent": "anthropic.claude-opus-5", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "available_providers": [ - "bedrock" - ] - }, - "eu.anthropic.claude-opus-5": { - "format": "anthropic", - "flavor": "chat", - "multimodal": true, - "input_cost_per_mil_tokens": 5.5, - "output_cost_per_mil_tokens": 27.5, - "input_cache_read_cost_per_mil_tokens": 0.55, - "input_cache_write_cost_per_mil_tokens": 6.875, - "displayName": "EU Claude Opus 5", - "reasoning": true, - "reasoning_budget": true, - "parent": "anthropic.claude-opus-5", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "available_providers": [ - "bedrock" - ] - }, - "au.anthropic.claude-opus-5": { - "format": "anthropic", - "flavor": "chat", - "multimodal": true, - "input_cost_per_mil_tokens": 5.5, - "output_cost_per_mil_tokens": 27.5, - "input_cache_read_cost_per_mil_tokens": 0.55, - "input_cache_write_cost_per_mil_tokens": 6.875, - "displayName": "AU Claude Opus 5", + "displayName": "Claude Opus 4.8", "reasoning": true, "reasoning_budget": true, - "parent": "anthropic.claude-opus-5", "max_input_tokens": 1000000, "max_output_tokens": 128000, "available_providers": [ @@ -8762,57 +8689,6 @@ "bedrock" ] }, - "command-a-03-2025": { - "format": "openai", - "flavor": "chat", - "input_cost_per_mil_tokens": 2.5, - "output_cost_per_mil_tokens": 10, - "displayName": "Command A", - "max_input_tokens": 256000, - "max_output_tokens": 8000, - "available_providers": [ - "cohere" - ] - }, - "command-r-plus-08-2024": { - "format": "openai", - "flavor": "chat", - "input_cost_per_mil_tokens": 2.5, - "output_cost_per_mil_tokens": 10, - "displayName": "Command R+ (08-2024)", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "available_providers": [ - "cohere", - "openrouter" - ] - }, - "command-r-08-2024": { - "format": "openai", - "flavor": "chat", - "input_cost_per_mil_tokens": 0.15, - "output_cost_per_mil_tokens": 0.6, - "displayName": "Command R (08-2024)", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "available_providers": [ - "cohere", - "openrouter" - ] - }, - "command-r7b-12-2024": { - "format": "openai", - "flavor": "chat", - "input_cost_per_mil_tokens": 0.0375, - "output_cost_per_mil_tokens": 0.15, - "displayName": "Command R7B", - "max_input_tokens": 128000, - "max_output_tokens": 4096, - "available_providers": [ - "cohere", - "openrouter" - ] - }, "mistral.devstral-2-123b": { "format": "converse", "flavor": "chat", @@ -9483,25 +9359,205 @@ "bedrock" ] }, - "us.anthropic.claude-opus-4-8": { + "global.anthropic.claude-fable-5": { "format": "anthropic", "flavor": "chat", "multimodal": true, - "input_cost_per_mil_tokens": 5.5, - "output_cost_per_mil_tokens": 27.5, - "input_cache_read_cost_per_mil_tokens": 0.55, - "input_cache_write_cost_per_mil_tokens": 6.875, - "displayName": "US Claude 4.8 Opus", + "input_cost_per_mil_tokens": 10, + "output_cost_per_mil_tokens": 50, + "input_cache_read_cost_per_mil_tokens": 1, + "input_cache_write_cost_per_mil_tokens": 12.5, + "displayName": "Global Claude Fable 5", "reasoning": true, "reasoning_budget": true, - "parent": "anthropic.claude-opus-4-8", + "parent": "anthropic.claude-fable-5", "max_input_tokens": 1000000, "max_output_tokens": 128000, "available_providers": [ "bedrock" ] }, - "us.anthropic.claude-opus-4-7": { + "global.anthropic.claude-opus-5": { + "format": "anthropic", + "flavor": "chat", + "multimodal": true, + "input_cost_per_mil_tokens": 5, + "output_cost_per_mil_tokens": 25, + "input_cache_read_cost_per_mil_tokens": 0.5, + "input_cache_write_cost_per_mil_tokens": 6.25, + "displayName": "Global Claude Opus 5", + "reasoning": true, + "reasoning_budget": true, + "parent": "anthropic.claude-opus-5", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "available_providers": [ + "bedrock" + ] + }, + "global.anthropic.claude-opus-4-8": { + "format": "anthropic", + "flavor": "chat", + "multimodal": true, + "input_cost_per_mil_tokens": 5, + "output_cost_per_mil_tokens": 25, + "input_cache_read_cost_per_mil_tokens": 0.5, + "input_cache_write_cost_per_mil_tokens": 6.25, + "displayName": "Global Claude 4.8 Opus", + "reasoning": true, + "reasoning_budget": true, + "parent": "anthropic.claude-opus-4-8", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "available_providers": [ + "bedrock" + ] + }, + "global.anthropic.claude-opus-4-7": { + "format": "anthropic", + "flavor": "chat", + "multimodal": true, + "input_cost_per_mil_tokens": 5, + "output_cost_per_mil_tokens": 25, + "input_cache_read_cost_per_mil_tokens": 0.5, + "input_cache_write_cost_per_mil_tokens": 6.25, + "displayName": "Global Claude 4.7 Opus", + "reasoning": true, + "reasoning_budget": true, + "parent": "anthropic.claude-opus-4-7", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "available_providers": [ + "bedrock" + ] + }, + "global.anthropic.claude-opus-4-6-v1": { + "format": "anthropic", + "flavor": "chat", + "multimodal": true, + "input_cost_per_mil_tokens": 5, + "output_cost_per_mil_tokens": 25, + "input_cache_read_cost_per_mil_tokens": 0.5, + "input_cache_write_cost_per_mil_tokens": 6.25, + "displayName": "Global Claude 4.6 Opus", + "reasoning": true, + "reasoning_budget": true, + "parent": "anthropic.claude-opus-4-6-v1", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "available_providers": [ + "bedrock" + ] + }, + "global.anthropic.claude-sonnet-5": { + "format": "anthropic", + "flavor": "chat", + "multimodal": true, + "input_cost_per_mil_tokens": 3, + "output_cost_per_mil_tokens": 15, + "input_cache_read_cost_per_mil_tokens": 0.3, + "input_cache_write_cost_per_mil_tokens": 3.75, + "displayName": "Global Claude Sonnet 5", + "reasoning": true, + "reasoning_budget": true, + "parent": "anthropic.claude-sonnet-5", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "available_providers": [ + "bedrock" + ] + }, + "global.anthropic.claude-sonnet-4-6": { + "format": "anthropic", + "flavor": "chat", + "multimodal": true, + "input_cost_per_mil_tokens": 3, + "output_cost_per_mil_tokens": 15, + "input_cache_read_cost_per_mil_tokens": 0.3, + "input_cache_write_cost_per_mil_tokens": 3.75, + "displayName": "Global Claude 4.6 Sonnet", + "reasoning": true, + "reasoning_budget": true, + "parent": "anthropic.claude-sonnet-4-6", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "available_providers": [ + "bedrock" + ] + }, + "global.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "format": "anthropic", + "flavor": "chat", + "multimodal": true, + "input_cost_per_mil_tokens": 3, + "output_cost_per_mil_tokens": 15, + "input_cache_read_cost_per_mil_tokens": 0.3, + "input_cache_write_cost_per_mil_tokens": 3.75, + "displayName": "Global Claude 4.5 Sonnet", + "reasoning": true, + "reasoning_budget": true, + "parent": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "available_providers": [ + "bedrock" + ] + }, + "global.anthropic.claude-haiku-4-5-20251001-v1:0": { + "format": "anthropic", + "flavor": "chat", + "multimodal": true, + "input_cost_per_mil_tokens": 1, + "output_cost_per_mil_tokens": 5, + "input_cache_read_cost_per_mil_tokens": 0.1, + "input_cache_write_cost_per_mil_tokens": 1.25, + "displayName": "Global Claude 4.5 Haiku", + "reasoning": true, + "reasoning_budget": true, + "parent": "anthropic.claude-haiku-4-5-20251001-v1:0", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "available_providers": [ + "bedrock" + ] + }, + "us.anthropic.claude-opus-5": { + "format": "anthropic", + "flavor": "chat", + "multimodal": true, + "input_cost_per_mil_tokens": 5.5, + "output_cost_per_mil_tokens": 27.5, + "input_cache_read_cost_per_mil_tokens": 0.55, + "input_cache_write_cost_per_mil_tokens": 6.875, + "displayName": "US Claude Opus 5", + "reasoning": true, + "reasoning_budget": true, + "parent": "anthropic.claude-opus-5", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "available_providers": [ + "bedrock" + ] + }, + "us.anthropic.claude-opus-4-8": { + "format": "anthropic", + "flavor": "chat", + "multimodal": true, + "input_cost_per_mil_tokens": 5.5, + "output_cost_per_mil_tokens": 27.5, + "input_cache_read_cost_per_mil_tokens": 0.55, + "input_cache_write_cost_per_mil_tokens": 6.875, + "displayName": "US Claude 4.8 Opus", + "reasoning": true, + "reasoning_budget": true, + "parent": "anthropic.claude-opus-4-8", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "available_providers": [ + "bedrock" + ] + }, + "us.anthropic.claude-opus-4-7": { "format": "anthropic", "flavor": "chat", "multimodal": true, @@ -9907,146 +9963,112 @@ "bedrock" ] }, - "global.anthropic.claude-fable-5": { - "format": "anthropic", - "flavor": "chat", - "multimodal": true, - "input_cost_per_mil_tokens": 10, - "output_cost_per_mil_tokens": 50, - "input_cache_read_cost_per_mil_tokens": 1, - "input_cache_write_cost_per_mil_tokens": 12.5, - "displayName": "Global Claude Fable 5", - "reasoning": true, - "reasoning_budget": true, - "parent": "anthropic.claude-fable-5", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "available_providers": [ - "bedrock" - ] - }, - "global.anthropic.claude-opus-4-8": { + "eu.anthropic.claude-opus-5": { "format": "anthropic", "flavor": "chat", "multimodal": true, - "input_cost_per_mil_tokens": 5, - "output_cost_per_mil_tokens": 25, - "input_cache_read_cost_per_mil_tokens": 0.5, - "input_cache_write_cost_per_mil_tokens": 6.25, - "displayName": "Global Claude 4.8 Opus", + "input_cost_per_mil_tokens": 5.5, + "output_cost_per_mil_tokens": 27.5, + "input_cache_read_cost_per_mil_tokens": 0.55, + "input_cache_write_cost_per_mil_tokens": 6.875, + "displayName": "EU Claude Opus 5", "reasoning": true, "reasoning_budget": true, - "parent": "anthropic.claude-opus-4-8", + "parent": "anthropic.claude-opus-5", "max_input_tokens": 1000000, "max_output_tokens": 128000, "available_providers": [ "bedrock" ] }, - "global.anthropic.claude-opus-4-7": { + "eu.anthropic.claude-3-haiku-20240307-v1:0": { "format": "anthropic", "flavor": "chat", "multimodal": true, - "input_cost_per_mil_tokens": 5, - "output_cost_per_mil_tokens": 25, - "input_cache_read_cost_per_mil_tokens": 0.5, - "input_cache_write_cost_per_mil_tokens": 6.25, - "displayName": "Global Claude 4.7 Opus", - "reasoning": true, - "reasoning_budget": true, - "parent": "anthropic.claude-opus-4-7", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, + "input_cost_per_mil_tokens": 0.25, + "output_cost_per_mil_tokens": 1.25, + "input_cache_read_cost_per_mil_tokens": 0.025, + "input_cache_write_cost_per_mil_tokens": 0.3125, + "displayName": "EU Claude 3 Haiku", + "deprecated": true, + "deprecation_date": "2026-04-20", + "parent": "anthropic.claude-3-haiku-20240307-v1:0", + "max_input_tokens": 200000, + "max_output_tokens": 4096, "available_providers": [ "bedrock" ] }, - "global.anthropic.claude-opus-4-6-v1": { + "eu.anthropic.claude-3-sonnet-20240229-v1:0": { "format": "anthropic", "flavor": "chat", "multimodal": true, - "input_cost_per_mil_tokens": 5, - "output_cost_per_mil_tokens": 25, - "input_cache_read_cost_per_mil_tokens": 0.5, - "input_cache_write_cost_per_mil_tokens": 6.25, - "displayName": "Global Claude 4.6 Opus", - "reasoning": true, - "reasoning_budget": true, - "parent": "anthropic.claude-opus-4-6-v1", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, + "input_cost_per_mil_tokens": 3, + "output_cost_per_mil_tokens": 15, + "input_cache_read_cost_per_mil_tokens": 0.3, + "input_cache_write_cost_per_mil_tokens": 3.75, + "displayName": "EU Claude 3 Sonnet", + "deprecated": true, + "deprecation_date": "2025-07-21", + "parent": "anthropic.claude-3-sonnet-20240229-v1:0", + "max_input_tokens": 200000, + "max_output_tokens": 4096, "available_providers": [ "bedrock" ] }, - "global.anthropic.claude-sonnet-5": { - "format": "anthropic", + "eu.meta.llama3-2-3b-instruct-v1:0": { + "format": "converse", "flavor": "chat", - "multimodal": true, - "input_cost_per_mil_tokens": 3, - "output_cost_per_mil_tokens": 15, - "input_cache_read_cost_per_mil_tokens": 0.3, - "input_cache_write_cost_per_mil_tokens": 3.75, - "displayName": "Global Claude Sonnet 5", - "reasoning": true, - "reasoning_budget": true, - "parent": "anthropic.claude-sonnet-5", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, + "input_cost_per_mil_tokens": 0.19, + "output_cost_per_mil_tokens": 0.19, + "displayName": "EU Llama 3.2 3B Instruct", + "parent": "meta.llama3-2-3b-instruct-v1:0", + "max_input_tokens": 128000, + "max_output_tokens": 4096, "available_providers": [ "bedrock" ] }, - "global.anthropic.claude-sonnet-4-6": { - "format": "anthropic", + "eu.meta.llama3-2-1b-instruct-v1:0": { + "format": "converse", "flavor": "chat", - "multimodal": true, - "input_cost_per_mil_tokens": 3, - "output_cost_per_mil_tokens": 15, - "input_cache_read_cost_per_mil_tokens": 0.3, - "input_cache_write_cost_per_mil_tokens": 3.75, - "displayName": "Global Claude 4.6 Sonnet", - "reasoning": true, - "reasoning_budget": true, - "parent": "anthropic.claude-sonnet-4-6", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, + "input_cost_per_mil_tokens": 0.13, + "output_cost_per_mil_tokens": 0.13, + "displayName": "EU Llama 3.2 1B Instruct", + "parent": "meta.llama3-2-1b-instruct-v1:0", + "max_input_tokens": 128000, + "max_output_tokens": 4096, "available_providers": [ "bedrock" ] }, - "global.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "format": "anthropic", + "eu.mistral.pixtral-large-2502-v1:0": { + "format": "converse", "flavor": "chat", "multimodal": true, - "input_cost_per_mil_tokens": 3, - "output_cost_per_mil_tokens": 15, - "input_cache_read_cost_per_mil_tokens": 0.3, - "input_cache_write_cost_per_mil_tokens": 3.75, - "displayName": "Global Claude 4.5 Sonnet", - "reasoning": true, - "reasoning_budget": true, - "parent": "anthropic.claude-sonnet-4-5-20250929-v1:0", - "max_input_tokens": 200000, - "max_output_tokens": 64000, + "displayName": "EU Pixtral Large (2502)", + "parent": "mistral.pixtral-large-2502-v1:0", + "max_input_tokens": 128000, + "max_output_tokens": 16000, "available_providers": [ "bedrock" ] }, - "global.anthropic.claude-haiku-4-5-20251001-v1:0": { + "au.anthropic.claude-opus-5": { "format": "anthropic", "flavor": "chat", "multimodal": true, - "input_cost_per_mil_tokens": 1, - "output_cost_per_mil_tokens": 5, - "input_cache_read_cost_per_mil_tokens": 0.1, - "input_cache_write_cost_per_mil_tokens": 1.25, - "displayName": "Global Claude 4.5 Haiku", + "input_cost_per_mil_tokens": 5.5, + "output_cost_per_mil_tokens": 27.5, + "input_cache_read_cost_per_mil_tokens": 0.55, + "input_cache_write_cost_per_mil_tokens": 6.875, + "displayName": "AU Claude Opus 5", "reasoning": true, "reasoning_budget": true, - "parent": "anthropic.claude-haiku-4-5-20251001-v1:0", - "max_input_tokens": 200000, - "max_output_tokens": 64000, + "parent": "anthropic.claude-opus-5", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, "available_providers": [ "bedrock" ] @@ -10119,78 +10141,55 @@ "bedrock" ] }, - "eu.anthropic.claude-3-haiku-20240307-v1:0": { - "format": "anthropic", - "flavor": "chat", - "multimodal": true, - "input_cost_per_mil_tokens": 0.25, - "output_cost_per_mil_tokens": 1.25, - "input_cache_read_cost_per_mil_tokens": 0.025, - "input_cache_write_cost_per_mil_tokens": 0.3125, - "displayName": "EU Claude 3 Haiku", - "deprecated": true, - "deprecation_date": "2026-04-20", - "parent": "anthropic.claude-3-haiku-20240307-v1:0", - "max_input_tokens": 200000, - "max_output_tokens": 4096, - "available_providers": [ - "bedrock" - ] - }, - "eu.anthropic.claude-3-sonnet-20240229-v1:0": { - "format": "anthropic", + "command-a-03-2025": { + "format": "openai", "flavor": "chat", - "multimodal": true, - "input_cost_per_mil_tokens": 3, - "output_cost_per_mil_tokens": 15, - "input_cache_read_cost_per_mil_tokens": 0.3, - "input_cache_write_cost_per_mil_tokens": 3.75, - "displayName": "EU Claude 3 Sonnet", - "deprecated": true, - "deprecation_date": "2025-07-21", - "parent": "anthropic.claude-3-sonnet-20240229-v1:0", - "max_input_tokens": 200000, - "max_output_tokens": 4096, + "input_cost_per_mil_tokens": 2.5, + "output_cost_per_mil_tokens": 10, + "displayName": "Command A", + "max_input_tokens": 256000, + "max_output_tokens": 8000, "available_providers": [ - "bedrock" + "cohere" ] }, - "eu.meta.llama3-2-3b-instruct-v1:0": { - "format": "converse", + "command-r-plus-08-2024": { + "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.19, - "output_cost_per_mil_tokens": 0.19, - "displayName": "EU Llama 3.2 3B Instruct", - "parent": "meta.llama3-2-3b-instruct-v1:0", + "input_cost_per_mil_tokens": 2.5, + "output_cost_per_mil_tokens": 10, + "displayName": "Command R+ (08-2024)", "max_input_tokens": 128000, "max_output_tokens": 4096, "available_providers": [ - "bedrock" + "cohere", + "openrouter" ] }, - "eu.meta.llama3-2-1b-instruct-v1:0": { - "format": "converse", + "command-r-08-2024": { + "format": "openai", "flavor": "chat", - "input_cost_per_mil_tokens": 0.13, - "output_cost_per_mil_tokens": 0.13, - "displayName": "EU Llama 3.2 1B Instruct", - "parent": "meta.llama3-2-1b-instruct-v1:0", + "input_cost_per_mil_tokens": 0.15, + "output_cost_per_mil_tokens": 0.6, + "displayName": "Command R (08-2024)", "max_input_tokens": 128000, "max_output_tokens": 4096, "available_providers": [ - "bedrock" + "cohere", + "openrouter" ] }, - "eu.mistral.pixtral-large-2502-v1:0": { - "format": "converse", + "command-r7b-12-2024": { + "format": "openai", "flavor": "chat", - "multimodal": true, - "displayName": "EU Pixtral Large (2502)", - "parent": "mistral.pixtral-large-2502-v1:0", + "input_cost_per_mil_tokens": 0.0375, + "output_cost_per_mil_tokens": 0.15, + "displayName": "Command R7B", "max_input_tokens": 128000, - "max_output_tokens": 16000, + "max_output_tokens": 4096, "available_providers": [ - "bedrock" + "cohere", + "openrouter" ] }, "deepseek-ai/DeepSeek-V4-Pro": { @@ -10641,7 +10640,7 @@ "flavor": "chat", "input_cost_per_mil_tokens": 1.4, "output_cost_per_mil_tokens": 4.4, - "input_cache_read_cost_per_mil_tokens": 0.26, + "input_cache_read_cost_per_mil_tokens": 0.14, "displayName": "GLM 5.2", "reasoning": true, "max_input_tokens": 262144, @@ -10651,6 +10650,20 @@ "together" ] }, + "zai-org/GLM-5.2-Fast": { + "format": "openai", + "flavor": "chat", + "input_cost_per_mil_tokens": 2.1, + "output_cost_per_mil_tokens": 6.6, + "input_cache_read_cost_per_mil_tokens": 0.21, + "displayName": "GLM 5.2 Fast", + "reasoning": true, + "parent": "zai-org/GLM-5.2", + "max_input_tokens": 524288, + "available_providers": [ + "baseten" + ] + }, "zai-org/GLM-5.1": { "format": "openai", "flavor": "chat", @@ -10733,6 +10746,20 @@ "baseten" ] }, + "thinkingmachines/inkling": { + "format": "openai", + "flavor": "chat", + "multimodal": true, + "input_cost_per_mil_tokens": 1, + "output_cost_per_mil_tokens": 4.05, + "input_cache_read_cost_per_mil_tokens": 0.17, + "displayName": "Inkling", + "reasoning": true, + "max_input_tokens": 1048576, + "available_providers": [ + "baseten" + ] + }, "mistral-large-latest": { "format": "openai", "flavor": "chat", @@ -11207,18 +11234,18 @@ "mistral" ] }, - "gemini-3.5-flash": { + "gemini-3.6-flash": { "format": "google", "flavor": "chat", "multimodal": true, "input_cost_per_mil_tokens": 1.5, - "output_cost_per_mil_tokens": 9, + "output_cost_per_mil_tokens": 7.5, "input_cache_read_cost_per_mil_tokens": 0.15, - "displayName": "Gemini 3.5 Flash", + "displayName": "Gemini 3.6 Flash", "reasoning": true, "reasoning_budget": true, "fallback_models": [ - "publishers/google/models/gemini-3.5-flash" + "publishers/google/models/gemini-3.6-flash" ], "max_input_tokens": 1048576, "max_output_tokens": 65536, @@ -11227,18 +11254,18 @@ "vertex" ] }, - "gemini-3.6-flash": { + "gemini-3.5-flash": { "format": "google", "flavor": "chat", "multimodal": true, "input_cost_per_mil_tokens": 1.5, - "output_cost_per_mil_tokens": 7.5, + "output_cost_per_mil_tokens": 9, "input_cache_read_cost_per_mil_tokens": 0.15, - "displayName": "Gemini 3.6 Flash", + "displayName": "Gemini 3.5 Flash", "reasoning": true, "reasoning_budget": true, "fallback_models": [ - "publishers/google/models/gemini-3.6-flash" + "publishers/google/models/gemini-3.5-flash" ], "max_input_tokens": 1048576, "max_output_tokens": 65536, @@ -12721,19 +12748,5 @@ "available_providers": [ "databricks" ] - }, - "thinkingmachines/inkling": { - "format": "openai", - "flavor": "chat", - "multimodal": true, - "input_cost_per_mil_tokens": 1, - "output_cost_per_mil_tokens": 4.05, - "input_cache_read_cost_per_mil_tokens": 0.17, - "displayName": "Inkling", - "reasoning": true, - "max_input_tokens": 1048576, - "available_providers": [ - "baseten" - ] } }