[ { "input_cost_per_character": 0.00003, "source": "https://cloud.google.com/text-to-speech/pricing", "supported_endpoints": [ "/v1/audio/speech" ], "model_id": "chirp", "model_name": "Chirp", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_second": 0.00026667, "metadata": { "calculation": "$0.016/60 seconds = $0.00026667 per second", "original_pricing_per_minute": 0.016 }, "source": "https://cloud.google.com/speech-to-text/pricing", "supported_endpoints": [ "/v1/audio/transcriptions" ], "model_id": "chirp_3", "model_name": "Chirp_3", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "audio", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "claude-3-5-haiku", "model_name": "Claude 3.5 Haiku", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "claude-3-5-haiku@20241022", "model_name": "Claude 3 5 Haiku@ (Oct 2024)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "claude-3-5-sonnet", "model_name": "Claude 3.5 Sonnet", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 8192, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_tool_choice": true, "model_id": "claude-3-5-sonnet@20240620", "model_name": "Claude 3 5 Sonnet@ (Jun 2024)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 8192, "deprecation_date": "2026-05-11", "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 8192, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "claude-3-7-sonnet@20250219", "model_name": "Claude 3 7 Sonnet@ (Feb 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-3-haiku", "model_name": "Claude 3 Haiku", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.00000125, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-3-haiku@20240307", "model_name": "Claude 3 Haiku@ (Mar 2024)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "output_cost_per_million": 1.25, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-3-opus", "model_name": "Claude 3 Opus", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-3-opus@20240229", "model_name": "Claude 3 Opus@ (Feb 2024)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-3-sonnet", "model_name": "Claude 3 Sonnet", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 4096, "max_tokens": 4096, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-3-sonnet@20240229", "model_name": "Claude 3 Sonnet@ (Feb 2024)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "model_id": "claude-fable-5", "model_name": "Claude Fable 5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00005, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.00002, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "model_id": "claude-fable-5@default", "model_name": "Claude Fable 5@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 10, "output_cost_per_million": 50, "cache_read_cost_per_token": 0.000001, "cache_read_cost_per_million": 1, "cache_write_cost_per_token": 0.0000125, "cache_write_cost_per_million": 12.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 8192, "cache_creation_input_token_cost_above_1hr": 0.000002, "max_tokens": 8192, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "model_id": "claude-haiku-4-5", "model_name": "Claude Haiku 4 5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000005, "max_input_tokens": 200000, "max_output_tokens": 8192, "cache_creation_input_token_cost_above_1hr": 0.000002, "max_tokens": 8192, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", "supports_assistant_prefill": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "model_id": "claude-haiku-4-5@20251001", "model_name": "Claude Haiku 4 5@ (Oct 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 5, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0.00000125, "cache_write_cost_per_million": 1.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "cache_creation_input_token_cost_above_1hr": 0.00003, "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "claude-opus-4", "model_name": "Claude Opus 4", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "cache_creation_input_token_cost_above_1hr": 0.00003, "input_cost_per_token_batches": 0.0000075, "max_tokens": 32000, "output_cost_per_token_batches": 0.0000375, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-opus-4-1", "model_name": "Claude Opus 4 1", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "cache_creation_input_token_cost_above_1hr": 0.00003, "input_cost_per_token_batches": 0.0000075, "max_tokens": 32000, "output_cost_per_token_batches": 0.0000375, "supports_assistant_prefill": true, "supports_tool_choice": true, "model_id": "claude-opus-4-1@20250805", "model_name": "Claude Opus 4 1@ (Aug 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "model_id": "claude-opus-4-5", "model_name": "Claude Opus 4 5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "supports_output_config": true, "model_id": "claude-opus-4-5@20251101", "model_name": "Claude Opus 4 5@ (Nov 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "model_id": "claude-opus-4-6", "model_name": "Claude Opus 4 6", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_output_config": true, "supports_max_reasoning_effort": true, "model_id": "claude-opus-4-6@default", "model_name": "Claude Opus 4 6@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "model_id": "claude-opus-4-7", "model_name": "Claude Opus 4 7", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "model_id": "claude-opus-4-7@default", "model_name": "Claude Opus 4 7@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "model_id": "claude-opus-4-8", "model_name": "Claude Opus 4 8", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000025, "max_input_tokens": 1000000, "max_output_tokens": 128000, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.00001, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "model_id": "claude-opus-4-8@default", "model_name": "Claude Opus 4 8@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 25, "cache_read_cost_per_token": 5e-7, "cache_read_cost_per_million": 0.5, "cache_write_cost_per_token": 0.00000625, "cache_write_cost_per_million": 6.25, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000015, "output_cost_per_token": 0.000075, "max_input_tokens": 200000, "max_output_tokens": 32000, "cache_creation_input_token_cost_above_1hr": 0.00003, "max_tokens": 32000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "claude-opus-4@20250514", "model_name": "Claude Opus 4@ (May 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 15, "output_cost_per_million": 75, "cache_read_cost_per_token": 0.0000015, "cache_read_cost_per_million": 1.5, "cache_write_cost_per_token": 0.00001875, "cache_write_cost_per_million": 18.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "claude-sonnet-4", "model_name": "Claude Sonnet 4", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_batches": 0.0000015, "max_tokens": 64000, "output_cost_per_token_batches": 0.0000075, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "claude-sonnet-4-5", "model_name": "Claude Sonnet 4 5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 200000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "input_cost_per_token_batches": 0.0000015, "max_tokens": 64000, "output_cost_per_token_batches": 0.0000075, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "supports_native_streaming": true, "model_id": "claude-sonnet-4-5@20250929", "model_name": "Claude Sonnet 4 5@ (Sep 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_output_config": true, "model_id": "claude-sonnet-4-6", "model_name": "Claude Sonnet 4 6", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "supports_adaptive_thinking": true, "cache_creation_input_token_cost_above_1hr": 0.000006, "max_tokens": 64000, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_max_reasoning_effort": true, "supports_tool_choice": true, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_output_config": true, "model_id": "claude-sonnet-4-6@default", "model_name": "Claude Sonnet 4 6@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000015, "max_input_tokens": 1000000, "max_output_tokens": 64000, "cache_creation_input_token_cost_above_1hr": 0.000006, "input_cost_per_token_above_200k_tokens": 0.000006, "output_cost_per_token_above_200k_tokens": 0.0000225, "cache_creation_input_token_cost_above_200k_tokens": 0.0000075, "cache_read_input_token_cost_above_200k_tokens": 6e-7, "max_tokens": 64000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_assistant_prefill": true, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "claude-sonnet-4@20250514", "model_name": "Claude Sonnet 4@ (May 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 15, "cache_read_cost_per_token": 3e-7, "cache_read_cost_per_million": 0.3, "cache_write_cost_per_token": 0.00000375, "cache_write_cost_per_million": 3.75, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000004, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "model_id": "claude-sonnet-5", "model_name": "Claude Sonnet 5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.00001, "max_input_tokens": 1000000, "max_output_tokens": 128000, "cache_creation_input_token_cost_above_1hr": 0.000004, "max_tokens": 128000, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, "supports_adaptive_thinking": true, "supports_assistant_prefill": false, "supports_computer_use": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_sampling_params": false, "supports_tool_choice": true, "supports_xhigh_reasoning_effort": true, "supports_max_reasoning_effort": true, "model_id": "claude-sonnet-5@default", "model_name": "Claude Sonnet 5@default", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 10, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0.0000025, "cache_write_cost_per_million": 2.5, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "codestral-2", "model_name": "Codestral 2", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 0.8999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "codestral-2@001", "model_name": "Codestral 2@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 0.8999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "codestral-2501", "model_name": "Codestral (Jan 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "codestral@2405", "model_name": "Codestral@2405", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "codestral@latest", "model_name": "Codestral@latest", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 65536, "max_output_tokens": 32768, "input_cost_per_image": 0.0011, "input_cost_per_token_batches": 0.000001, "max_tokens": 32768, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token_batches": 0.000006, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image", "model_id": "deep-research-pro-preview-12-2025", "model_name": "Deep Research Pro Preview 12 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "ocr_cost_per_page": 0.0003, "source": "https://cloud.google.com/vertex-ai/pricing", "supported_regions": [ "us-central1" ], "model_id": "deepseek-ai/deepseek-ocr-maas", "model_name": "Deepseek Ocr Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "ocr", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054, "max_input_tokens": 65336, "max_output_tokens": 8192, "max_tokens": 8192, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "us-central1" ], "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "deepseek-ai/deepseek-r1-0528-maas", "model_name": "Deepseek R1 0528 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.35, "output_cost_per_million": 5.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.00000135, "output_cost_per_token": 0.0000054, "max_input_tokens": 163840, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "us-central1" ], "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "deepseek-ai/deepseek-v3.1-maas", "model_name": "Deepseek V3.1 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.35, "output_cost_per_million": 5.4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 5.6e-7, "output_cost_per_token": 0.00000168, "max_input_tokens": 163840, "max_output_tokens": 32768, "input_cost_per_token_batches": 2.8e-7, "max_tokens": 32768, "output_cost_per_token_batches": 8.4e-7, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "global" ], "supports_assistant_prefill": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "deepseek-ai/deepseek-v3.2-maas", "model_name": "Deepseek V3.2 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.56, "output_cost_per_million": 1.68, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-7, "max_tokens": 8192, "source": "https://ai.google.dev/pricing#2_0flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_input": true, "supports_audio_output": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "model_id": "gemini-2.0-flash", "model_name": "Gemini 2.0 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 0.000001, "max_tokens": 8192, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "model_id": "gemini-2.0-flash-001", "model_name": "Gemini 2.0 Flash 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 3.75e-8, "cache_read_cost_per_million": 0.0375, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-8, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "model_id": "gemini-2.0-flash-lite", "model_name": "Gemini 2.0 Flash-Lite", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 1.875e-8, "cache_read_cost_per_million": 0.01875, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-8, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "model_id": "gemini-2.0-flash-lite-001", "model_name": "Gemini 2.0 Flash Lite 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 1.875e-8, "cache_read_cost_per_million": 0.01875, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 128000, "max_output_tokens": 64000, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_tokens": 64000, "output_cost_per_token_above_200k_tokens": 0.000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text" ], "supports_computer_use": true, "supports_system_messages": true, "supports_tool_choice": true, "model_id": "gemini-2.5-computer-use-preview-10-2025", "model_name": "Gemini 2.5 Computer Use Preview 10 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_image_size": false, "model_id": "gemini-2.5-flash", "model_name": "Gemini 2.5 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 32768, "max_output_tokens": 32768, "input_cost_per_audio_token": 0.000001, "max_tokens": 32768, "output_cost_per_image": 0.039, "output_cost_per_image_token": 0.00003, "output_cost_per_reasoning_token": 0.0000025, "rpm": 100000, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "image" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": false, "tpm": 8000000, "supports_image_size": false, "model_id": "gemini-2.5-flash-image", "model_name": "Gemini 2.5 Flash Image", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 3e-8, "cache_read_cost_per_million": 0.03, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 3e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_image_size": false, "model_id": "gemini-2.5-flash-lite", "model_name": "Gemini 2.5 Flash Lite", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecation_date": "2025-11-18", "input_cost_per_audio_token": 5e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_image_size": false, "model_id": "gemini-2.5-flash-lite-preview-06-17", "model_name": "Gemini 2.5 Flash Lite Preview 06 17", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 1e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 3e-7, "max_tokens": 65535, "output_cost_per_reasoning_token": 4e-7, "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_image_size": false, "model_id": "gemini-2.5-flash-lite-preview-09-2025", "model_name": "Gemini 2.5 Flash Lite Preview 09 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 1e-8, "cache_read_cost_per_million": 0.01, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "source": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "supports_image_size": false, "model_id": "gemini-2.5-flash-preview-09-2025", "model_name": "Gemini 2.5 Flash Preview 09 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "model_id": "gemini-2.5-pro", "model_name": "Gemini 2.5 Pro", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.00000125, "output_cost_per_token": 0.00001, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_audio_token": 7e-7, "input_cost_per_token_above_200k_tokens": 0.0000025, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000015, "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", "supported_modalities": [ "text" ], "supported_output_modalities": [ "audio" ], "supports_audio_output": false, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "model_id": "gemini-2.5-pro-preview-tts", "model_name": "Gemini 2.5 Pro Preview TTS", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.25, "output_cost_per_million": 10, "cache_read_cost_per_token": 1.25e-7, "cache_read_cost_per_million": 0.125, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000003, "source": "https://ai.google.dev/pricing/gemini-3", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 9e-7, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000054, "cache_read_input_token_cost_priority": 9e-8, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "gemini-3-flash-preview", "model_name": "Gemini 3 Flash Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 65536, "max_output_tokens": 32768, "input_cost_per_image": 0.0011, "input_cost_per_token_batches": 0.000001, "max_tokens": 32768, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token_batches": 0.000006, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image", "model_id": "gemini-3-pro-image", "model_name": "Gemini 3 Pro Image", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 65536, "max_output_tokens": 32768, "input_cost_per_image": 0.0011, "input_cost_per_token_batches": 0.000001, "max_tokens": 32768, "output_cost_per_image": 0.134, "output_cost_per_image_token": 0.00012, "output_cost_per_token_batches": 0.000006, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image", "model_id": "gemini-3-pro-image-preview", "model_name": "Gemini 3 Pro Image Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65535, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65535, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "gemini-3-pro-preview", "model_name": "Gemini 3 Pro Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 65536, "max_output_tokens": 32768, "input_cost_per_image": 0.00056, "max_tokens": 32768, "output_cost_per_image": 0.0672, "output_cost_per_image_token": 0.00006, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "model_id": "gemini-3.1-flash-image", "model_name": "Gemini 3.1 Flash Image", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 5e-7, "output_cost_per_token": 0.000003, "max_input_tokens": 65536, "max_output_tokens": 32768, "input_cost_per_image": 0.00056, "max_tokens": 32768, "output_cost_per_image": 0.0672, "output_cost_per_image_token": 0.00006, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "model_id": "gemini-3.1-flash-image-preview", "model_name": "Gemini 3.1 Flash Image Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.5, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_token_cost_flex": 1.25e-8, "cache_read_input_token_cost_priority": 4.5e-8, "input_cost_per_audio_token": 5e-7, "input_cost_per_token_batches": 1.25e-7, "input_cost_per_token_flex": 1.25e-7, "input_cost_per_token_priority": 4.5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "output_cost_per_token_batches": 7.5e-7, "output_cost_per_token_flex": 7.5e-7, "output_cost_per_token_priority": 0.0000027, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "gemini-3.1-flash-lite", "model_name": "Gemini 3.1 Flash Lite", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.0000015, "max_input_tokens": 1048576, "max_output_tokens": 65536, "input_cost_per_audio_token": 5e-7, "max_tokens": 65536, "output_cost_per_reasoning_token": 0.0000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_audio_output": false, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "gemini-3.1-flash-lite-preview", "model_name": "Gemini 3.1 Flash Lite Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "output_cost_per_million": 1.5, "cache_read_cost_per_token": 2.5e-8, "cache_read_cost_per_million": 0.024999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "gemini-3.1-pro-preview", "model_name": "Gemini 3.1 Pro Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000012, "max_input_tokens": 1048576, "max_output_tokens": 65536, "cache_read_input_token_cost_above_200k_tokens": 4e-7, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-7, "input_cost_per_token_above_200k_tokens": 0.000004, "input_cost_per_token_batches": 0.000001, "max_tokens": 65536, "output_cost_per_token_above_200k_tokens": 0.000018, "output_cost_per_token_batches": 0.000006, "output_cost_per_image": 0.00012, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_video_input": true, "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000036, "input_cost_per_token_above_200k_tokens_priority": 0.0000072, "output_cost_per_token_priority": 0.0000216, "output_cost_per_token_above_200k_tokens_priority": 0.0000324, "cache_read_input_token_cost_priority": 3.6e-7, "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "gemini-3.1-pro-preview-customtools", "model_name": "Gemini 3.1 Pro Preview Customtools", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 12, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000009, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.000009, "source": "https://ai.google.dev/pricing/gemini-3", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", "/v1/batch" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_audio_input": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_video_input": true, "supports_web_search": true, "supports_native_streaming": true, "input_cost_per_token_priority": 0.0000027, "input_cost_per_audio_token_priority": 0.0000018, "output_cost_per_token_priority": 0.0000162, "cache_read_input_token_cost_priority": 2.7e-7, "search_context_cost_per_query": { "search_context_size_low": 0.014, "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", "model_id": "gemini-3.5-flash", "model_name": "Gemini 3.5 Flash", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1.5, "output_cost_per_million": 9, "cache_read_cost_per_token": 1.5e-7, "cache_read_cost_per_million": 0.15, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "max_tokens": 2048, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "model_id": "gemini-embedding-001", "model_name": "Gemini Embedding 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.15, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_video_per_second": 0.00079, "max_tokens": 8192, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true, "model_id": "gemini-embedding-2", "model_name": "Gemini Embedding 2", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "input_cost_per_audio_per_second": 0.00016, "input_cost_per_image": 0.00012, "input_cost_per_video_per_second": 0.00079, "max_tokens": 8192, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supports_multimodal": true, "uses_embed_content": true, "model_id": "gemini-embedding-2-preview", "model_name": "Gemini Embedding 2 Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 1000000, "max_output_tokens": 8192, "input_cost_per_character": 0, "max_tokens": 8192, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "uses_embed_content": true, "model_id": "gemini-flash-experimental", "model_name": "Gemini Flash Experimental", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000003, "max_tokens": 65535, "output_cost_per_audio_token": 0.000012, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/vertex_ai/live" ], "supported_modalities": [ "text", "image", "audio", "video" ], "supported_output_modalities": [ "text", "audio" ], "supports_audio_input": true, "supports_audio_output": true, "supports_pdf_input": true, "supports_prompt_caching": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "supports_web_search": true, "search_context_cost_per_query": { "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 }, "gemini_native_audio": true, "model_id": "gemini-live-2.5-flash-preview-native-audio-09-2025", "model_name": "Gemini Live 2.5 Flash Preview Native Audio 09 2025", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2, "cache_read_cost_per_token": 7.5e-8, "cache_read_cost_per_million": 0.075, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "realtime", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 1048576, "max_output_tokens": 65535, "input_cost_per_audio_token": 0.000001, "max_tokens": 65535, "output_cost_per_reasoning_token": 0.0000025, "source": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" ], "supported_modalities": [ "text", "image", "video", "audio" ], "supported_output_modalities": [ "text" ], "supports_audio_output": false, "supports_prompt_caching": false, "supports_reasoning": true, "supports_system_messages": true, "supports_tool_choice": true, "supports_url_context": true, "model_id": "gemini-robotics-er-1.5-preview", "model_name": "Gemini Robotics Er 1.5 Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": true }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 256000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/maas/google/gemma-4-26b-a4b-it", "supported_regions": [ "global" ], "supports_tool_choice": true, "model_id": "google/gemma-4-26b-a4b-it-maas", "model_name": "Gemma 4 26B A4B It Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_id": "imagegeneration@006", "model_name": "Imagegeneration@006", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/image/edit-insert-objects", "model_id": "imagen-3.0-capability-001", "model_name": "Imagen 3.0 Capability 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_id": "imagen-3.0-fast-generate-001", "model_name": "Imagen 3.0 Fast Generate 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_id": "imagen-3.0-generate-001", "model_name": "Imagen 3.0 Generate 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "deprecation_date": "2025-11-10", "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_id": "imagen-3.0-generate-002", "model_name": "Imagen 3.0 Generate 002", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_image": 0.02, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_id": "imagen-4.0-fast-generate-001", "model_name": "Imagen 4.0 Fast Generate 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_image": 0.04, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_id": "imagen-4.0-generate-001", "model_name": "Imagen 4.0 Generate 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "output_cost_per_image": 0.06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_id": "imagen-4.0-ultra-generate-001", "model_name": "Imagen 4.0 Ultra Generate 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "image", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-1.5", "model_name": "Jamba 1.5", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-1.5-large", "model_name": "Jamba 1.5 Large", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000008, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-1.5-large@001", "model_name": "Jamba 1.5 Large@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 8, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-1.5-mini", "model_name": "Jamba 1.5 Mini", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 2e-7, "output_cost_per_token": 4e-7, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "supports_tool_choice": true, "model_id": "jamba-1.5-mini@001", "model_name": "Jamba 1.5 Mini@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.39999999999999997, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 8192, "max_output_tokens": 1024, "input_cost_per_character": 0.000005, "max_tokens": 1024, "output_cost_per_character": 0.000015, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true, "model_id": "medlm-large", "model_name": "Medlm Large", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 32768, "max_output_tokens": 8192, "input_cost_per_character": 5e-7, "max_tokens": 8192, "output_cost_per_character": 0.000001, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "supports_tool_choice": true, "model_id": "medlm-medium", "model_name": "Medlm Medium", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 0.000005, "output_cost_per_token": 0.000016, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "model_id": "meta/llama-3.1-405b-instruct-maas", "model_name": "Llama 3.1 405B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 5, "output_cost_per_million": 16, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "model_id": "meta/llama-3.1-70b-instruct-maas", "model_name": "Llama 3.1 70B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.1 API service for llama-3.1-70b-instruct-maas and llama-3.1-8b-instruct-maas are in public preview and at no cost." }, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "model_id": "meta/llama-3.1-8b-instruct-maas", "model_name": "Llama 3.1 8B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_vision": true, "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 128000, "max_output_tokens": 2048, "max_tokens": 2048, "metadata": { "notes": "VertexAI states that The Llama 3.2 API service is at no cost during public preview, and will be priced as per dollar-per-1M-tokens at GA." }, "source": "https://console.cloud.google.com/vertex-ai/publishers/meta/model-garden/llama-3.2-90b-vision-instruct-maas", "supports_system_messages": true, "supports_tool_choice": true, "model_id": "meta/llama-3.2-90b-vision-instruct-maas", "model_name": "Llama 3.2 90B Vision Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.00000115, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_tool_choice": true, "model_id": "meta/llama-4-maverick-17b-128e-instruct-maas", "model_name": "Llama 4 Maverick 17B 128e Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.35, "output_cost_per_million": 1.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3.5e-7, "output_cost_per_token": 0.00000115, "max_input_tokens": 1000000, "max_output_tokens": 1000000, "max_tokens": 1000000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_tool_choice": true, "model_id": "meta/llama-4-maverick-17b-16e-instruct-maas", "model_name": "Llama 4 Maverick 17B 16e Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.35, "output_cost_per_million": 1.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 7e-7, "max_input_tokens": 10000000, "max_output_tokens": 10000000, "max_tokens": 10000000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_tool_choice": true, "model_id": "meta/llama-4-scout-17b-128e-instruct-maas", "model_name": "Llama 4 Scout 17B 128e Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "output_cost_per_million": 0.7, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 7e-7, "max_input_tokens": 10000000, "max_output_tokens": 10000000, "max_tokens": 10000000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_modalities": [ "text", "image" ], "supported_output_modalities": [ "text", "code" ], "supports_tool_choice": true, "model_id": "meta/llama-4-scout-17b-16e-instruct-maas", "model_name": "Llama 4 Scout 17B 16e Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "output_cost_per_million": 0.7, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true, "model_id": "meta/llama3-405b-instruct-maas", "model_name": "Llama3 405B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true, "model_id": "meta/llama3-70b-instruct-maas", "model_name": "Llama3 70B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0, "output_cost_per_token": 0, "max_input_tokens": 32000, "max_output_tokens": 32000, "max_tokens": 32000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true, "model_id": "meta/llama3-8b-instruct-maas", "model_name": "Llama3 8B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 196608, "max_output_tokens": 196608, "max_tokens": 196608, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true, "model_id": "minimaxai/minimax-m2-maas", "model_name": "Minimax M2 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-large-2411", "model_name": "Mistral Large (Nov 2024)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-large@2407", "model_name": "Mistral Large@2407", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-large@2411-001", "model_name": "Mistral Large@2411 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-large@latest", "model_name": "Mistral Large@latest", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-medium-3", "model_name": "Mistral Medium 3", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-medium-3@001", "model_name": "Mistral Medium 3@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000003, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "mistral-nemo@2407", "model_name": "Mistral Nemo@2407", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 3, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 1.5e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "mistral-nemo@latest", "model_name": "Mistral Nemo@latest", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.15, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "ocr_cost_per_page": 0.0005, "supported_endpoints": [ "/v1/ocr" ], "source": "https://cloud.google.com/generative-ai-app-builder/pricing", "model_id": "mistral-ocr-2505", "model_name": "Mistral Ocr (May 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "ocr", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "mistral-small-2503", "model_name": "Mistral Small (Mar 2025)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000003, "max_input_tokens": 32000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistral-small-2503@001", "model_name": "Mistral Small 2503@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "mistralai/codestral-2", "model_name": "Codestral 2", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 0.8999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 3e-7, "output_cost_per_token": 9e-7, "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "supports_tool_choice": true, "model_id": "mistralai/codestral-2@001", "model_name": "Codestral 2@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.3, "output_cost_per_million": 0.8999999999999999, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistralai/mistral-medium-3", "model_name": "Mistral Medium 3", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 4e-7, "output_cost_per_token": 0.000002, "max_input_tokens": 128000, "max_output_tokens": 8191, "max_tokens": 8191, "supports_tool_choice": true, "model_id": "mistralai/mistral-medium-3@001", "model_name": "Mistral Medium 3@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.39999999999999997, "output_cost_per_million": 2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000025, "max_input_tokens": 256000, "max_output_tokens": 256000, "max_tokens": 256000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supports_tool_choice": true, "supports_web_search": true, "model_id": "moonshotai/kimi-k2-thinking-maas", "model_name": "Kimi K2 Thinking Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.5, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "input_cost_per_character": 2e-7, "input_cost_per_image": 0.0001, "input_cost_per_video_per_second": 0.0005, "input_cost_per_video_per_second_above_15s_interval": 0.002, "input_cost_per_video_per_second_above_8s_interval": 0.001, "max_tokens": 2048, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image", "video" ], "model_id": "multimodalembedding", "model_name": "Multimodalembedding", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 8e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "input_cost_per_character": 2e-7, "input_cost_per_image": 0.0001, "input_cost_per_video_per_second": 0.0005, "input_cost_per_video_per_second_above_15s_interval": 0.002, "input_cost_per_video_per_second_above_8s_interval": 0.001, "max_tokens": 2048, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "supported_endpoints": [ "/v1/embeddings" ], "supported_modalities": [ "text", "image", "video" ], "model_id": "multimodalembedding@001", "model_name": "Multimodalembedding@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.7999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1.5e-7, "output_cost_per_token": 6e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", "supports_reasoning": true, "model_id": "openai/gpt-oss-120b-maas", "model_name": "GPT Oss 120B Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.15, "output_cost_per_million": 0.6, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 7.5e-8, "output_cost_per_token": 3e-7, "max_input_tokens": 131072, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://console.cloud.google.com/vertex-ai/publishers/openai/model-garden/gpt-oss-120b-maas", "supports_reasoning": true, "model_id": "openai/gpt-oss-20b-maas", "model_name": "GPT Oss 20B Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.075, "output_cost_per_million": 0.3, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 2.5e-7, "output_cost_per_token": 0.000001, "max_input_tokens": 262144, "max_output_tokens": 16384, "max_tokens": 16384, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global", "us-south1" ], "supports_tool_choice": true, "model_id": "qwen/qwen3-235b-a22b-instruct-2507-maas", "model_name": "Qwen3 235B A22B Instruct 2507 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.25, "output_cost_per_million": 1, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.000004, "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global" ], "supports_tool_choice": true, "model_id": "qwen/qwen3-coder-480b-a35b-instruct-maas", "model_name": "Qwen3 Coder 480B A35B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 4, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global" ], "supports_tool_choice": true, "model_id": "qwen/qwen3-next-80b-a3b-instruct-maas", "model_name": "Qwen3 Next 80B A3B Instruct Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.15, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 1.5e-7, "output_cost_per_token": 0.0000012, "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "supported_regions": [ "global" ], "supports_tool_choice": true, "model_id": "qwen/qwen3-next-80b-a3b-thinking-maas", "model_name": "Qwen3 Next 80B A3B Thinking Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.15, "output_cost_per_million": 1.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_query": 0.0015, "model_id": "search_api", "model_name": "Search_api", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_input_tokens": 0, "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "vector_store", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "deprecation_date": "2026-01-14", "input_cost_per_character": 2.5e-8, "max_tokens": 2048, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "model_id": "text-embedding-004", "model_name": "Text Embedding 004", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "input_cost_per_character": 2.5e-8, "max_tokens": 2048, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "model_id": "text-embedding-005", "model_name": "Text Embedding 005", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 8192, "input_cost_per_character": 2.5e-8, "max_tokens": 8192, "output_vector_size": 3072, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "model_id": "text-embedding-large-exp-03-07", "model_name": "Text Embedding Large Exp 03 07", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 6.25e-9, "output_cost_per_token": 0, "max_input_tokens": 3072, "max_tokens": 3072, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_id": "text-embedding-preview-0409", "model_name": "Text Embedding Preview (Sep 2004)", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.0062499999999999995, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 1e-7, "output_cost_per_token": 0, "max_input_tokens": 2048, "input_cost_per_character": 2.5e-8, "max_tokens": 2048, "output_vector_size": 768, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models", "model_id": "text-multilingual-embedding-002", "model_name": "Text Multilingual Embedding 002", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_million": 0.09999999999999999, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "embedding", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.000028, "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "model_id": "text-unicorn", "model_name": "Text Unicorn", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 10, "output_cost_per_million": 28, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "completion", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "input_cost_per_token": 0.00001, "output_cost_per_token": 0.000028, "max_input_tokens": 8192, "max_output_tokens": 1024, "max_tokens": 1024, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "model_id": "text-unicorn@001", "model_name": "Text Unicorn@001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 10, "output_cost_per_million": 28, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "completion", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 1024, "max_tokens": 1024, "output_cost_per_second": 0.35, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "model_id": "veo-2.0-generate-001", "model_name": "Veo 2.0 Generate 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "video_generation", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 1024, "max_tokens": 1024, "output_cost_per_second": 0.15, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "model_id": "veo-3.0-fast-generate-001", "model_name": "Veo 3.0 Fast Generate 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "video_generation", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 1024, "max_tokens": 1024, "output_cost_per_second": 0.4, "source": "https://ai.google.dev/gemini-api/docs/video", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "model_id": "veo-3.0-generate-001", "model_name": "Veo 3.0 Generate 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "video_generation", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 1024, "max_tokens": 1024, "output_cost_per_second": 0.15, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "model_id": "veo-3.1-fast-generate-001", "model_name": "Veo 3.1 Fast Generate 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "video_generation", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 1024, "max_tokens": 1024, "output_cost_per_second": 0.15, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "model_id": "veo-3.1-fast-generate-preview", "model_name": "Veo 3.1 Fast Generate Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "video_generation", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 1024, "max_tokens": 1024, "output_cost_per_second": 0.4, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "model_id": "veo-3.1-generate-001", "model_name": "Veo 3.1 Generate 001", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "video_generation", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "max_input_tokens": 1024, "max_tokens": 1024, "output_cost_per_second": 0.4, "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/veo", "supported_modalities": [ "text" ], "supported_output_modalities": [ "video" ], "model_id": "veo-3.1-generate-preview", "model_name": "Veo 3.1 Generate Preview", "provider_id": "vertex", "provider_name": "Google Vertex AI", "max_output_tokens": 0, "input_cost_per_token": 0, "input_cost_per_million": 0, "output_cost_per_token": 0, "output_cost_per_million": 0, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "video_generation", "deprecation_date": null, "supports_function_calling": false, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "supports_tool_choice": true, "supports_web_search": true, "model_id": "xai/grok-4.1-fast-non-reasoning", "model_name": "Grok 4.1 Fast Non Reasoning", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 2e-7, "output_cost_per_token": 5e-7, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "xai/grok-4.1-fast-reasoning", "model_name": "Grok 4.1 Fast Reasoning", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.19999999999999998, "output_cost_per_million": 0.5, "cache_read_cost_per_token": 5e-8, "cache_read_cost_per_million": 0.049999999999999996, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "supports_tool_choice": true, "supports_web_search": true, "model_id": "xai/grok-4.20-non-reasoning", "model_name": "Grok 4.20 Non Reasoning", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "supports_vision": true, "supports_response_schema": true, "input_cost_per_token": 0.000002, "output_cost_per_token": 0.000006, "max_input_tokens": 2000000, "max_output_tokens": 2000000, "max_tokens": 2000000, "source": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "supports_reasoning": true, "supports_tool_choice": true, "supports_web_search": true, "model_id": "xai/grok-4.20-reasoning", "model_name": "Grok 4.20 Reasoning", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 2, "output_cost_per_million": 6, "cache_read_cost_per_token": 2e-7, "cache_read_cost_per_million": 0.19999999999999998, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_json_mode": true, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 6e-7, "output_cost_per_token": 0.0000022, "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#partner-models", "supported_regions": [ "global" ], "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai-org/glm-4.7-maas", "model_name": "Glm 4.7 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 0.6, "output_cost_per_million": 2.2, "cache_read_cost_per_token": 0, "cache_read_cost_per_million": 0, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false }, { "supports_function_calling": true, "input_cost_per_token": 0.000001, "output_cost_per_token": 0.0000032, "max_input_tokens": 200000, "max_output_tokens": 128000, "max_tokens": 128000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#glm-models", "supported_regions": [ "global" ], "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, "model_id": "zai-org/glm-5-maas", "model_name": "Glm 5 Maas", "provider_id": "vertex", "provider_name": "Google Vertex AI", "input_cost_per_million": 1, "output_cost_per_million": 3.1999999999999997, "cache_read_cost_per_token": 1e-7, "cache_read_cost_per_million": 0.09999999999999999, "cache_write_cost_per_token": 0, "cache_write_cost_per_million": 0, "model_type": "chat", "deprecation_date": null, "supports_vision": false, "supports_json_mode": false, "supports_parallel_functions": false } ]