Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Utilizing the top-performing model for each specific request allows us to surpass the capabilities of any individual model. Martian consistently exceeds the performance of GPT-4 as demonstrated in OpenAI's evaluations (open/evals). We transform complex, opaque systems into clear and understandable representations. Our router represents the pioneering tool developed from our model mapping technique. Additionally, we are exploring a variety of applications for model mapping, such as converting intricate transformer matrices into programs that are easily comprehensible for humans. In instances where a company faces outages or experiences periods of high latency, our system can seamlessly reroute to alternative providers, ensuring that customers remain unaffected. You can assess your potential savings by utilizing the Martian Model Router through our interactive cost calculator, where you can enter your user count, tokens utilized per session, and monthly session frequency, alongside your desired cost versus quality preference. This innovative approach not only enhances reliability but also provides a clearer understanding of operational efficiencies.
Description
Weave Router serves as a sophisticated routing service designed for workflows involving coding agents. It evaluates incoming coding requests and efficiently directs them to appropriate language models based on factors such as the complexity of the task, costs associated with cache switching, and the progress of the task being handled. Developers have the option to integrate various coding tools like Claude Code, Codex, GitHub Copilot CLI, OpenCode, and Pi through a convenient installer, or they can opt for manual configuration using Cursor. Additionally, the service acts as a compatible proxy for different API formats from providers like Anthropic, OpenAI, and Gemini, accommodating features such as streaming, tool interactions, and image input processing. Teams looking for flexibility can choose between using Weave’s hosted service or deploying the Apache-2.0-licensed proxy with their own provider credentials, which allows for enhanced control over deployment and associated costs. While self-hosting empowers teams to manage their infrastructure and expenses, the hosted plans come with separate billing arrangements. Ultimately, Weave Router is tailored for developers and engineering teams aiming to streamline the routing of coding-agent model requests through either managed services or their own self-hosted systems, ensuring optimal performance and cost-effectiveness.
API Access
Has API
Yes
API Access
Has API
Yes
Screenshots View All
No images available
Integrations
Claude Code
No
Codex CLI
No
Cursor
No
GitHub Copilot CLI
No
Node.js
Yes
OpenCode
No
Python
Yes
Integrations
Claude Code
Yes
Codex CLI
Yes
Cursor
Yes
GitHub Copilot CLI
Yes
Node.js
No
OpenCode
Yes
Python
No
Pricing Details
No price information available.
Free Trial
No
Free Version
No
Pricing Details
$10/month
The hosted Code Max plan is $10 per month. The self-hosted proxy is available under the Apache-2.0 license with no software license fee; model-provider and infrastructure charges may apply.
Free Trial
No
Free Version
Yes
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
Yes
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
Martian
Founded
2022
Country
United States
Website
withmartian.com
Vendor Details
Company Name
Weave
Founded
2024
Country
United States
Website
weaveos.com/products/router