@agentjido/llmdb 2026.8.2 → 2026.8.3

package/dist/providers/google_vertex.js

@@ -1,5 +1,5 @@
 import { createProviderCatalog } from "../provider.js";
 
-export const data = {"alias_of":null,"base_url":"https://{region}-aiplatform.googleapis.com","catalog_only":true,"config_schema":[{"doc":"Path to service account JSON file (can also use GOOGLE_APPLICATION_CREDENTIALS env var)","name":"service_account_json","required":false,"type":"string"},{"doc":"Google Cloud project ID (can also use GOOGLE_CLOUD_PROJECT env var)","name":"project_id","required":true,"type":"string"},{"default":"global","doc":"Google Cloud region where Vertex AI is available (default 'global' for newest models)","name":"region","required":false,"type":"string"}],"doc":"https://cloud.google.com/vertex-ai/docs","env":["GOOGLE_APPLICATION_CREDENTIALS","GOOGLE_CLOUD_PROJECT"],"exclude_models":["claude-3-5-sonnet@20241022"],"extra":{"auth_pattern":"service_account","supports_anthropic_models":true,"supports_gemini_models":true},"id":"google_vertex","models":{"claude-3-5-sonnet-v2@20241022":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":null,"family":null,"id":"claude-3-5-sonnet-v2@20241022","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":"Claude Sonnet 3.5 v2","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"claude-haiku-4-5@20251001":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-haiku-4-5@20251001","knowledge":"2025-02-28","last_updated":"2025-10-15","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Haiku 4.5","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"claude-opus-4-1@20250805":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"status":"deprecated","temperature":true},"family":null,"id":"claude-opus-4-1@20250805","knowledge":"2025-03-31","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.1","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"claude-opus-4-5@20251101":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-opus-4-5@20251101","knowledge":"2025-05","last_updated":"2025-11-01","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.5","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-11-01","retired":false,"tags":null},"claude-opus-4-6@default":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-opus-4-6@default","knowledge":"2025-05-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"claude-opus-4-7@default":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"claude-opus-4-7@default","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"claude-opus-4-8@default":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"claude-opus-4-8@default","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-opus-4@20250514":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"status":"deprecated","temperature":true},"family":null,"id":"claude-opus-4@20250514","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"claude-opus-5@default":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"claude-opus-5@default","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"claude-sonnet-4-5@20250929":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-sonnet-4-5@20250929","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"claude-sonnet-4-6@default":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-sonnet-4-6@default","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"claude-sonnet-4@20250514":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"status":"deprecated","temperature":true},"family":null,"id":"claude-sonnet-4@20250514","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"claude-sonnet-5@default":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"claude-sonnet-5@default","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"deepseek-ai/deepseek-v3.1-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":1.7},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/deepseek-v3.1-maas","knowledge":null,"last_updated":"2025-08-28","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"DeepSeek V3.1","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-08-28","retired":false,"tags":null},"deepseek-ai/deepseek-v3.2-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.056,"input":0.56,"output":1.68},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/deepseek-v3.2-maas","knowledge":null,"last_updated":"2026-04-04","lifecycle":null,"limits":{"context":163840,"output":65536},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"DeepSeek V3.2","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"gemini-2.0-flash":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":null,"family":null,"id":"gemini-2.0-flash","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"gemini-3.1-flash-lite","retires_at":"2026-06-01","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-02-05","retired":true,"tags":null},"gemini-2.0-flash-lite":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":null,"family":null,"id":"gemini-2.0-flash-lite","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"gemini-3.1-flash-lite","retires_at":"2026-06-01","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-02-25","retired":true,"tags":null},"gemini-2.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"cache_write":0.383,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":24576,"min":0,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"gemini-2.5-flash","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-2.5-flash-image":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.3,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","open_weights":false,"temperature":true},"family":null,"id":"gemini-2.5-flash-image","knowledge":"2024-06","last_updated":"2025-08-26","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"gemini-2.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.1,"input_audio":0.3,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":24576,"min":512,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"gemini-2.5-flash-lite","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash-Lite","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-07-22","retired":false,"tags":null},"gemini-2.5-flash-lite-preview-09-2025":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":null,"family":null,"id":"gemini-2.5-flash-lite-preview-09-2025","knowledge":"2025-01","last_updated":null,"lifecycle":{"replacement":"gemini-2.5-flash-lite","retires_at":"2026-07-09","status":"active"},"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","code","image","audio","video"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash-Lite Preview 09-2025","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-09-25","retired":false,"tags":null},"gemini-2.5-flash-preview-09-2025":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":null,"family":null,"id":"gemini-2.5-flash-preview-09-2025","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"gemini-2.5-flash","retires_at":"2026-07-09","status":"active"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"gemini-2.5-flash-tts":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.5,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-flash","open_weights":false,"temperature":false},"family":null,"id":"gemini-2.5-flash-tts","knowledge":"2025-01","last_updated":"2025-12-10","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Gemini 2.5 Flash TTS","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"gemini-2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"gemini-2.5-pro","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Pro","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-2.5-pro-tts":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1,"output":20},"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-pro","open_weights":false,"temperature":false},"family":null,"id":"gemini-2.5-pro-tts","knowledge":"2025-01","last_updated":"2025-12-10","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Gemini 2.5 Pro TTS","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"gemini-3-flash-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.5,"input_audio":1,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"gemini-3-pro-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":2,"output":120},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gemini-3-pro-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana Pro","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"gemini-3.1-flash-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.5,"output":60},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"temperature":true},"family":null,"id":"gemini-3.1-flash-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image","video","pdf"],"output":["text","image"]},"model":null,"name":"Nano Banana 2","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"gemini-3.1-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"input_audio":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-flash-lite","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"gemini-3.1-flash-lite-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"input_audio":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-flash-lite-preview","knowledge":"2025-01","last_updated":"2026-03-03","lifecycle":{"replacement":"gemini-3.1-flash-lite","retires_at":"2026-07-09","status":"active"},"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite Preview","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-03-03","retired":false,"tags":null},"gemini-3.1-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-pro-preview","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"gemini-3.1-pro-preview-customtools":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-pro-preview-customtools","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview Custom Tools","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"gemini-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"input_audio":1.5,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"gemini-3.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash Lite","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"gemini-3.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"input_audio":1.5,"output":7.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"gemini-embedding-001":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.15,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","open_weights":false,"temperature":false},"family":null,"id":"gemini-embedding-001","knowledge":"2025-05","last_updated":"2025-05-20","lifecycle":{"retires_at":"2026-07-14","status":"active"},"limits":{"context":2048,"output":1},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemini Embedding 001","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-05-20","retired":false,"tags":null},"gemini-flash-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"input_audio":1.5,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-flash-latest","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini Flash Latest","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"gemini-flash-lite-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"input_audio":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"temperature":true},"family":null,"id":"gemini-flash-lite-latest","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini Flash-Lite Latest","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"meta/llama-3.3-70b-instruct-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.72,"output":0.72},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"meta/llama-3.3-70b-instruct-maas","knowledge":"2023-12","last_updated":"2025-04-29","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"meta/llama-4-maverick-17b-128e-instruct-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.35,"output":1.15},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"structured_output":true,"temperature":true},"family":null,"id":"meta/llama-4-maverick-17b-128e-instruct-maas","knowledge":"2024-08","last_updated":"2025-04-29","lifecycle":null,"limits":{"context":524288,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Maverick 17B 128E Instruct","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"moonshotai/kimi-k2-thinking-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2-thinking-maas","knowledge":"2024-08","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Thinking","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-oss-120b-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09,"output":0.36},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/gpt-oss-120b-maas","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.25},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"deprecated","temperature":true},"family":null,"id":"openai/gpt-oss-20b-maas","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"qwen/qwen3-235b-a22b-instruct-2507-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.22,"output":0.88},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b-instruct-2507-maas","knowledge":null,"last_updated":"2025-08-13","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-08-13","retired":false,"tags":null},"zai-org/glm-4.7-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"toggle"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-4.7-maas","knowledge":"2025-04","last_updated":"2026-01-06","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-01-06","retired":false,"tags":null},"zai-org/glm-5-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"toggle"}],"status":"deprecated","temperature":true},"family":null,"id":"zai-org/glm-5-maas","knowledge":null,"last_updated":"2026-02-11","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-02-11","retired":false,"tags":null}},"name":"Google Vertex AI","pricing_defaults":null};
+export const data = {"alias_of":null,"base_url":"https://{region}-aiplatform.googleapis.com","catalog_only":true,"config_schema":[{"doc":"Path to service account JSON file (can also use GOOGLE_APPLICATION_CREDENTIALS env var)","name":"service_account_json","required":false,"type":"string"},{"doc":"Google Cloud project ID (can also use GOOGLE_CLOUD_PROJECT env var)","name":"project_id","required":true,"type":"string"},{"default":"global","doc":"Google Cloud region where Vertex AI is available (default 'global' for newest models)","name":"region","required":false,"type":"string"}],"doc":"https://cloud.google.com/vertex-ai/docs","env":["GOOGLE_APPLICATION_CREDENTIALS","GOOGLE_CLOUD_PROJECT"],"exclude_models":["claude-3-5-sonnet@20241022"],"extra":{"auth_pattern":"service_account","supports_anthropic_models":true,"supports_gemini_models":true},"id":"google_vertex","models":{"claude-3-5-sonnet-v2@20241022":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":null,"family":null,"id":"claude-3-5-sonnet-v2@20241022","knowledge":null,"last_updated":null,"lifecycle":null,"limits":null,"modalities":null,"model":null,"name":"Claude Sonnet 3.5 v2","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"claude-haiku-4-5@20251001":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"cache_write":1.25,"input":1,"output":5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Claude model for responsive assistance, classification, and lightweight agents","family":"claude-haiku","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-haiku-4-5@20251001","knowledge":"2025-02-28","last_updated":"2025-10-15","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Haiku 4.5","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-10-15","retired":false,"tags":null},"claude-opus-4-1@20250805":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"status":"deprecated","temperature":true},"family":null,"id":"claude-opus-4-1@20250805","knowledge":"2025-03-31","last_updated":"2025-08-05","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.1","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"claude-opus-4-5@20251101":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high"]},{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-opus-4-5@20251101","knowledge":"2025-05","last_updated":"2025-11-01","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.5","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-11-01","retired":false,"tags":null},"claude-opus-4-6@default":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"High-end Claude for difficult coding, planning, and slower expert reasoning","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-opus-4-6@default","knowledge":"2025-05-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.6","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-02-05","retired":false,"tags":null},"claude-opus-4-7@default":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Stronger Opus tier for advanced software work and high-stakes reasoning","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"claude-opus-4-7@default","knowledge":"2026-01-31","last_updated":"2026-04-16","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.7","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-04-16","retired":false,"tags":null},"claude-opus-4-8@default":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"claude-opus-4-8@default","knowledge":"2026-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4.8","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"claude-opus-4@20250514":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":1.5,"cache_write":18.75,"input":15,"output":75},"deprecated":false,"extra":{"attachment":true,"description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"status":"deprecated","temperature":true},"family":null,"id":"claude-opus-4@20250514","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":32000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 4","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"claude-opus-5@default":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.5,"cache_write":6.25,"input":5,"output":25},"deprecated":false,"extra":{"attachment":true,"description":"Strongest Claude Opus model for coding, agents, and professional work","family":"claude-opus","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"claude-opus-5@default","knowledge":"2026-05","last_updated":"2026-07-24","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Opus 5","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-07-24","retired":false,"tags":null},"claude-sonnet-4-5@20250929":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-sonnet-4-5@20250929","knowledge":"2025-07-31","last_updated":"2025-09-29","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.5","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-09-29","retired":false,"tags":null},"claude-sonnet-4-6@default":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Claude workhorse for coding agents, careful analysis, and production cost control","family":"claude-sonnet","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"effort","values":["low","medium","high","max"]},{"min":1024,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"claude-sonnet-4-6@default","knowledge":"2025-08-31","last_updated":"2026-03-13","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4.6","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-02-17","retired":false,"tags":null},"claude-sonnet-4@20250514":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.3,"cache_write":3.75,"input":3,"output":15},"deprecated":false,"extra":{"attachment":true,"description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","family":"claude-sonnet","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"min":1024,"type":"budget_tokens"}],"status":"deprecated","temperature":true},"family":null,"id":"claude-sonnet-4@20250514","knowledge":"2025-03-31","last_updated":"2025-05-22","lifecycle":null,"limits":{"context":200000,"output":64000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 4","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-05-22","retired":false,"tags":null},"claude-sonnet-5@default":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"cache_write":2.5,"input":2,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Everyday Claude agent model for coding, planning, browsing, and general work","family":"claude-sonnet","open_weights":false,"provider":{"npm":"@ai-sdk/google-vertex/anthropic"},"reasoning_options":[{"type":"toggle"},{"type":"effort","values":["low","medium","high","xhigh","max"]}],"temperature":false},"family":null,"id":"claude-sonnet-5@default","knowledge":"2026-01-31","last_updated":"2026-06-30","lifecycle":null,"limits":{"context":1000000,"output":128000},"modalities":{"input":["text","image","pdf"],"output":["text"]},"model":null,"name":"Claude Sonnet 5","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-06-30","retired":false,"tags":null},"deepseek-ai/deepseek-v3.1-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":1.7},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/deepseek-v3.1-maas","knowledge":null,"last_updated":"2025-08-28","lifecycle":null,"limits":{"context":163840,"output":32768},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"DeepSeek V3.1","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-08-28","retired":false,"tags":null},"deepseek-ai/deepseek-v3.2-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.056,"input":0.56,"output":1.68},"deprecated":false,"extra":{"attachment":false,"description":"DeepSeek chat model for instruction following, coding, and analysis","family":"deepseek","open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"deepseek-ai/deepseek-v3.2-maas","knowledge":null,"last_updated":"2026-04-04","lifecycle":null,"limits":{"context":163840,"output":65536},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"DeepSeek V3.2","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"gemini-2.0-flash":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":null,"family":null,"id":"gemini-2.0-flash","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"gemini-3.1-flash-lite","retires_at":"2026-06-01","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-02-05","retired":true,"tags":null},"gemini-2.0-flash-lite":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":true,"extra":null,"family":null,"id":"gemini-2.0-flash-lite","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"gemini-3.1-flash-lite","retires_at":"2026-06-01","status":"retired"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-02-25","retired":true,"tags":null},"gemini-2.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"cache_write":0.383,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":24576,"min":0,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"gemini-2.5-flash","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-2.5-flash-image":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.3,"output":30},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana image model for fast generation, edits, and character-consistent assets","family":"gemini-flash","open_weights":false,"temperature":true},"family":null,"id":"gemini-2.5-flash-image","knowledge":"2024-06","last_updated":"2025-08-26","lifecycle":null,"limits":{"context":32768,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-08-26","retired":false,"tags":null},"gemini-2.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.01,"input":0.1,"input_audio":0.3,"output":0.4},"deprecated":false,"extra":{"attachment":true,"description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"toggle"},{"max":24576,"min":512,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"gemini-2.5-flash-lite","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash-Lite","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-07-22","retired":false,"tags":null},"gemini-2.5-flash-lite-preview-09-2025":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":null,"deprecated":false,"extra":null,"family":null,"id":"gemini-2.5-flash-lite-preview-09-2025","knowledge":"2025-01","last_updated":null,"lifecycle":{"replacement":"gemini-2.5-flash-lite","retires_at":"2026-07-09","status":"active"},"limits":{"context":1048576,"output":65535},"modalities":{"input":["text","code","image","audio","video"],"output":["text"]},"model":null,"name":"Gemini 2.5 Flash-Lite Preview 09-2025","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-09-25","retired":false,"tags":null},"gemini-2.5-flash-preview-09-2025":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":null,"deprecated":false,"extra":null,"family":null,"id":"gemini-2.5-flash-preview-09-2025","knowledge":null,"last_updated":null,"lifecycle":{"replacement":"gemini-2.5-flash","retires_at":"2026-07-09","status":"active"},"limits":null,"modalities":null,"model":null,"name":null,"pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":null,"retired":false,"tags":null},"gemini-2.5-flash-tts":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.5,"output":10},"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-flash","open_weights":false,"temperature":false},"family":null,"id":"gemini-2.5-flash-tts","knowledge":"2025-01","last_updated":"2025-12-10","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Gemini 2.5 Flash TTS","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"gemini-2.5-pro":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.125,"input":1.25,"output":10},"deprecated":false,"extra":{"attachment":true,"description":"Google's proven reasoning model for coding, math, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"max":32768,"min":128,"type":"budget_tokens"}],"temperature":true},"family":null,"id":"gemini-2.5-pro","knowledge":"2025-01","last_updated":"2025-06-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","audio","video","pdf"],"output":["text"]},"model":null,"name":"Gemini 2.5 Pro","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-06-17","retired":false,"tags":null},"gemini-2.5-pro-tts":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":1,"output":20},"deprecated":false,"extra":{"attachment":false,"description":"Speech generation model for controllable voice, narration, and audio delivery","family":"gemini-pro","open_weights":false,"temperature":false},"family":null,"id":"gemini-2.5-pro-tts","knowledge":"2025-01","last_updated":"2025-12-10","lifecycle":null,"limits":{"context":32768,"output":16384},"modalities":{"input":["text"],"output":["audio"]},"model":null,"name":"Gemini 2.5 Pro TTS","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-09-30","retired":false,"tags":null},"gemini-3-flash-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.05,"input":0.5,"input_audio":1,"output":3},"deprecated":false,"extra":{"attachment":true,"description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3-flash-preview","knowledge":"2025-01","last_updated":"2025-12-17","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3 Flash Preview","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-12-17","retired":false,"tags":null},"gemini-3-pro-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":2,"output":120},"deprecated":false,"extra":{"attachment":true,"description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","family":"gemini-pro","open_weights":false,"reasoning_options":[],"temperature":true},"family":null,"id":"gemini-3-pro-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":65536,"output":32768},"modalities":{"input":["text","image"],"output":["text","image"]},"model":null,"name":"Nano Banana Pro","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"gemini-3.1-flash-image":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"text":true,"tool_calls":false},"tools":{"enabled":false,"parallel":false,"streaming":false,"strict":false}},"catalog_only":true,"cost":{"input":0.5,"output":60},"deprecated":false,"extra":{"attachment":true,"description":"Image model for prompt-driven generation, editing, and visual design workflows","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","high"]}],"temperature":true},"family":null,"id":"gemini-3.1-flash-image","knowledge":"2025-01","last_updated":"2026-05-28","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text","image","video","pdf"],"output":["text","image"]},"model":null,"name":"Nano Banana 2","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-28","retired":false,"tags":null},"gemini-3.1-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"input_audio":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-flash-lite","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"gemini-3.1-flash-lite-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"input_audio":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-flash-lite-preview","knowledge":"2025-01","last_updated":"2026-03-03","lifecycle":{"replacement":"gemini-3.1-flash-lite","retires_at":"2026-07-09","status":"active"},"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Flash Lite Preview","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-03-03","retired":false,"tags":null},"gemini-3.1-pro-preview":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-pro-preview","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"gemini-3.1-pro-preview-customtools":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.2,"input":2,"output":12},"deprecated":false,"extra":{"attachment":true,"description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","family":"gemini-pro","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.1-pro-preview-customtools","knowledge":"2025-01","last_updated":"2026-02-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.1 Pro Preview Custom Tools","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-02-19","retired":false,"tags":null},"gemini-3.5-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"input_audio":1.5,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"gemini-3.5-flash-lite":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.03,"input":0.3,"output":2.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.5-flash-lite","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.5 Flash Lite","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"gemini-3.6-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"input_audio":1.5,"output":7.5},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.6-flash","knowledge":"2026-03","last_updated":"2026-07-21","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.6 Flash","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-07-21","retired":false,"tags":null},"gemini-3.7-flash":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.075,"input":0.75,"input_audio":0.75,"output":3.75},"deprecated":false,"extra":{"attachment":true,"description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-3.7-flash","knowledge":"2026-03","last_updated":"2026-08-13","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini 3.7 Flash","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-08-13","retired":false,"tags":null},"gemini-embedding-001":{"aliases":[],"base_url":null,"capabilities":null,"catalog_only":true,"cost":{"input":0.15,"output":0},"deprecated":false,"extra":{"attachment":false,"description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","family":"gemini","open_weights":false,"temperature":false},"family":null,"id":"gemini-embedding-001","knowledge":"2025-05","last_updated":"2025-05-20","lifecycle":{"retires_at":"2026-07-14","status":"active"},"limits":{"context":2048,"output":1},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Gemini Embedding 001","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-05-20","retired":false,"tags":null},"gemini-flash-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.15,"input":1.5,"input_audio":1.5,"output":9},"deprecated":false,"extra":{"attachment":true,"description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","family":"gemini-flash","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"structured_output":true,"temperature":true},"family":null,"id":"gemini-flash-latest","knowledge":"2025-01","last_updated":"2026-05-19","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini Flash Latest","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-19","retired":false,"tags":null},"gemini-flash-lite-latest":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.025,"input":0.25,"input_audio":0.5,"output":1.5},"deprecated":false,"extra":{"attachment":true,"description":"Low-latency Gemini model for high-volume multimodal and agent workloads","family":"gemini-flash-lite","open_weights":false,"reasoning_options":[{"type":"effort","values":["minimal","low","medium","high"]}],"temperature":true},"family":null,"id":"gemini-flash-lite-latest","knowledge":"2025-01","last_updated":"2026-05-07","lifecycle":null,"limits":{"context":1048576,"output":65536},"modalities":{"input":["text","image","video","audio","pdf"],"output":["text"]},"model":null,"name":"Gemini Flash-Lite Latest","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-05-07","retired":false,"tags":null},"meta/llama-3.3-70b-instruct-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.72,"output":0.72},"deprecated":false,"extra":{"attachment":false,"description":"Open Llama instruction model for multilingual chat, reasoning, and coding","family":"llama","open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"meta/llama-3.3-70b-instruct-maas","knowledge":"2023-12","last_updated":"2025-04-29","lifecycle":null,"limits":{"context":128000,"output":8192},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Llama 3.3 70B Instruct","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"meta/llama-4-maverick-17b-128e-instruct-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":false},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.35,"output":1.15},"deprecated":false,"extra":{"attachment":true,"description":"Open multimodal Llama model for strong reasoning and fast responses","family":"llama","open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"structured_output":true,"temperature":true},"family":null,"id":"meta/llama-4-maverick-17b-128e-instruct-maas","knowledge":"2024-08","last_updated":"2025-04-29","lifecycle":null,"limits":{"context":524288,"output":8192},"modalities":{"input":["text","image"],"output":["text"]},"model":null,"name":"Llama 4 Maverick 17B 128E Instruct","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-04-29","retired":false,"tags":null},"moonshotai/kimi-k2-thinking-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.5},"deprecated":false,"extra":{"attachment":false,"description":"Kimi reasoning model for long-horizon research, planning, and tool use","family":"kimi-thinking","interleaved":{"field":"reasoning_content"},"open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"moonshotai/kimi-k2-thinking-maas","knowledge":"2024-08","last_updated":"2025-11-13","lifecycle":null,"limits":{"context":262144,"output":262144},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Kimi K2 Thinking","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-11-13","retired":false,"tags":null},"openai/gpt-oss-120b-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.09,"output":0.36},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"temperature":true},"family":null,"id":"openai/gpt-oss-120b-maas","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 120B","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"openai/gpt-oss-20b-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.07,"output":0.25},"deprecated":false,"extra":{"attachment":false,"description":"Open-weight GPT model for self-hosted reasoning and instruction-following workloads","family":"gpt-oss","open_weights":true,"reasoning_options":[{"type":"effort","values":["low","medium","high"]}],"status":"deprecated","temperature":true},"family":null,"id":"openai/gpt-oss-20b-maas","knowledge":null,"last_updated":"2025-08-05","lifecycle":null,"limits":{"context":131072,"output":32768},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GPT OSS 20B","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-08-05","retired":false,"tags":null},"qwen/qwen3-235b-a22b-instruct-2507-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.22,"output":0.88},"deprecated":false,"extra":{"attachment":false,"description":"Qwen instruction model for multilingual chat, reasoning, and tool use","family":"qwen","open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"reasoning_options":[],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"qwen/qwen3-235b-a22b-instruct-2507-maas","knowledge":null,"last_updated":"2025-08-13","lifecycle":null,"limits":{"context":262144,"output":16384},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"Qwen3 235B A22B Instruct","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2025-08-13","retired":false,"tags":null},"zai-org/glm-4.7-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"input":0.6,"output":2.2},"deprecated":false,"extra":{"attachment":false,"description":"GLM vision model for visual reasoning, documents, and multimodal agents","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"toggle"}],"status":"deprecated","structured_output":true,"temperature":true},"family":null,"id":"zai-org/glm-4.7-maas","knowledge":"2025-04","last_updated":"2026-01-06","lifecycle":null,"limits":{"context":200000,"output":128000},"modalities":{"input":["text","pdf"],"output":["text"]},"model":null,"name":"GLM-4.7","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-01-06","retired":false,"tags":null},"zai-org/glm-5-maas":{"aliases":[],"base_url":null,"capabilities":{"chat":true,"embeddings":false,"json":{"native":false,"schema":false,"strict":false},"reasoning":{"enabled":true},"rerank":false,"streaming":{"tool_calls":true},"tools":{"enabled":true}},"catalog_only":true,"cost":{"cache_read":0.1,"input":1,"output":3.2},"deprecated":false,"extra":{"attachment":false,"description":"Flagship GLM model for hybrid reasoning, coding, and agentic engineering","family":"glm","interleaved":{"field":"reasoning_content"},"open_weights":true,"provider":{"api":"https://${GOOGLE_VERTEX_ENDPOINT}/v1/projects/${GOOGLE_VERTEX_PROJECT}/locations/${GOOGLE_VERTEX_LOCATION}/endpoints/openapi","npm":"@ai-sdk/openai-compatible"},"reasoning_options":[{"type":"toggle"}],"status":"deprecated","temperature":true},"family":null,"id":"zai-org/glm-5-maas","knowledge":null,"last_updated":"2026-02-11","lifecycle":null,"limits":{"context":202752,"output":131072},"modalities":{"input":["text"],"output":["text"]},"model":null,"name":"GLM-5","pricing":null,"provider":"google_vertex","provider_model_id":null,"release_date":"2026-02-11","retired":false,"tags":null}},"name":"Google Vertex AI","pricing_defaults":null};
 const provider = /* @__PURE__ */ createProviderCatalog(data);
 export default provider;