AWS
on Orq.ai
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.
Capabilities:
Chat
Code
Embeddings
Reasoning
Vision
Models Supported:
eu.anthropic.claude-opus-5
global.anthropic.claude-opus-5
us.anthropic.claude-opus-5
eu.anthropic.claude-sonnet-5
global.anthropic.claude-sonnet-5
Provider HQ:
Amazon Web Services, headquartered in Seattle, Washington.
Access AWS Bedrock through Orq.ai’s AI Router
Amazon Bedrock is AWS’s managed platform for foundation models, offering first‑party models (for example Nova, Titan) and selected third‑party providers under a single AWS service. These models cover high‑end reasoning, general‑purpose coding, and cost‑efficient high‑volume use cases.
Orq.ai supports major Qwen variants (for example Qwen‑Max, Qwen‑Plus, Qwen‑Turbo and newer Qwen3.x tiers), with availability depending on provider access, region, and your workspace configuration.
AWS Bedrock models available on Orq.ai
Exact model names and availability may vary by region and account; this table uses representative Bedrock text/chat tiers mapped into a premium, balanced, and cost‑efficient grouping within Orq.
Model | Type | Context / scope | Best for | Pricing tier |
|---|---|---|---|---|
Amazon Nova Pro (or similar high‑end Bedrock chat model) | Chat / reasoning / vision | Large context (check Bedrock/Orq docs for current limits) | Complex reasoning, analysis, coding, and high‑stakes tasks where you want AWS’s strongest Bedrock chat/reasoning model in your region | Premium – Bedrock standard API pricing; typically a higher‑cost tier per million tokens vs other Bedrock options |
Amazon Nova Lite / Titan Text Express (balanced tier) | Chat / reasoning / coding | Medium–large context (verify in Bedrock/Orq docs) | Everyday production workloads, RAG, coding, product features, and workflows that balance quality with cost and latency | Mid‑tier – Bedrock standard API pricing; moderate per‑million token cost, suitable for most production use cases |
Amazon Nova Micro / Titan Text Lite (or similar faster tier) | Chat / fast / cost‑efficient | Medium context (confirm in docs) | Fast, lower‑cost tasks such as classification, extraction, lightweight chat, routing, and high‑volume support workflows | Cost‑efficient – Bedrock standard API pricing; lower per‑million token cost aimed at high‑throughput workloads |
Pricing tiers here are approximate and based on AWS Bedrock’s public model pricing; Orq.ai may apply its own billing or BYOK mapping. Always check Orq.ai’s pricing page and your configured AWS/BEDROCK provider for current per‑model rates, quotas, and billing details.
Why use AWS Bedrock through Orq.ai?
Capability | Provider / models | Direct | Through Orq.ai |
|---|---|---|---|
Chat | AWS Bedrock chat models (for example Nova, Titan Text chat) | Call Bedrock models directly via the AWS API for chat, reasoning, coding, and multimodal tasks | Use Bedrock models through Orq.ai’s OpenAI‑compatible endpoint, adding routing, tracing, evals, budgets, and governance controls around each request |
Code | Bedrock models tuned or suitable for coding/analysis | Use Bedrock directly for code generation, debugging, refactoring, and agentic coding workflows. | Route coding workloads through Orq.ai, compare Bedrock models against other providers, and monitor cost, latency, and quality from one control layer |
Embeddings | Embedding providers configured in Orq.ai (including, where applicable, AWS embeddings) | Bedrock focuses primarily on chat/reasoning and some embeddings; choice depends on your AWS setup | Use Orq.ai to route embedding workloads to supported embedding providers (including AWS where configured) while keeping Bedrock models for reasoning, generation, and agent steps |
This gives teams a practical way to use AWS Bedrock models where they perform best while centralising routing, observability, evals, and cost controls across the wider model stack.
Pricing
Bedrock model pricing may differ depending on whether you:
connect your own AWS account and Bedrock usage (BYOK), or
use Bedrock models billed through Orq.ai where available
Check the Orq.ai pricing page and your workspace’s provider configuration for current per‑model rates, quotas, and plan details.
Centralized cost tracking
AWS Bedrock usage can be tracked per project, team, and route inside Orq.ai so you can see which workflows are driving Bedrock spend and adjust routing or budgets accordingly.
Budgets and limits
You can set per‑team or per‑workflow budgets and rate limits around Bedrock usage in Orq.ai to prevent surprise bills and enforce governance rules.
Compatible frameworks and tools
Orq.ai exposes AWS Bedrock models through:
an OpenAI‑compatible API layer, and
native SDKs and router integrations where applicable.
That means:
Popular AI frameworks (for example, OpenAI‑compatible clients and orchestration libraries) can talk to Bedrock models via Orq’s router.
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 Bedrock, depending on model and integration configuration.
Check the Orq.ai integration docs for the latest supported frameworks and tools for AWS Bedrock.
FAQs
Do I need a separate AWS account to use Bedrock through Orq.ai?
You can either connect your own AWS Bedrock account and credentials into Orq.ai or, where available, use Bedrock models billed via Orq.ai; the exact options depend on your Orq plan, region, and how AWS is configured in your workspace. In both cases, Orq.ai gives you one place to manage routing, observability, and cost controls around that Bedrock usage.
Can I route only some workflows to AWS and others to different providers?
Yes. You define routes per workflow in Orq.ai and decide which ones should use Bedrock vs other models, so you can reserve AWS for specific regions, compliance needs, or workloads while sending other tasks to different providers.
Does using AWS Bedrock 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
AWS
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
Z.ai
Use Z.ai’s GLM‑5 family through a single Orq.ai integration. Route models such as GLM‑5.2, GLM‑5.1, GLM‑5, GLM‑5‑Turbo, GLM‑4.7, and GLM‑4.7‑FlashX via Orq’s AI Router for chat, reasoning, coding, multilingual tasks, vision, and cost‑efficient high‑volume workloads.
Chat
Image Generation
Reasoning
Vision
Models:
glm-5.2
glm-5.1
glm-5v-turbo
