Vertex AI
on Orq.ai
Use Google Vertex AI’s Gemini models through a single Orq.ai API. Route models such as Gemini 2.5 Pro, Gemini 2.5 Flash, and Gemini 1.5 Flash via Orq’s AI Router for chat, reasoning, coding, and multimodal workloads.
Capabilities:
Models Supported:
No models available
Provider HQ:
Google (Google Cloud / Gemini Enterprise Agent Platform), headquartered in Mountain View, California.
Access Google Vertex AI through Orq.ai’s AI Router
Vertex AI (now part of the Gemini Enterprise Agent Platform) is Google Cloud’s managed platform for foundation models, offering Gemini text and multimodal models plus additional third‑party and open models through Model Garden. These models cover high‑end reasoning, general‑purpose coding, and cost‑efficient high‑volume use cases.
Orq.ai supports major Gemini variants on Vertex AI (for example Gemini 2.5 Pro, Gemini 2.5 Flash, Gemini 1.5 Flash), with availability depending on project setup, region, and your workspace configuration.
Google Vertex AI models available on Orq.ai
Model (example) | Type | Context | Best for | Pricing tier (reference) |
|---|---|---|---|---|
Gemini 2.5 Pro (Vertex AI) | Chat / reasoning / vision | Up to around 1–2M tokens (check Vertex / Orq docs for current limits) | Complex reasoning, analysis, coding, and high‑stakes tasks where you want Google Cloud’s most capable Gemini model in your region | Premium – Gemini 2.5 Pro on Vertex AI priced around 1.25 USD / 1M input tokens and 10.00 USD / 1M output tokens for base context, rising to about 2.50 input / 15.00 output at higher context tiers |
Gemini 1.5 Pro / Gemini 3.1 Pro (where available) | Chat / reasoning / coding | Long context (up to 2M tokens) | Large‑context RAG, long documents, multi‑step workflows, and enterprise applications needing long‑context reasoning | Alternative premium – Gemini 1.5 Pro priced roughly 1.25–2.50 USD / 1M input and 5–10 USD / 1M output depending on context tier |
Gemini 2.5 Flash (Vertex AI) | Chat / reasoning / coding | Around 1M tokens | Everyday production workloads, RAG, coding, product features, and workflows that balance quality with cost and latency | Mid‑tier – Gemini 2.5 Flash around 0.30 USD / 1M input tokens and 2.50 USD / 1M output tokens |
Gemini 1.5 Flash / Flash‑8B
Chat / fast / cost‑efficient
About 1M tokens
Fast, lower‑cost tasks such as classification, extraction, lightweight chat, routing, and high‑volume support workflows
Cost‑efficient – Gemini 1.5 Flash around 0.075 USD / 1M input and 0.30 USD / 1M output tokens; Gemini 1.5 Flash‑8B around 0.037 USD input and 0.15 USD output per 1M tokens
Pricing tiers here are approximate and based on Vertex AI’s public Gemini pricing; Orq.ai may apply its own billing or BYOK mapping. Always check Orq.ai’s pricing page and your configured Vertex provider for current per‑model rates, quotas, and billing details.
Why use Google Vertex AI through Orq.ai?
Capability | Provider / models | Direct | Through Orq.ai |
|---|---|---|---|
Chat | Gemini chat models on Vertex (for example Gemini 2.5 Pro, 2.5 Flash, 1.5 Flash) | Call Gemini models directly via Vertex AI’s generative AI APIs for chat, reasoning, coding, and multimodal tasks | Use Vertex‑hosted Gemini models through Orq.ai’s OpenAI‑compatible endpoint, adding routing, tracing, evals, budgets, and governance controls around each request |
Code | Gemini models tuned or suitable for coding/analysis | Use Gemini on Vertex AI for code generation, debugging, refactoring, and agentic coding workflows | Route coding workloads through Orq.ai, compare Gemini on Vertex against other providers, and monitor cost, latency, and quality from one control layer |
Embeddings / multimodal | Gemini models and Vertex embedding endpoints | Vertex AI offers Gemini text, image, and multimodal support, as well as embedding models such as Embedding 003 | Use Orq.ai to route embedding or multimodal workloads to Vertex while keeping other providers for complementary tasks, with unified observability |
This gives teams a practical way to use Vertex-hosted models where it performs best while centralising routing, observability, evals, and cost controls across the wider model stack.
Pricing
Model rates
Gemini on Vertex AI pricing may differ depending on whether you:
connect your own Google Cloud project and Vertex AI (BYOK), or
use Vertex models billed through Orq.ai where available
Key patterns from current public pricing:
Gemini 2.5 Pro: about 1.25 USD / 1M input and 10.00 USD / 1M output tokens (higher at larger context tiers).
Gemini 2.5 Flash: about 0.30 USD / 1M input and 2.50 USD / 1M output tokens.
Gemini 1.5 Flash: about 0.075 USD / 1M input and 0.30 USD / 1M output tokens.
Embedding 003: roughly 0.02 USD per 1M tokens for both input and output
Vertex AI also charges separately for training, custom deployment, and certain grounding features, but those costs typically sit outside pure token usage.
Check the Orq.ai pricing page and your workspace’s provider configuration for current per‑model rates, quotas, and plan details.
Compatible frameworks and tools
Orq.ai exposes Vertex AI through:
a dedicated Vertex AI provider configuration in the Model Garden / AI Router, and
an OpenAI‑compatible API layer for applications that expect that interface.
That means:
Popular AI frameworks (for example, OpenAI‑compatible clients and orchestration libraries) can talk to Gemini on Vertex via Orq’s router by pointing at Orq’s OpenAI‑compatible endpoint while Orq routes to Vertex behind the scenes.
Code assistants and IDE tools that support MCP or OpenAI‑compatible APIs (Cursor, VS Code, Claude Desktop, Warp, Zed, and similar tools you’ve documented) can route through Orq.ai to Gemini on Vertex, depending on model and integration configuration.
Check the Orq.ai integration docs for the latest supported frameworks and tools for Vertex AI.
FAQs
Do I need a separate Google Cloud account to use Vertex AI through Orq.ai?
You can either connect your own Google Cloud project, Vertex AI configuration, and service account into Orq.ai or, where available, use Vertex models billed via Orq.ai; the exact options depend on your Orq plan, region, and how Vertex is configured in your workspace. In both cases, Orq.ai gives you one place to manage routing, observability, and cost controls around that Vertex AI usage.
Can I route only some workflows to Vertex AI and others to different providers?
Yes. You define routes per workflow in Orq.ai and decide which ones should use Gemini on Vertex vs other models, so you can reserve Vertex for specific regions, compliance needs, or long‑context / multimodal workloads while sending other tasks to different providers.
Does using Vertex AI through Orq.ai add latency?
Orq.ai is designed as a lightweight router layer, so the added overhead is small compared to the model’s own latency. You can use routing policies, caching, and provider selection to keep end‑to‑end performance within your targets.
Alternatives to
Vertex AI
Anthropic
Use Claude Opus 4.7, Sonnet 4.6, Haiku 4.5, and other supported Claude models through one API.
Chat
Code
Reasoning
Vision
Models:
claude-opus-5
claude-sonnet-5
claude-fable-5
Open AI
Use OpenAI's foundation models through a single Orq.ai API. Route models such as GPT-4.1, GPT-4.1-mini, o3-mini, and GPT-4o-class models via Orq's AI Router for chat, reasoning, coding, and multimodal workloads.
Chat
Code
Image Generation
Reasoning
Speech
Vision
Models:
gpt-5.5 (EU)
gpt-5.6-luna (EU)
gpt-5.6-sol (EU)
Google AI
Use Google’s Gemini models through a single Orq.ai API. Route models such as Gemini 3.1 Pro, Gemini 2.5 Flash, and Gemini 2.0 Flash‑Lite via Orq’s AI Router for chat, reasoning, coding, and multimodal workloads.
Chat
Code
Embeddings
Image Generation
Reasoning
Speech
Vision
Models:
gemini-3.5-flash-lite (Gemini API)
gemini-3.6-flash (Gemini API)
Gemini 3 Pro Image
AWS
Use AWS Bedrock’s foundation models through a single Orq.ai API. Route models such as Amazon Nova, Amazon Titan Text, and compatible third‑party models exposed via Bedrock through Orq’s AI Router for chat, reasoning, coding, and multimodal workloads.
Chat
Code
Embeddings
Reasoning
Vision
Models:
eu.anthropic.claude-opus-5
global.anthropic.claude-opus-5
us.anthropic.claude-opus-5
