diff --git a/plugin-server/src/ingestion/ai-costs/providers/canonical-providers.ts b/plugin-server/src/ingestion/ai-costs/providers/canonical-providers.ts index 30c49bdb78..0644f2c900 100644 --- a/plugin-server/src/ingestion/ai-costs/providers/canonical-providers.ts +++ b/plugin-server/src/ingestion/ai-costs/providers/canonical-providers.ts @@ -1,5 +1,5 @@ // Auto-generated from OpenRouter API - Do not edit manually -// Generated at: 2025-11-10 10:03:38 UTC +// Generated at: 2025-11-11 10:03:37 UTC export type CanonicalProvider = | 'default' @@ -89,6 +89,8 @@ export type CanonicalProvider = | 'parasail-bf16' | 'parasail-fp4' | 'parasail-fp8' + | 'parasail-int4' + | 'parasail-int8' | 'perplexity' | 'phala' | 'relace-fp8' diff --git a/plugin-server/src/ingestion/ai-costs/providers/llm-costs.json b/plugin-server/src/ingestion/ai-costs/providers/llm-costs.json index 67b8829fe3..f528eb2e4e 100644 --- a/plugin-server/src/ingestion/ai-costs/providers/llm-costs.json +++ b/plugin-server/src/ingestion/ai-costs/providers/llm-costs.json @@ -350,13 +350,6 @@ "prompt_token": 0.000003, "completion_token": 0.000015, "image": 0.0048 - }, - "google-vertex": { - "prompt_token": 0.000003, - "completion_token": 0.000015, - "cache_read_token": 3e-7, - "cache_write_token": 0.00000375, - "image": 0.0048 } } }, @@ -2275,12 +2268,8 @@ "model": "meta-llama/llama-3.1-405b-instruct", "cost": { "default": { - "prompt_token": 8e-7, - "completion_token": 8e-7 - }, - "deepinfra-fp8": { - "prompt_token": 8e-7, - "completion_token": 8e-7 + "prompt_token": 0.0000035, + "completion_token": 0.0000035 }, "google-vertex": { "prompt_token": 0.000005, @@ -2406,16 +2395,12 @@ "model": "meta-llama/llama-3.2-1b-instruct", "cost": { "default": { - "prompt_token": 5e-9, - "completion_token": 1e-8 + "prompt_token": 2.7e-8, + "completion_token": 2e-7 }, "cloudflare": { "prompt_token": 2.7e-8, "completion_token": 2e-7 - }, - "deepinfra-bf16": { - "prompt_token": 5e-9, - "completion_token": 1e-8 } } }, @@ -2540,7 +2525,7 @@ "prompt_token": 1.3e-7, "completion_token": 3.9e-7 }, - "parasail-fp8": { + "parasail-int8": { "prompt_token": 1.5e-7, "completion_token": 5e-7 }, @@ -2613,10 +2598,6 @@ "completion_token": 6e-7, "image": 0.0006684 }, - "deepinfra-turbo": { - "prompt_token": 5e-7, - "completion_token": 5e-7 - }, "friendli": { "prompt_token": 2e-7, "completion_token": 6e-7 @@ -2957,6 +2938,14 @@ "prompt_token": 3e-7, "completion_token": 0.0000012 }, + "gmicloud-fp8": { + "prompt_token": 3e-7, + "completion_token": 0.0000012 + }, + "google-vertex": { + "prompt_token": 3e-7, + "completion_token": 1.2e-7 + }, "minimax": { "prompt_token": 2.55e-7, "completion_token": 0.00000102 @@ -2978,10 +2967,6 @@ "prompt_token": 0, "completion_token": 0 }, - "gmicloud-fp8": { - "prompt_token": 0, - "completion_token": 0 - }, "minimax": { "prompt_token": 0, "completion_token": 0 @@ -3177,12 +3162,8 @@ "model": "mistralai/mistral-7b-instruct-v0.3", "cost": { "default": { - "prompt_token": 2.8e-8, - "completion_token": 5.4e-8 - }, - "deepinfra-bf16": { - "prompt_token": 2.8e-8, - "completion_token": 5.4e-8 + "prompt_token": 2e-7, + "completion_token": 2e-7 }, "together": { "prompt_token": 2e-7, @@ -3633,9 +3614,9 @@ "cache_read_token": 1.5e-7 }, "moonshotai-turbo": { - "prompt_token": 0.0000024, - "completion_token": 0.00001, - "cache_read_token": 6e-7 + "prompt_token": 0.00000115, + "completion_token": 0.000008, + "cache_read_token": 1.5e-7 }, "novita-fp8": { "prompt_token": 6e-7, @@ -3671,8 +3652,9 @@ "completion_token": 0.0000025 }, "moonshotai-turbo": { - "prompt_token": 0.0000024, - "completion_token": 0.00001 + "prompt_token": 0.00000115, + "completion_token": 0.000008, + "cache_read_token": 1.5e-7 } } }, @@ -3699,7 +3681,7 @@ "completion_token": 0.0000025, "cache_read_token": 1.5e-7 }, - "parasail-fp4": { + "parasail-int4": { "prompt_token": 6e-7, "completion_token": 0.0000025 } @@ -4611,8 +4593,8 @@ "completion_token": 2.8e-7 }, "google-vertex": { - "prompt_token": 1.5e-7, - "completion_token": 6e-7 + "prompt_token": 9e-8, + "completion_token": 3.6e-7 }, "groq": { "prompt_token": 1.5e-7, @@ -4702,8 +4684,8 @@ "completion_token": 3e-7 }, "google-vertex": { - "prompt_token": 7.5e-8, - "completion_token": 3e-7 + "prompt_token": 7e-8, + "completion_token": 2.5e-7 }, "groq": { "prompt_token": 7.5e-8,