From 80221911cd85446846455fddb3a4f28f8b56b1b2 Mon Sep 17 00:00:00 2001 From: "berriai-litellm-provider-info-sync[bot]" <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 21:29:36 -0700 Subject: [PATCH] chore(prices): sync Vertex AI prices: 2 models, 2 new [enrichment failed: Vertex AI, 224 held] (#42589) * chore(prices): sync Vertex AI prices: 2 models, 2 new [enrichment failed: Vertex AI, 224 held] vertex_ai/gemini-2.0-flash: input_cost_per_token, output_cost_per_token, input_cost_per_character, input_cost_per_audio_token, input_cost_per_token_batches, output_cost_per_token_batches, input_cost_per_audio_token_batches vertex_ai/gemini-2.0-flash-lite: input_cost_per_token, output_cost_per_token, input_cost_per_character, input_cost_per_audio_token, input_cost_per_token_batches, output_cost_per_token_batches, input_cost_per_audio_token_batches * chore(prices): sync Vertex AI prices: 52 models vertex_ai/claude-fable-5: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-fable-5@default: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-fable-5-1: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-fable-5-1@default: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-haiku-4-5: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-haiku-4-5@20251001: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-opus-4-5: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-opus-4-5@20251101: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-opus-4-6: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-opus-4-6@default: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-opus-4-7: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-opus-4-7@default: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-opus-4-8: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-opus-4-8@default: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-opus-5: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-opus-5@default: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-opus-5-5: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-opus-5-5@default: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-sonnet-4-5: cache_read_input_token_cost_batches vertex_ai/claude-sonnet-4-5@20250929: cache_read_input_token_cost_batches vertex_ai/claude-sonnet-4-6: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-sonnet-4-6@default: input_cost_per_token_batches, output_cost_per_token_batches, cache_read_input_token_cost_batches, cache_creation_input_token_cost_batches vertex_ai/claude-sonnet-5: input_cost_per_token_batches, output_cost_per_token_batches vertex_ai/claude-sonnet-5@default: input_cost_per_token_batches, output_cost_per_token_batches vertex_ai/codestral-2: vertex_ai/codestral-2@001: vertex_ai/deepseek-ai/deepseek-ocr-maas: vertex_ai/deepseek-ai/deepseek-r1-0528-maas: input_cost_per_token_batches, output_cost_per_token_batches vertex_ai/deepseek-ai/deepseek-v3.1-maas: cache_read_input_token_cost, input_cost_per_token_batches, output_cost_per_token_batches vertex_ai/deepseek-ai/deepseek-v3.2-maas: cache_read_input_token_cost vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas: input_cost_per_token_batches, output_cost_per_token_batches vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas: input_cost_per_token_batches, output_cost_per_token_batches vertex_ai/minimaxai/minimax-m2-maas: cache_read_input_token_cost vertex_ai/mistral-medium-3: vertex_ai/mistral-medium-3@001: vertex_ai/mistral-small-2503: vertex_ai/mistral-small-2503@001: vertex_ai/mistralai/codestral-2: vertex_ai/mistralai/codestral-2@001: vertex_ai/mistralai/mistral-medium-3: vertex_ai/mistralai/mistral-medium-3@001: vertex_ai/moonshotai/kimi-k2-thinking-maas: cache_read_input_token_cost vertex_ai/openai/gpt-oss-120b-maas: input_cost_per_token_batches, output_cost_per_token_batches vertex_ai/openai/gpt-oss-20b-maas: input_cost_per_token_batches, output_cost_per_token_batches vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas: input_cost_per_token_batches, output_cost_per_token_batches vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas: cache_read_input_token_cost, input_cost_per_token_batches, output_cost_per_token_batches vertex_ai/qwen/qwen3-next-80b-a3b-instruct-maas: vertex_ai/qwen/qwen3-next-80b-a3b-thinking-maas: vertex_ai/xai/grok-4.1-fast-non-reasoning: vertex_ai/xai/grok-4.1-fast-reasoning: vertex_ai/zai-org/glm-4.7-maas: cache_read_input_token_cost vertex_ai/zai-org/glm-5-maas: Price-Sync: litellm-providers * chore(prices): add verified Vertex AI zai glm-5.2-maas entry and fix Gemini 2.0 mode Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(prices): add Vertex AI claude-sonnet-4-5 1h cache write price above 200K The Vertex AI pricing page prices Claude Sonnet 4.5's 1h Cache Write at $6.00 up to 200K input tokens and $12.00 above, matching the value the anthropic and bedrock entries already carry. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * feat(prices): add vertex_ai/gemini-omni-1.1-flash-preview from the Vertex pricing page Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: berriai-litellm-provider-info-sync[bot] <328147090+berriai-litellm-provider-info-sync[bot]@users.noreply.github.com> Co-authored-by: kerry Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 297 +++++++++++++++--- model_prices_and_context_window.json | 297 +++++++++++++++--- 2 files changed, 504 insertions(+), 90 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 93bcc11ff64..9b38df9282e 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -46720,16 +46720,20 @@ "deprecation_date": "2026-10-15", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, "regional_endpoint_uplift_multiplier": 1.1, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -46745,16 +46749,20 @@ "deprecation_date": "2026-10-15", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, "regional_endpoint_uplift_multiplier": 1.1, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -46877,14 +46885,18 @@ "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -46901,20 +46913,25 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-5@20251101": { "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -46932,7 +46949,8 @@ "supports_vision": true, "supports_native_streaming": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-6": { "deprecation_date": "2027-02-05", @@ -46941,14 +46959,18 @@ "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -46965,7 +46987,8 @@ "supports_vision": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-6@default": { "deprecation_date": "2027-02-05", @@ -46974,14 +46997,18 @@ "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -46998,7 +47025,8 @@ "supports_vision": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-7": { "deprecation_date": "2027-04-16", @@ -47006,14 +47034,18 @@ "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47031,7 +47063,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-7@default": { "deprecation_date": "2027-04-16", @@ -47039,14 +47072,18 @@ "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47064,7 +47101,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5": { "deprecation_date": "2027-06-08", @@ -47072,14 +47110,18 @@ "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 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": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47099,14 +47141,17 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5-1": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, @@ -47136,7 +47181,10 @@ "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, - "deprecation_date": "2027-03-01" + "deprecation_date": "2027-03-01", + "input_cost_per_token_batches": 5e-06, + "output_cost_per_token_batches": 2.5e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5@default": { "deprecation_date": "2027-06-08", @@ -47144,14 +47192,18 @@ "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 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": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47171,14 +47223,17 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5-1@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, @@ -47208,7 +47263,10 @@ "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, - "deprecation_date": "2027-03-01" + "deprecation_date": "2027-03-01", + "input_cost_per_token_batches": 5e-06, + "output_cost_per_token_batches": 2.5e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-5": { "deprecation_date": "2027-01-24", @@ -47217,14 +47275,18 @@ "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47242,7 +47304,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-5@default": { "deprecation_date": "2027-01-24", @@ -47251,14 +47314,18 @@ "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47276,21 +47343,26 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-5-5": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47312,21 +47384,26 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-5-5@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47348,7 +47425,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-8": { "deprecation_date": "2027-05-28", @@ -47357,14 +47435,18 @@ "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47382,7 +47464,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-8@default": { "deprecation_date": "2027-05-28", @@ -47391,14 +47474,18 @@ "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47416,18 +47503,21 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-5": { "deprecation_date": "2026-09-29", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -47446,7 +47536,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-5": { "deprecation_date": "2026-12-24", @@ -47456,12 +47547,14 @@ "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47480,7 +47573,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-6": { "regional_endpoint_uplift_multiplier": 1.1, @@ -47488,14 +47582,18 @@ "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.88e-06, "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -47512,18 +47610,21 @@ "search_context_size_medium": 0.01 }, "supports_output_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-5@20250929": { "deprecation_date": "2026-09-29", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -47543,7 +47644,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_streaming": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/mistralai/codestral-2@001": { "input_cost_per_token": 3e-07, @@ -47553,6 +47655,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -47564,6 +47667,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -47575,6 +47679,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -47586,6 +47691,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -47623,14 +47729,17 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { + "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.7e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "output_cost_per_token_batches": 8.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "us-central1" ], @@ -47641,6 +47750,7 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.2-maas": { + "cache_read_input_token_cost": 5.6e-08, "input_cost_per_token": 5.6e-07, "input_cost_per_token_batches": 2.8e-07, "litellm_provider": "vertex_ai-deepseek_models", @@ -47650,7 +47760,7 @@ "mode": "chat", "output_cost_per_token": 1.68e-06, "output_cost_per_token_batches": 8.4e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -47662,13 +47772,15 @@ }, "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { "input_cost_per_token": 1.35e-06, + "input_cost_per_token_batches": 6.75e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 65336, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "output_cost_per_token_batches": 2.7e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "us-central1" ], @@ -48244,13 +48356,15 @@ }, "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { "input_cost_per_token": 3.5e-07, + "input_cost_per_token_batches": 1.75e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "output_cost_per_token_batches": 5.75e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image" @@ -48304,13 +48418,15 @@ }, "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "output_cost_per_token_batches": 3.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image" @@ -48356,6 +48472,7 @@ "supports_tool_choice": true }, "vertex_ai/minimaxai/minimax-m2-maas": { + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-minimax_models", "max_input_tokens": 196608, @@ -48363,11 +48480,12 @@ "max_tokens": 196608, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/moonshotai/kimi-k2-thinking-maas": { + "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-moonshot_models", "max_input_tokens": 256000, @@ -48375,12 +48493,13 @@ "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true }, "vertex_ai/zai-org/glm-4.7-maas": { + "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, @@ -48388,7 +48507,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -48405,7 +48524,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -48422,6 +48541,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -48433,6 +48553,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -48444,6 +48565,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -48455,6 +48577,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -48535,7 +48658,7 @@ "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/mistral-small-2503@001": { "input_cost_per_token": 1e-07, @@ -48547,7 +48670,7 @@ "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_tool_choice": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/mistral-ocr-2505": { "litellm_provider": "vertex_ai", @@ -48564,7 +48687,7 @@ "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "ocr_cost_per_page": 0.0003, - "source": "https://cloud.google.com/vertex-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "us-central1" ] @@ -48587,13 +48710,15 @@ }, "vertex_ai/openai/gpt-oss-120b-maas": { "input_cost_per_token": 9e-08, + "input_cost_per_token_batches": 4.5e-08, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.6e-07, - "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", + "output_cost_per_token_batches": 1.8e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_reasoning": true }, "vertex_ai/openai/gpt-oss-20b-maas": { @@ -48604,9 +48729,11 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.5e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_reasoning": true, - "cache_read_input_token_cost": 7e-09 + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token_batches": 3.5e-08, + "output_cost_per_token_batches": 1.25e-07 }, "vertex_ai/xai/grok-4.1-fast-non-reasoning": { "cache_read_input_token_cost": 5e-08, @@ -48617,7 +48744,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://docs.x.ai/developers/models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -48634,7 +48761,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://docs.x.ai/developers/models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -48726,13 +48853,15 @@ }, "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "output_cost_per_token_batches": 4.4e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global", "us-south1" @@ -48741,14 +48870,17 @@ "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { + "cache_read_input_token_cost": 2.2e-08, "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "output_cost_per_token_batches": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -48763,7 +48895,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -48778,7 +48910,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -54979,12 +55111,14 @@ "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -55003,7 +55137,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-6@default": { "regional_endpoint_uplift_multiplier": 1.1, @@ -55011,14 +55146,18 @@ "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.88e-06, "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -55035,7 +55174,8 @@ "search_context_size_medium": 0.01 }, "supports_output_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "duckduckgo/search": { "litellm_provider": "duckduckgo", @@ -66059,6 +66199,32 @@ "output_cost_per_token": 9e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, + "vertex_ai/gemini-omni-1.1-flash-preview": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "vertex_ai", + "max_output_tokens": 57920, + "max_tokens": 57920, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.75e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1beta/interactions" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "video" + ], + "supports_reasoning": true, + "supports_video_input": true, + "supports_vision": true + }, "vertex_ai/gemma-4-26b-a4b-it": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, @@ -72657,5 +72823,46 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true + }, + "vertex_ai/gemini-2.0-flash": { + "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_character": 3.75e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "vertex_ai", + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-2.0-flash-lite": { + "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_audio_token_batches": 3.75e-08, + "input_cost_per_character": 1.875e-08, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_batches": 3.75e-08, + "litellm_provider": "vertex_ai", + "mode": "chat", + "output_cost_per_token": 3e-07, + "output_cost_per_token_batches": 1.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/zai-org/glm-5.2-maas": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "vertex_ai-zai_models", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_regions": ["global"], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 93bcc11ff64..9b38df9282e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -46720,16 +46720,20 @@ "deprecation_date": "2026-10-15", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, "regional_endpoint_uplift_multiplier": 1.1, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -46745,16 +46749,20 @@ "deprecation_date": "2026-10-15", "cache_creation_input_token_cost": 1.25e-06, "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_creation_input_token_cost_batches": 6.25e-07, "cache_read_input_token_cost": 1e-07, + "cache_read_input_token_cost_batches": 5e-08, "input_cost_per_token": 1e-06, + "input_cost_per_token_batches": 5e-07, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 5e-06, + "output_cost_per_token_batches": 2.5e-06, "regional_endpoint_uplift_multiplier": 1.1, - "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_pdf_input": true, @@ -46877,14 +46885,18 @@ "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -46901,20 +46913,25 @@ "supports_tool_choice": true, "supports_vision": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-5@20251101": { "deprecation_date": "2026-11-24", "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 2.5e-05, + "output_cost_per_token_batches": 1.25e-05, "regional_endpoint_uplift_multiplier": 1.1, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -46932,7 +46949,8 @@ "supports_vision": true, "supports_native_streaming": true, "supports_output_config": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-6": { "deprecation_date": "2027-02-05", @@ -46941,14 +46959,18 @@ "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -46965,7 +46987,8 @@ "supports_vision": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-6@default": { "deprecation_date": "2027-02-05", @@ -46974,14 +46997,18 @@ "supports_legacy_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -46998,7 +47025,8 @@ "supports_vision": true, "supports_output_config": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 4096 + "prompt_cache_min_tokens": 4096, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-7": { "deprecation_date": "2027-04-16", @@ -47006,14 +47034,18 @@ "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47031,7 +47063,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-7@default": { "deprecation_date": "2027-04-16", @@ -47039,14 +47072,18 @@ "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47064,7 +47101,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 2048 + "prompt_cache_min_tokens": 2048, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5": { "deprecation_date": "2027-06-08", @@ -47072,14 +47110,18 @@ "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 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": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47099,14 +47141,17 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5-1": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, @@ -47136,7 +47181,10 @@ "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, - "deprecation_date": "2027-03-01" + "deprecation_date": "2027-03-01", + "input_cost_per_token_batches": 5e-06, + "output_cost_per_token_batches": 2.5e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5@default": { "deprecation_date": "2027-06-08", @@ -47144,14 +47192,18 @@ "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_batches": 5e-07, "input_cost_per_token": 1e-05, + "input_cost_per_token_batches": 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": 5e-05, + "output_cost_per_token_batches": 2.5e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47171,14 +47223,17 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-fable-5-1@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_1hr": 2e-05, + "cache_creation_input_token_cost_batches": 6.25e-06, "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-07, "input_cost_per_token": 1e-05, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, @@ -47208,7 +47263,10 @@ "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "prompt_cache_min_tokens": 512, - "deprecation_date": "2027-03-01" + "deprecation_date": "2027-03-01", + "input_cost_per_token_batches": 5e-06, + "output_cost_per_token_batches": 2.5e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-5": { "deprecation_date": "2027-01-24", @@ -47217,14 +47275,18 @@ "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47242,7 +47304,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-5@default": { "deprecation_date": "2027-01-24", @@ -47251,14 +47314,18 @@ "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47276,21 +47343,26 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-5-5": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47312,21 +47384,26 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-5-5@default": { "regional_endpoint_uplift_multiplier": 1.1, "supports_mid_conversation_system": true, "cache_creation_input_token_cost": 5e-06, "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_creation_input_token_cost_batches": 2.5e-06, "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, "input_cost_per_token": 4e-06, + "input_cost_per_token_batches": 2.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2e-05, + "output_cost_per_token_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47348,7 +47425,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 512 + "prompt_cache_min_tokens": 512, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-8": { "deprecation_date": "2027-05-28", @@ -47357,14 +47435,18 @@ "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47382,7 +47464,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-opus-4-8@default": { "deprecation_date": "2027-05-28", @@ -47391,14 +47474,18 @@ "supports_adaptive_thinking": true, "cache_creation_input_token_cost": 6.25e-06, "cache_creation_input_token_cost_above_1hr": 1e-05, + "cache_creation_input_token_cost_batches": 3.125e-06, "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-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_batches": 1.25e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47416,18 +47503,21 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-5": { "deprecation_date": "2026-09-29", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -47446,7 +47536,8 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-5": { "deprecation_date": "2026-12-24", @@ -47456,12 +47547,14 @@ "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -47480,7 +47573,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-6": { "regional_endpoint_uplift_multiplier": 1.1, @@ -47488,14 +47582,18 @@ "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.88e-06, "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -47512,18 +47610,21 @@ "search_context_size_medium": 0.01 }, "supports_output_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-5@20250929": { "deprecation_date": "2026-09-29", "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05, "cache_read_input_token_cost": 3e-07, "input_cost_per_token": 3e-06, "input_cost_per_token_above_200k_tokens": 6e-06, "output_cost_per_token_above_200k_tokens": 2.25e-05, "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 200000, @@ -47543,7 +47644,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_native_streaming": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/mistralai/codestral-2@001": { "input_cost_per_token": 3e-07, @@ -47553,6 +47655,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -47564,6 +47667,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -47575,6 +47679,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -47586,6 +47691,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -47623,14 +47729,17 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.1-maas": { + "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 6e-07, + "input_cost_per_token_batches": 3e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.7e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "output_cost_per_token_batches": 8.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "us-central1" ], @@ -47641,6 +47750,7 @@ "supports_tool_choice": true }, "vertex_ai/deepseek-ai/deepseek-v3.2-maas": { + "cache_read_input_token_cost": 5.6e-08, "input_cost_per_token": 5.6e-07, "input_cost_per_token_batches": 2.8e-07, "litellm_provider": "vertex_ai-deepseek_models", @@ -47650,7 +47760,7 @@ "mode": "chat", "output_cost_per_token": 1.68e-06, "output_cost_per_token_batches": 8.4e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -47662,13 +47772,15 @@ }, "vertex_ai/deepseek-ai/deepseek-r1-0528-maas": { "input_cost_per_token": 1.35e-06, + "input_cost_per_token_batches": 6.75e-07, "litellm_provider": "vertex_ai-deepseek_models", "max_input_tokens": 65336, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", "output_cost_per_token": 5.4e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "output_cost_per_token_batches": 2.7e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "us-central1" ], @@ -48244,13 +48356,15 @@ }, "vertex_ai/meta/llama-4-maverick-17b-128e-instruct-maas": { "input_cost_per_token": 3.5e-07, + "input_cost_per_token_batches": 1.75e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "mode": "chat", "output_cost_per_token": 1.15e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "output_cost_per_token_batches": 5.75e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image" @@ -48304,13 +48418,15 @@ }, "vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas": { "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, "litellm_provider": "vertex_ai-llama_models", "max_input_tokens": 10000000, "max_output_tokens": 10000000, "max_tokens": 10000000, "mode": "chat", "output_cost_per_token": 7e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "output_cost_per_token_batches": 3.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_modalities": [ "text", "image" @@ -48356,6 +48472,7 @@ "supports_tool_choice": true }, "vertex_ai/minimaxai/minimax-m2-maas": { + "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 3e-07, "litellm_provider": "vertex_ai-minimax_models", "max_input_tokens": 196608, @@ -48363,11 +48480,12 @@ "max_tokens": 196608, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, "vertex_ai/moonshotai/kimi-k2-thinking-maas": { + "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-moonshot_models", "max_input_tokens": 256000, @@ -48375,12 +48493,13 @@ "max_tokens": 256000, "mode": "chat", "output_cost_per_token": 2.5e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true, "supports_web_search": true }, "vertex_ai/zai-org/glm-4.7-maas": { + "cache_read_input_token_cost": 6e-08, "input_cost_per_token": 6e-07, "litellm_provider": "vertex_ai-zai_models", "max_input_tokens": 200000, @@ -48388,7 +48507,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 2.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -48405,7 +48524,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -48422,6 +48541,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -48433,6 +48553,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -48444,6 +48565,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -48455,6 +48577,7 @@ "max_tokens": 8191, "mode": "chat", "output_cost_per_token": 2e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_tool_choice": true }, @@ -48535,7 +48658,7 @@ "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/mistral-small-2503@001": { "input_cost_per_token": 1e-07, @@ -48547,7 +48670,7 @@ "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_tool_choice": true, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/mistral-ocr-2505": { "litellm_provider": "vertex_ai", @@ -48564,7 +48687,7 @@ "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, "ocr_cost_per_page": 0.0003, - "source": "https://cloud.google.com/vertex-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "us-central1" ] @@ -48587,13 +48710,15 @@ }, "vertex_ai/openai/gpt-oss-120b-maas": { "input_cost_per_token": 9e-08, + "input_cost_per_token_batches": 4.5e-08, "litellm_provider": "vertex_ai-openai_models", "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 3.6e-07, - "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", + "output_cost_per_token_batches": 1.8e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_reasoning": true }, "vertex_ai/openai/gpt-oss-20b-maas": { @@ -48604,9 +48729,11 @@ "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 2.5e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_reasoning": true, - "cache_read_input_token_cost": 7e-09 + "cache_read_input_token_cost": 7e-09, + "input_cost_per_token_batches": 3.5e-08, + "output_cost_per_token_batches": 1.25e-07 }, "vertex_ai/xai/grok-4.1-fast-non-reasoning": { "cache_read_input_token_cost": 5e-08, @@ -48617,7 +48744,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://docs.x.ai/developers/models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -48634,7 +48761,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 5e-07, - "source": "https://docs.x.ai/developers/models", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, @@ -48726,13 +48853,15 @@ }, "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": { "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", "output_cost_per_token": 8.8e-07, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "output_cost_per_token_batches": 4.4e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global", "us-south1" @@ -48741,14 +48870,17 @@ "supports_tool_choice": true }, "vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas": { + "cache_read_input_token_cost": 2.2e-08, "input_cost_per_token": 2.2e-07, + "input_cost_per_token_batches": 1.1e-07, "litellm_provider": "vertex_ai-qwen_models", "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", "output_cost_per_token": 1.8e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "output_cost_per_token_batches": 9e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -48763,7 +48895,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -48778,7 +48910,7 @@ "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supported_regions": [ "global" ], @@ -54979,12 +55111,14 @@ "cache_creation_input_token_cost_above_1hr": 4e-06, "cache_read_input_token_cost": 2e-07, "input_cost_per_token": 2e-06, + "input_cost_per_token_batches": 1e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 1e-05, + "output_cost_per_token_batches": 5e-06, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -55003,7 +55137,8 @@ "supports_vision": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "vertex_ai/claude-sonnet-4-6@default": { "regional_endpoint_uplift_multiplier": 1.1, @@ -55011,14 +55146,18 @@ "supports_legacy_thinking": true, "cache_creation_input_token_cost": 3.75e-06, "cache_creation_input_token_cost_above_1hr": 6e-06, + "cache_creation_input_token_cost_batches": 1.88e-06, "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_batches": 1.5e-07, "input_cost_per_token": 3e-06, + "input_cost_per_token_batches": 1.5e-06, "litellm_provider": "vertex_ai-anthropic_models", "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_batches": 7.5e-06, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_function_calling": true, @@ -55035,7 +55174,8 @@ "search_context_size_medium": 0.01 }, "supports_output_config": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "duckduckgo/search": { "litellm_provider": "duckduckgo", @@ -66059,6 +66199,32 @@ "output_cost_per_token": 9e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, + "vertex_ai/gemini-omni-1.1-flash-preview": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "vertex_ai", + "max_output_tokens": 57920, + "max_tokens": 57920, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.75e-05, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_endpoints": [ + "/v1beta/interactions" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "video" + ], + "supports_reasoning": true, + "supports_video_input": true, + "supports_vision": true + }, "vertex_ai/gemma-4-26b-a4b-it": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 1.5e-07, @@ -72657,5 +72823,46 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true + }, + "vertex_ai/gemini-2.0-flash": { + "input_cost_per_audio_token": 1e-06, + "input_cost_per_audio_token_batches": 5e-07, + "input_cost_per_character": 3.75e-08, + "input_cost_per_token": 1.5e-07, + "input_cost_per_token_batches": 7.5e-08, + "litellm_provider": "vertex_ai", + "mode": "chat", + "output_cost_per_token": 6e-07, + "output_cost_per_token_batches": 3e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/gemini-2.0-flash-lite": { + "input_cost_per_audio_token": 7.5e-08, + "input_cost_per_audio_token_batches": 3.75e-08, + "input_cost_per_character": 1.875e-08, + "input_cost_per_token": 7.5e-08, + "input_cost_per_token_batches": 3.75e-08, + "litellm_provider": "vertex_ai", + "mode": "chat", + "output_cost_per_token": 3e-07, + "output_cost_per_token_batches": 1.5e-07, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + }, + "vertex_ai/zai-org/glm-5.2-maas": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "vertex_ai-zai_models", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "supported_regions": ["global"], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true } }