AI TrustMark

Model routing companies, products & suppliers

Choosing which model handles a request for quality, cost or latency. Jobs: quality-based routing; cost-aware fallbacks; a/b between models.

What is Model routing?

Choosing which model handles a request for quality, cost or latency. Jobs: quality-based routing; cost-aware fallbacks; a/b between models.

What problems does it solve?

One model is used for every task, wasting cost or quality.

Typical business use cases

  • Quality-based routing
  • Cost-aware fallbacks
  • A/B between models

Important capabilities

  • Router policy
  • Eval hooks
  • Fallback

What buyers should evaluate

  • How the router decides
  • Eval honesty
  • Lock-in

Risks and governance considerations

Silent routing to a cheaper model that fails the original eval.

Procurement checklist

  • Decision logs
  • Eval set
  • Override

Relevant AI Trustmark assurance

AI Trustmark independent findings appear only when an assessment or certificate exists. Category membership does not imply verification.

Methodology · How verification works

Products and providers

Open a product profile for its catalogue details, or use the provider link for the company profile. Claimed listings appear first, then by name. Payment never changes the order.

  • AI/ML API

    By AI/ML API

    Access 1000+ AI models through a single API for text, image, video, audio, code, embeddings, and more. Compare pricing, latency, and capabilities—all in one place with AIMLAPI. AI/

  • Amazon Bedrock

    By Amazon Web Services

    Amazon Bedrock is AWS's fully managed service for building generative AI applications and agents. It offers access to foundation models from Amazon and other model providers throug

  • Braintrust Gateway

    By Braintrust

    The Braintrust Gateway is a unified LLM API that routes requests to many AI providers through one endpoint. Teams can use their preferred SDK with any supported provider, generate

  • Eden AI Gateway

    By Eden AI

    Access 500+ LLMs and expert AI models through one unified API. Route requests by cost, performance, and region with built-in smart routing and fallbacks. Eden AI Gateway is Eden AI

  • Hugging Face Inference Providers

    By Hugging Face

    Hugging Face operates a model hub, inference tooling and collaboration products for machine-learning teams. Public pages cover hosting, inference endpoints and open-model distribut

  • Martian Gateway

    By Martian

    Measurement. Explanation. Application. That's how we're tackling AI interpretability: the greatest scientific problem of our age. Martian Gateway is Martian's platform, f

  • Bifrost AI Gateway

    By Maxim AI

    Bifrost, from Maxim AI, is an open-source enterprise AI gateway that routes requests to LLM providers through one control plane. It acts as a drop-in replacement for OpenAI, Anthro

  • Not Diamond

    By Not Diamond

    Not Diamond provides LLM routing and evaluation to send each prompt to the best-performing model. Public marketing also emphasises router + eval framing for multi-model stacks. It

  • OpenRouter

    By OpenRouter

    The unified interface for every model. Find the best models & prices for your prompts. OpenRouter is OpenRouter's platform, from OpenRouter, Inc. Published at openrouter.ai. Direct

  • Portkey AI Gateway

    By Portkey

    Democratize and productionize Gen AI across your entire org with Portkey. Portkey AI Gateway is Portkey's platform, from Portkey, Inc. Published at portkey.ai/features/ai-gateway.

  • Requesty LLM Routing Platform

    By Requesty

    Route every LLM call through one OpenAI-compatible API. 600+ models from OpenAI, Anthropic, Google and more. Smart routing, caching, failover, observability, EU data residency and

  • Vercel AI Gateway

    By Vercel

    Vercel AI Gateway is Vercel's platform, from Vercel Inc. Published at vercel.com/ai-gateway. Directory filing: Model routing. Vendor legal name on this product record: Vercel Inc.

Products

Claimed products appear first. Ranking packs and payment do not change this list.

Also used in this category

These products have a different primary category so they do not compete for the same ranking queries. They are listed here because buyers still encounter them in this job.

Related categories

Relevant procurement and assurance guides

Frequently asked questions

What is Model routing?

Choosing which model handles a request for quality, cost or latency. Jobs: quality-based routing; cost-aware fallbacks; a/b between models.

What should not be listed as Model routing?

Products whose buyer job is gateways, hosting, or token-cost dashboards without routing logic. Those belong on their own category page so search queries are not split.

Has AI Trustmark independently assessed every Model routing supplier?

No. A category listing is descriptive. Independent assessment is shown only on company or product pages that carry Trustmark evidence.

What model or provider changes should a buyer insist on being told about?

Material change usually includes a new model family, new region, new subprocessor, new write-capable tool, or a change that affects logging, privacy or human oversight. Those changes should trigger evidence refresh rather than a silent release.

How should buyers verify where AI customer data is processed?

Ask for the named processing locations, cloud regions and any subprocessors that see prompts, files or outputs. A directory listing is not evidence of residency. Independent assessment records the locations that were in scope on the assessment date.

Does a TrustMark on one product cover the rest of the company?

No. Independent assessment is scoped to the named organisation and, where relevant, the named product. Category pages list suppliers as a topic label. They do not imply that every listed company has been assessed.

What incident-handling evidence is useful for AI suppliers?

Buyers should see how AI-specific failures are detected, contained and notified — including unsafe outputs, data leakage and unauthorised agent actions. An incident policy that never mentions models, prompts or tools is incomplete for this class of product.

What security testing evidence should buyers request for an AI product?

Ask what was tested, against which version, whether prompt-injection, data-exfiltration and tenant isolation were in scope, and where failed prompts were stored. A generic ISO certificate or a vendor scanner screenshot is not by itself an AI TrustMark assessment.