LIVE
Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|Mistral Makes Large 4 Available as Open Weights29/10/26 · Mistral AI|Gemini 4 Carbon tops the Artificial Analysis Intelligence Index v529/10/26 · Google|Mistral Large 4 now available on Hugging Face29/10/26 · Mistral AI|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|New benchmark checks whether LLMs actually test their temporal medical claims29/10/26|An ODE-based sampling method speeds up discrete diffusion models29/10/26|OpenAI revises its Model Spec with five guiding values for AI behavior29/10/26 · OpenAI|Inside Proton's internal clash over its AI pivot29/10/26 · Proton|
Appofficial publisher

Not Diamond

App : A product you use directly

Smart router that selects the cheapest model capable of handling each request.

Interesting for reducing costs at constant quality, to be validated on your own data.

Overall score
7.4 /10
Security: nothing to flag
Utility
6.5
Reliability
6.0
Security
No caveat on record
Ease
5 min · Technical

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Engineering teams using coding agents face a cost problem: by default, they reach for the most powerful model for every task, even when a simpler one would do. Not Diamond solves this by automatically selecting the most appropriate model for each request, taking into account cost, complexity, and domain.

In practice, Not Diamond integrates via a secure API into existing infrastructure (harness and gateway of your choice). For each incoming request, the router predicts which model to use among available providers such as Anthropic, OpenAI, or open-source models, then forwards the request to the selected model without changing the rest of the pipeline.

Not Diamond is aimed at development teams running coding agents at scale who want to reduce their inference costs without sacrificing output quality. The tool is SOC-2 and ISO 27001 certified, with customizable ZDR policies and around-the-clock support.

That said, Not Diamond is not designed for individual or occasional use: its positioning and features explicitly target technical teams in production environments, not general users looking to try an AI assistant.

What it offers

  • ·Intelligent routing of requests to the most suitable model across multiple providers (Anthropic, OpenAI, open source).
  • ·Integration via secure API, compatible with existing harnesses and gateways without replacing infrastructure.
  • ·Estimation of potential savings based on number of engineers, monthly spend, and usage growth.
  • ·Protection against vendor lock-in through a stack-agnostic architecture.
  • ·SOC-2 and ISO 27001 compliance with customizable ZDR policies (paid).
  • ·24/7 support for production teams (paid).
  • ·Compatibility with OpenRouter for automatic routing across all available models.

In practice

Price
Freemium
Commercial use
Commercial use: yes
Available on
web, cli

Security and data

Rating
Security: nothing to flag
Your data
Data with the vendor
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 May 2024

How to install Not Diamond

1. Go to https://www.notdiamond.ai and create an account. 2. Retrieve your API key from your personal dashboard. 3. Integrate the Not Diamond API into your existing model gateway following the provided documentation. 4. Configure the desired providers (Anthropic, OpenAI, open source) in the router settings. 5. Test routing on a subset of requests before switching all traffic over. 6. Never share your API key and enable a ZDR policy if your data is sensitive.

In the same category

Whole category Route & save →