Wafer logo

Wafer

Access models hosted through Wafer using Orq.ai for reasoning, coding, agentic, and high-throughput AI workloads through one API.

8 models · 10 direct routes · 1 region

Direct regions:

Global

Loading pricing…

Role

Inference provider

HQ

San Francisco, California

Role

Inference provider

HQ

San Francisco, California

Direct API routes

8 models · 10 direct routes · 1 region

Global

Zero data retention

10 of 10 routes

Capabilities

Code

Vision

Reasoning

Chat

Partner routes

Access Wafer through Orq.ai’s AI Router

Wafer is an AI inference platform focused on serving open and open-weight models with high-throughput, predictable performance. Its platform supports language, reasoning, coding, and agentic workloads through managed inference and compatible API interfaces.

Wafer models available on Orq.ai

Compare the Wafer-hosted models currently available through Orq.ai, including their supported capabilities, context windows, pricing, and availability.

8 models · newest first · base prices from this provider

8

Model
Input types
Region
ZDR
Input price
Output price
Intelligence
Context (tokens)
Release date
Select up to 3 models using the checkboxes to compare
Loading models…

EU and ZDR reflect all listed model routes, including partners.

Model
Select up to 3 models using the checkboxes to compare
Loading models…

EU and ZDR reflect all listed model routes, including partners.

Model
Select up to 3 models using the checkboxes to compare
Loading models…

EU and ZDR reflect all listed model routes, including partners.

Why use Wafer through Orq.ai?

Chat & reasoning

Route Wafer-hosted models through Orq.ai while applying routing, tracing, evaluations, budgets, and governance controls around each request.

Coding

Route coding workloads through Orq.ai, compare Wafer with other providers, and monitor cost, latency, and quality from a shared control layer.

High-throughput agents

Route throughput-heavy agent workloads to Wafer while using other providers for tasks with different capability, cost, or regional requirements.

Pricing

Pricing varies by model, usage, access method, and billing configuration. Services may use consumption pricing, subscriptions, or usage allowances; caching, privacy controls, and other options may affect billing. Check Orq.ai and your Wafer setup for current rates.

Works with

Wafer supports common model-inference API formats. Compatible applications can incorporate Wafer-hosted models through Orq.ai depending on the model, endpoint, and workspace configuration.

FAQs

Do I need a separate Wafer account to use Wafer through Orq.ai?

You can connect supported Wafer credentials to Orq.ai or use other available access options depending on your workspace, plan, and region.

Can I route only some workflows to Wafer and others to different providers?

Yes. Orq.ai lets you route different workloads to different providers, so you can use Wafer for high-throughput, coding, agentic, or privacy-sensitive workloads while routing other requests elsewhere.

Does using Wafer through Orq.ai add latency?

Orq.ai adds a routing layer between your application and the model provider. Teams can monitor end-to-end latency and use routing, caching, and provider controls where appropriate to manage performance.

Alternatives to Wafer

Meta logo

Meta

Explore Meta-created models through Orq.ai. Direct pricing and route statistics use Meta-hosted routes; other hosting providers are listed separately.

Image generation

Speech

Vision

Reasoning

Chat

Google logo

Google

Explore Google-created models, including Gemini and Gemma, through Orq.ai. Direct pricing and route statistics on this page use Google AI; other hosts are listed separately.

Code

Image generation

Speech

Embeddings

Vision

Reasoning

Chat

inception logo

Inception

Access Inception’s Mercury diffusion language models through Orq.ai for fast reasoning, coding, agentic, and other latency-sensitive AI workloads.

Code

Vision

Reasoning

Chat

Anthropic logo

Anthropic

Access Anthropic’s Claude models through Orq.ai for reasoning, coding, vision, and agentic workflows through one API.

Vision

Reasoning

Chat

Take control of your AI