diff --git a/proxy/internal/llm/pricing/defaults_coverage_test.go b/proxy/internal/llm/pricing/defaults_coverage_test.go index be23682da..8df1557ea 100644 --- a/proxy/internal/llm/pricing/defaults_coverage_test.go +++ b/proxy/internal/llm/pricing/defaults_coverage_test.go @@ -28,12 +28,12 @@ func TestDefaultTable_FirstPartyModelCoverage(t *testing.T) { "ministral-8b-latest", "mistral-embed", }, "anthropic": { - "claude-fable-5", "claude-opus-4-8", "claude-opus-4-7", "claude-opus-4-6", + "claude-fable-5", "claude-opus-5", "claude-opus-4-8", "claude-opus-4-7", "claude-opus-4-6", "claude-opus-4-1", "claude-sonnet-4-6", "claude-sonnet-4-5", "claude-haiku-4-5", }, // bedrock keys are the normalized ids the request parser emits. "bedrock": { - "anthropic.claude-opus-4-8", "anthropic.claude-opus-4-7", "anthropic.claude-opus-4-6", + "anthropic.claude-opus-5", "anthropic.claude-opus-4-8", "anthropic.claude-opus-4-7", "anthropic.claude-opus-4-6", "anthropic.claude-opus-4-1", "anthropic.claude-sonnet-4-6", "anthropic.claude-sonnet-4-5", "anthropic.claude-haiku-4-5", "meta.llama3-3-70b-instruct", "amazon.nova-pro", "amazon.nova-lite", "amazon.nova-micro", "amazon.nova-2-lite", diff --git a/proxy/internal/llm/pricing/defaults_pricing.yaml b/proxy/internal/llm/pricing/defaults_pricing.yaml index 3fba8fe3f..988426105 100644 --- a/proxy/internal/llm/pricing/defaults_pricing.yaml +++ b/proxy/internal/llm/pricing/defaults_pricing.yaml @@ -180,6 +180,11 @@ anthropic: output_per_1k: 0.050 cache_read_per_1k: 0.001 cache_creation_per_1k: 0.0125 + claude-opus-5: + input_per_1k: 0.005 + output_per_1k: 0.025 + cache_read_per_1k: 0.0005 + cache_creation_per_1k: 0.00625 claude-opus-4-8: input_per_1k: 0.005 output_per_1k: 0.025 @@ -236,6 +241,11 @@ bedrock: # eu.anthropic.claude-sonnet-4-5-20250929-v1:0 -> anthropic.claude-sonnet-4-5. # Anthropic-on-Bedrock keeps the additive cache buckets (read ≈0.1x input, # write ≈1.25x input); Nova / Llama report no cache, so cost is input+output. + anthropic.claude-opus-5: + input_per_1k: 0.005 + output_per_1k: 0.025 + cache_read_per_1k: 0.0005 + cache_creation_per_1k: 0.00625 anthropic.claude-opus-4-8: input_per_1k: 0.005 output_per_1k: 0.025