ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: align claude 4.6 pricing tests

Browse Source
This commit is contained in:
Chesars 2026-03-23 14:23:29 -03:00
parent fef4392fb3
commit da0c6c14bb
4 changed files with 155 additions and 119 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

89
litellm/model_prices_and_context_window_backup.json
View File

@ -1760,7 +1760,7 @@
"input_cost_per_token": 5e-06,
"output_cost_per_token": 2.5e-05,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -1831,7 +1831,7 @@
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
@ -8498,18 +8498,18 @@
},
"claude-sonnet-4-6": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
"cache_creation_input_token_cost_above_200k_tokens": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
"cache_read_input_token_cost_above_200k_tokens": 3e-07,
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"input_cost_per_token_above_200k_tokens": 3e-06,
"litellm_provider": "anthropic",
"max_input_tokens": 200000,
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
"output_cost_per_token_above_200k_tokens": 1.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -8690,19 +8690,19 @@
},
"claude-opus-4-6": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_creation_input_token_cost_above_200k_tokens": 6.25e-06,
"cache_creation_input_token_cost_above_1hr": 1e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"cache_read_input_token_cost_above_200k_tokens": 5e-07,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"input_cost_per_token_above_200k_tokens": 5e-06,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"output_cost_per_token_above_200k_tokens": 3.75e-05,
"output_cost_per_token_above_200k_tokens": 2.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -8725,19 +8725,19 @@
},
"claude-opus-4-6-20260205": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_creation_input_token_cost_above_200k_tokens": 6.25e-06,
"cache_creation_input_token_cost_above_1hr": 1e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"cache_read_input_token_cost_above_200k_tokens": 5e-07,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"input_cost_per_token_above_200k_tokens": 5e-06,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"output_cost_per_token_above_200k_tokens": 3.75e-05,
"output_cost_per_token_above_200k_tokens": 2.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -14599,17 +14599,14 @@
"uses_embed_content": true
},
"vertex_ai/gemini-embedding-2-preview": {
"input_cost_per_audio_per_second": 0.00016,
"input_cost_per_image": 0.00012,
"input_cost_per_token": 2e-07,
"input_cost_per_video_per_second": 0.00079,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
"supports_multimodal": true,
"uses_embed_content": true
},
@ -14626,18 +14623,6 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"uses_embed_content": true
},
"vertex_ai/gemini-embedding-2-preview": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
"supports_multimodal": true,
"uses_embed_content": true
},
"gemini/gemini-embedding-001": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "gemini",
@ -30192,18 +30177,18 @@
},
"vertex_ai/claude-opus-4-6": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_creation_input_token_cost_above_200k_tokens": 6.25e-06,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"cache_read_input_token_cost_above_200k_tokens": 5e-07,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"input_cost_per_token_above_200k_tokens": 5e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"output_cost_per_token_above_200k_tokens": 3.75e-05,
"output_cost_per_token_above_200k_tokens": 2.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -30222,18 +30207,18 @@
},
"vertex_ai/claude-opus-4-6@default": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_creation_input_token_cost_above_200k_tokens": 6.25e-06,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"cache_read_input_token_cost_above_200k_tokens": 5e-07,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"input_cost_per_token_above_200k_tokens": 5e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"output_cost_per_token_above_200k_tokens": 3.75e-05,
"output_cost_per_token_above_200k_tokens": 2.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -30278,18 +30263,18 @@
},
"vertex_ai/claude-sonnet-4-6": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
"cache_creation_input_token_cost_above_200k_tokens": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
"cache_read_input_token_cost_above_200k_tokens": 3e-07,
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"input_cost_per_token_above_200k_tokens": 3e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
"output_cost_per_token_above_200k_tokens": 1.5e-05,
"supports_assistant_prefill": true,
"supports_computer_use": true,
"supports_function_calling": true,
@ -31013,7 +30998,9 @@
"mode": "chat",
"output_cost_per_token": 3.2e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models",
"supported_regions": ["global"],
"supported_regions": [
"global"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
@ -37015,18 +37002,18 @@
},
"vertex_ai/claude-sonnet-4-6@default": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
"cache_creation_input_token_cost_above_200k_tokens": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
"cache_read_input_token_cost_above_200k_tokens": 3e-07,
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"input_cost_per_token_above_200k_tokens": 3e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
"output_cost_per_token_above_200k_tokens": 1.5e-05,
"supports_assistant_prefill": true,
"supports_computer_use": true,
"supports_function_calling": true,

89
model_prices_and_context_window.json
View File

@ -1760,7 +1760,7 @@
"input_cost_per_token": 5e-06,
"output_cost_per_token": 2.5e-05,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
@ -1831,7 +1831,7 @@
"cache_read_input_token_cost": 3e-07,
"input_cost_per_token": 3e-06,
"litellm_provider": "azure_ai",
"max_input_tokens": 200000,
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
@ -8498,18 +8498,18 @@
},
"claude-sonnet-4-6": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
"cache_creation_input_token_cost_above_200k_tokens": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
"cache_read_input_token_cost_above_200k_tokens": 3e-07,
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"input_cost_per_token_above_200k_tokens": 3e-06,
"litellm_provider": "anthropic",
"max_input_tokens": 200000,
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
"output_cost_per_token_above_200k_tokens": 1.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -8690,19 +8690,19 @@
},
"claude-opus-4-6": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_creation_input_token_cost_above_200k_tokens": 6.25e-06,
"cache_creation_input_token_cost_above_1hr": 1e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"cache_read_input_token_cost_above_200k_tokens": 5e-07,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"input_cost_per_token_above_200k_tokens": 5e-06,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"output_cost_per_token_above_200k_tokens": 3.75e-05,
"output_cost_per_token_above_200k_tokens": 2.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -8725,19 +8725,19 @@
},
"claude-opus-4-6-20260205": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_creation_input_token_cost_above_200k_tokens": 6.25e-06,
"cache_creation_input_token_cost_above_1hr": 1e-05,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"cache_read_input_token_cost_above_200k_tokens": 5e-07,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"input_cost_per_token_above_200k_tokens": 5e-06,
"litellm_provider": "anthropic",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"output_cost_per_token_above_200k_tokens": 3.75e-05,
"output_cost_per_token_above_200k_tokens": 2.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -14599,17 +14599,14 @@
"uses_embed_content": true
},
"vertex_ai/gemini-embedding-2-preview": {
"input_cost_per_audio_per_second": 0.00016,
"input_cost_per_image": 0.00012,
"input_cost_per_token": 2e-07,
"input_cost_per_video_per_second": 0.00079,
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
"supports_multimodal": true,
"uses_embed_content": true
},
@ -14626,18 +14623,6 @@
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
"uses_embed_content": true
},
"vertex_ai/gemini-embedding-2-preview": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "vertex_ai",
"max_input_tokens": 8192,
"max_tokens": 8192,
"mode": "embedding",
"output_cost_per_token": 0,
"output_vector_size": 3072,
"source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
"supports_multimodal": true,
"uses_embed_content": true
},
"gemini/gemini-embedding-001": {
"input_cost_per_token": 1.5e-07,
"litellm_provider": "gemini",
@ -30192,18 +30177,18 @@
},
"vertex_ai/claude-opus-4-6": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_creation_input_token_cost_above_200k_tokens": 6.25e-06,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"cache_read_input_token_cost_above_200k_tokens": 5e-07,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"input_cost_per_token_above_200k_tokens": 5e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"output_cost_per_token_above_200k_tokens": 3.75e-05,
"output_cost_per_token_above_200k_tokens": 2.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -30222,18 +30207,18 @@
},
"vertex_ai/claude-opus-4-6@default": {
"cache_creation_input_token_cost": 6.25e-06,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_creation_input_token_cost_above_200k_tokens": 6.25e-06,
"cache_read_input_token_cost": 5e-07,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"cache_read_input_token_cost_above_200k_tokens": 5e-07,
"input_cost_per_token": 5e-06,
"input_cost_per_token_above_200k_tokens": 1e-05,
"input_cost_per_token_above_200k_tokens": 5e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 2.5e-05,
"output_cost_per_token_above_200k_tokens": 3.75e-05,
"output_cost_per_token_above_200k_tokens": 2.5e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
@ -30278,18 +30263,18 @@
},
"vertex_ai/claude-sonnet-4-6": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
"cache_creation_input_token_cost_above_200k_tokens": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
"cache_read_input_token_cost_above_200k_tokens": 3e-07,
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"input_cost_per_token_above_200k_tokens": 3e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
"output_cost_per_token_above_200k_tokens": 1.5e-05,
"supports_assistant_prefill": true,
"supports_computer_use": true,
"supports_function_calling": true,
@ -31013,7 +30998,9 @@
"mode": "chat",
"output_cost_per_token": 3.2e-06,
"source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models",
"supported_regions": ["global"],
"supported_regions": [
"global"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
@ -37015,18 +37002,18 @@
},
"vertex_ai/claude-sonnet-4-6@default": {
"cache_creation_input_token_cost": 3.75e-06,
"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,
"cache_creation_input_token_cost_above_200k_tokens": 3.75e-06,
"cache_read_input_token_cost": 3e-07,
"cache_read_input_token_cost_above_200k_tokens": 6e-07,
"cache_read_input_token_cost_above_200k_tokens": 3e-07,
"input_cost_per_token": 3e-06,
"input_cost_per_token_above_200k_tokens": 6e-06,
"input_cost_per_token_above_200k_tokens": 3e-06,
"litellm_provider": "vertex_ai-anthropic_models",
"max_input_tokens": 200000,
"max_input_tokens": 1000000,
"max_output_tokens": 64000,
"max_tokens": 64000,
"mode": "chat",
"output_cost_per_token": 1.5e-05,
"output_cost_per_token_above_200k_tokens": 2.25e-05,
"output_cost_per_token_above_200k_tokens": 1.5e-05,
"supports_assistant_prefill": true,
"supports_computer_use": true,
"supports_function_calling": true,

30
tests/test_litellm/test_claude_opus_4_6_config.py
View File

@ -72,29 +72,26 @@ def test_opus_4_6_model_pricing_and_capabilities():
"has_long_context_pricing": True,
"tool_use_system_prompt_tokens": 346,
"max_input_tokens": 1000000,
# Anthropic direct API charges 2x for >200k tokens
"input_cost_per_token_above_200k_tokens": 1e-05,
"output_cost_per_token_above_200k_tokens": 3.75e-05,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"input_cost_per_token_above_200k_tokens": 5e-06,
"output_cost_per_token_above_200k_tokens": 2.5e-05,
"cache_creation_input_token_cost_above_200k_tokens": 6.25e-06,
"cache_read_input_token_cost_above_200k_tokens": 5e-07,
},
"claude-opus-4-6-20260205": {
"provider": "anthropic",
"has_long_context_pricing": True,
"tool_use_system_prompt_tokens": 346,
"max_input_tokens": 1000000,
# Anthropic direct API charges 2x for >200k tokens
"input_cost_per_token_above_200k_tokens": 1e-05,
"output_cost_per_token_above_200k_tokens": 3.75e-05,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"input_cost_per_token_above_200k_tokens": 5e-06,
"output_cost_per_token_above_200k_tokens": 2.5e-05,
"cache_creation_input_token_cost_above_200k_tokens": 6.25e-06,
"cache_read_input_token_cost_above_200k_tokens": 5e-07,
},
"anthropic.claude-opus-4-6-v1": {
"provider": "bedrock_converse",
"has_long_context_pricing": True,
"tool_use_system_prompt_tokens": 346,
"max_input_tokens": 1000000,
# Bedrock does not surcharge for >200k tokens
"input_cost_per_token_above_200k_tokens": 5e-06,
"output_cost_per_token_above_200k_tokens": 2.5e-05,
"cache_creation_input_token_cost_above_200k_tokens": 6.25e-06,
@ -105,17 +102,16 @@ def test_opus_4_6_model_pricing_and_capabilities():
"has_long_context_pricing": True,
"tool_use_system_prompt_tokens": 346,
"max_input_tokens": 1000000,
# Vertex AI charges 2x for >200k tokens
"input_cost_per_token_above_200k_tokens": 1e-05,
"output_cost_per_token_above_200k_tokens": 3.75e-05,
"cache_creation_input_token_cost_above_200k_tokens": 1.25e-05,
"cache_read_input_token_cost_above_200k_tokens": 1e-06,
"input_cost_per_token_above_200k_tokens": 5e-06,
"output_cost_per_token_above_200k_tokens": 2.5e-05,
"cache_creation_input_token_cost_above_200k_tokens": 6.25e-06,
"cache_read_input_token_cost_above_200k_tokens": 5e-07,
},
"azure_ai/claude-opus-4-6": {
"provider": "azure_ai",
"has_long_context_pricing": False,
"tool_use_system_prompt_tokens": 159,
"max_input_tokens": 200000,
"max_input_tokens": 1000000,
},
}

66
tests/test_litellm/test_claude_sonnet_4_6_config.py
View File

@ -8,6 +8,72 @@ import os
import litellm
def test_sonnet_4_6_model_pricing_and_capabilities():
json_path = os.path.join(os.path.dirname(__file__), "../../model_prices_and_context_window.json")
with open(json_path) as f:
model_data = json.load(f)
expected_models = {
"claude-sonnet-4-6": {
"provider": "anthropic",
"has_long_context_pricing": True,
"tool_use_system_prompt_tokens": 346,
"max_input_tokens": 1000000,
"input_cost_per_token_above_200k_tokens": 3e-06,
"output_cost_per_token_above_200k_tokens": 1.5e-05,
"cache_creation_input_token_cost_above_200k_tokens": 3.75e-06,
"cache_read_input_token_cost_above_200k_tokens": 3e-07,
},
"vertex_ai/claude-sonnet-4-6": {
"provider": "vertex_ai-anthropic_models",
"has_long_context_pricing": True,
"tool_use_system_prompt_tokens": 346,
"max_input_tokens": 1000000,
"input_cost_per_token_above_200k_tokens": 3e-06,
"output_cost_per_token_above_200k_tokens": 1.5e-05,
"cache_creation_input_token_cost_above_200k_tokens": 3.75e-06,
"cache_read_input_token_cost_above_200k_tokens": 3e-07,
},
"azure_ai/claude-sonnet-4-6": {
"provider": "azure_ai",
"has_long_context_pricing": False,
"tool_use_system_prompt_tokens": None,
"max_input_tokens": 1000000,
},
}
for model_name, config in expected_models.items():
assert model_name in model_data, f"Missing model entry: {model_name}"
info = model_data[model_name]
assert info["litellm_provider"] == config["provider"]
assert info["mode"] == "chat"
assert info["max_input_tokens"] == config["max_input_tokens"]
assert info["max_output_tokens"] == 64000
assert info["max_tokens"] == 64000
assert info["input_cost_per_token"] == 3e-06
assert info["output_cost_per_token"] == 1.5e-05
assert info["cache_creation_input_token_cost"] == 3.75e-06
assert info["cache_read_input_token_cost"] == 3e-07
if config["has_long_context_pricing"]:
assert info["input_cost_per_token_above_200k_tokens"] == config["input_cost_per_token_above_200k_tokens"]
assert info["output_cost_per_token_above_200k_tokens"] == config["output_cost_per_token_above_200k_tokens"]
assert info["cache_creation_input_token_cost_above_200k_tokens"] == config["cache_creation_input_token_cost_above_200k_tokens"]
assert info["cache_read_input_token_cost_above_200k_tokens"] == config["cache_read_input_token_cost_above_200k_tokens"]
assert info["supports_assistant_prefill"] is True
assert info["supports_function_calling"] is True
assert info["supports_prompt_caching"] is True
assert info["supports_reasoning"] is True
assert info["supports_tool_choice"] is True
assert info["supports_vision"] is True
if config["tool_use_system_prompt_tokens"] is not None:
assert info["tool_use_system_prompt_tokens"] == config["tool_use_system_prompt_tokens"]
def test_sonnet_4_6_bedrock_regional_model_pricing():
"""
Validate that Bedrock Claude Sonnet 4.6 regional models have correct pricing.