Ir para o conteúdo
AI.info

AI Tools

Not Diamond Model Router

Not Diamond Model Router: preços, capacidades, atualizações e alternativas, lidos nas páginas do próprio desenvolvedor.

O site de Not Diamond Model Router

Em inglês

Key facts

Price
Paid plans: see pricing Read on notdiamond.ai
Free plan
No Read on notdiamond.ai
Platforms
Web · API
API
Yes
Open source
Not stated on the maker’s pages
Certifications
SOC 2 Type II · ISO 27001 Read on notdiamond.ai
Last update
4 Aug 2026 Read on notdiamond.ai
Prices checked
26 Oct 2026 Read on notdiamond.ai

Not Diamond is a model-routing service for developers and teams. It can select a model for a request, train custom routers on evaluation data, and optimize prompts. Its coding-agent router also considers session state and reasoning effort when recommending models.

It integrates with existing gateways or providers rather than replacing them; model calls use the configured provider or gateway. The API supports Python, TypeScript, and REST. Pay-as-you-go routing is priced per million tokens; Enterprise pricing is not listed. Not Diamond Code is offered through a gated waitlist.

Category
Developer Tools
Read from the maker’s pages
2026-11-18

Company

Not Diamond

Features

  • Routes requests to a suitable model from a candidate pool
  • Trains custom routers using a team's data and evaluation criteria
  • Optimizes prompts to adapt them to different models
  • Supports Python, TypeScript, and REST API integration
  • Offers quality, cost, and latency routing trade-off modes
  • Selects models and reasoning effort across coding-agent sessions
  • Provides privacy-preserving routing using derived request metadata
  • Includes a savings and usage dashboard on the Pay-as-you-go tier

Use cases

  • Route coding-agent steps to models based on session needs and cost
  • Choose models for application requests without hard-coding one model
  • Train a router against domain-specific evaluation data
  • Optimize prompts for use with different models
  • Balance response quality, inference cost, or latency for an application

Pricing

Paid plans: see pricing

Prices checked
2026-10-26

Pay-as-you-go

$0.05 per million tokens routed

  • $0.05 per million tokens routed
  • Multi-harness support
  • Multi-provider support
  • Savings and usage dashboard
  • Continuous learning from harness usage

Enterprise

price on request

  • Volume-based discounts
  • Organization-wide analytics
  • Advanced security and admin controls
  • SSO with SAML
  • Privacy-preserving deployment

Capabilities

  • Choice of models — “Intelligent model routing predicts which AI model to use for each prompt, maximizing accuracy while minimizing cost.” source
  • No code retained — “With privacy preserving routing enabled, Not Diamond bases routing decisions solely on derived request metadata and locally computed features, meaning we never see your payload, inputs, or outputs.” source
  • API — “Python , TypeScript , and REST API support : Seamlessly integrate Not Diamond across a variety of technology stacks.” source
  • Official SDKs — “Typescript SDK” source

Latest updates

Where it works

Web · API

Security

  • SOC 2 Type II — “Our information security management system is certified to ISO/IEC 27001, and we are SOC 2 Type II compliant.” source
  • SOC 2 — “Our information security management system is certified to ISO/IEC 27001, and we are SOC 2 Type II compliant.” source
  • ISO 27001 — “Our information security management system is certified to ISO/IEC 27001, and we are SOC 2 Type II compliant.” source

Alternatives to Not Diamond Model Router

  • Helicone

    Helicone routes, logs, and analyzes AI application requests, helping teams debug model calls, track costs, and manage prompts.

  • OpenRouter

    OpenRouter provides one API to access and route requests across AI models from multiple providers, with model selection, fallbacks, and usage tracking.

  • LiteLLM

    LiteLLM routes requests to multiple LLM providers through one OpenAI-compatible API, with a Python SDK and a self-hosted gateway.

  • Braintrust

    Braintrust helps teams inspect AI-agent activity, evaluate outputs, and find production issues.

  • Fireworks AI

    Fireworks AI hosts, routes, and trains open and custom models for applications, teams, and research.

  • Langfuse

    Langfuse traces AI applications, manages prompts, and evaluates model and agent outputs using cloud or self-hosted deployments.

Questions about Not Diamond Model Router

Is Not Diamond Model Router free?

No. The maker’s pricing page lists no free plan for Not Diamond Model Router. Prices checked on 26 Oct 2026.

How much does Not Diamond Model Router cost?

The plans on the maker’s pricing page: Pay-as-you-go ($0.05 per million tokens routed) and Enterprise (price on request). Prices checked on 26 Oct 2026.

Does Not Diamond Model Router have an API?

Yes. The maker’s pages state that Not Diamond Model Router has an API. Read on the maker’s pages on 18 Nov 2026.

Which platforms does Not Diamond Model Router run on?

Not Diamond Model Router runs on Web and API, as its maker’s pages state. Read on the maker’s pages on 18 Nov 2026.

Is Not Diamond Model Router still available?

Yes, as of 18 Nov 2026: its maker’s pages were read that day and carried no notice that Not Diamond Model Router has ended.

What changed recently in Not Diamond Model Router?

The latest entry in its maker’s changelog: 4 Aug 2026, “Not Diamond Code: intelligent model routing for coding agents”. Before it: 20 Jan 2026, “Prompt Optimization is now generally available”. Changelog checked on 16 Nov 2026.

Sources

Not confirmed

Open source
The pages read do not establish whether the current product is open source or specify a license.
Latest version
No current product version or router model name was identified on the pages read.
Official website