Intelligent model router · Verified August 16, 2026

TrustedRouter vs Not Diamond

Not Diamond predicts the best model per request — since August 2026 chiefly for coding agents, via a local proxy that executes through your existing gateway for $0.05 per million tokens routed. TrustedRouter is the execution layer itself: about 550 model routes, provider failover, prepaid billing, and an attested gateway with no durable prompt logs on realtime inference.

Compare details
8decision dimensions
7official sources
1base URL to try TR
Choose Not Diamond when

Its operating model is the feature.

Choose Not Diamond when learned per-prompt selection is the point: custom routers trained on your own scored evals in about an hour, per-step model and reasoning-effort routing for coding agents, and a design that keeps payloads out of the routing vendor's hands while you keep your existing gateway and provider contracts.

Choose TrustedRouter when

Privacy needs evidence.

Choose TrustedRouter when you need the execution layer: one OpenAI-compatible API over about 550 model routes and roughly 49 providers, provider failover, prepaid billing at provider price + 5.5% ($0.01/M floor), ZDR and E2E privacy routes plus an EU jurisdiction route, and a gateway build you can verify by live attestation on three clouds.

DimensionNot DiamondTrustedRouter
DeploymentLocal proxy beside your coding agent; executes through your existing gateway or providerHosted control plane, source-available (BUSL-1.1), with an attested API path
API surfaceselect_model API plus new Apache-2.0 Python/TS SDKs; 2024-era SDKs archived late 2025OpenAI Chat Completions and Responses plus Anthropic Messages
Model access~80 candidate models across 13 providers (May 2026 docs); you supply provider access500+ models across ~50 providers: prepaid, BYOK, and direct
RoutingLearned per-prompt selection plus custom routers trained on your scored evalsProvider fallback plus auto, cheap, fast, free, ZDR, E2E, and EU routes with composable privacy and jurisdiction preferences
ObservabilitySession IDs, savings/usage dashboard; org-wide analytics on enterprise tierMetadata analytics and opt-in external broadcast
Prompt contentCode proxy routes on derived metadata; hosted content generally retained ~90 days where retention is enabledNo durable prompt or output logs on realtime inference; batch is opt-in encrypted retention
VerificationSOC 2 and ISO 27001 claimed in Aug 2026 launch post; no public trust portal foundLive gateway attestation on three clouds, bound to published source and release evidence
Billing$0.05 per 1M tokens routed; inference billed by your own providers or gatewayPrepaid at provider price + 5.5% ($0.01/M floor), or BYOK

What Not Diamond is

Not Diamond predicts which model should handle each request; execution stays on infrastructure you already run. Its June 2026 explainer on routers versus gateways places the product between your agent and your gateway. Not Diamond is San Francisco based, roughly 15 people, on a $2.3M seed raised in July 2024 with angels including Jeff Dean and Tom Preston-Werner. Fortune's August 9, 2026 coverage of the router market names SAP among its enterprise clients.

There are two product generations. The 2024-2025 model-selection API returns a recommendation from a select_model call and your client executes the request itself, with optional fuzzy hashing so the recommendation engine never receives raw query text. Since August 4, 2026 the flagship is Not Diamond Code: a local proxy beside your coding harness that sends derived request metadata to Not Diamond's optimization service, gets back a model and reasoning-effort choice, and executes through your existing gateway or provider. The pricing page lists $0.05 per million tokens routed, a stated 100-150ms of added latency per recommendation, and claimed inference savings of at least 20-40%. Not Diamond does not resell execution; inference is billed by your providers.

Where it is the right choice

Learned per-prompt selection is Not Diamond's specialty, productized end to end. You upload a CSV of prompts, candidate-model responses, and evaluation scores (15 to 10,000 samples) and get a custom router back within about an hour. Their RoRF router is open source under MIT. For coding agents, Not Diamond Code routes each step of a session, choosing both the model and the reasoning effort from request complexity and conversation history.

The architecture also keeps payloads out of Not Diamond's hands. With privacy-preserving routing enabled, Not Diamond Code decides from locally computed features and derived metadata; the launch post says routing works "without ever requiring agent payloads, inputs, or outputs, to leave a developer's local machine." The legacy API went further by never executing calls at all. And because Code rides on your existing gateway and provider contracts, the execution side has no lock-in: you keep negotiated rates and can drop the router without re-plumbing inference.

The load-bearing difference: selection versus execution

TrustedRouter is the layer Not Diamond assumes you already have. We execute the request: one OpenAI-compatible API over about 550 model routes across roughly 49 providers as of August 16, 2026 (see /models), with provider failover, prepaid billing, and BYOK. Not Diamond's docs list about 80 candidate models across 13 providers as of May 2026, and you hold the credentials for each provider it might select.

On the selection axis, Not Diamond's routing is the more sophisticated. TrustedRouter routes are policy pools with composable preferences: trustedrouter/auto, free, cheap, fast, zdr, e2e, and eu, plus provider ordering, privacy floors, and jurisdiction pins. Nothing in our stack trains a per-prompt predictor on your evals. What we add instead is enforcement: trustedrouter/zdr refuses providers below a contractual zero-data-retention tier, and trustedrouter/e2e routes only to confidential-compute providers with provider-side end-to-end encryption (currently tinfoil and phala).

The fees sit on different bases and cannot be equated. Not Diamond charges a flat $0.05 per million tokens routed, on top of whatever your gateway and providers bill for inference. TrustedRouter's prepaid fee is 5.5% of the provider's token price with a $0.01 per million token floor, and that is the whole bill: at a $3.00/M provider price you pay $3.165/M, execution included. One is a selection fee, the other an execution markup; per-model numbers are on /pricing.

Privacy: two models, both real

Not Diamond's strongest privacy argument is structural: in privacy-preserving mode your payload never reaches them. The caveats live in their privacy policy: hosted-service input and output content is retained about 90 days by default, API logs up to 18 months, and for hosted model services opt-out from payload processing is not available. We could not establish whether privacy-preserving routing is on by default.

TrustedRouter sees your prompt, because we execute the call, so we prove what happens to it instead. Realtime inference keeps no durable prompt or output logs; what we retain is metadata: request ids, model and provider, token counts, latency, cost, region, and API-key hash (full list on /privacy). The gateway build serving api.trustedrouter.com is attested on GCP Confidential Space, AWS Nitro Enclaves, and Azure Confidential Containers; anyone can run the verifier against trust.trustedrouter.com, and /security documents the model. The attestation boundary stops at our gateway: downstream model providers are covered by cited policy tiers, except the E2E routes, where the provider's own confidential-compute mechanisms apply.

What we do not claim

Our repos are young: public since late April 2026, with benchmark history from June 2026 — a short operating record. The 99.99% figure on /status is a published availability target with live burn rates, not a certified SLA. We publish a DPA, BAA, and subprocessor list, but no SOC 2 or HIPAA certification today; Not Diamond claims SOC 2 compliance and ISO 27001 certification in its August 2026 launch post, self-reported, with no public trust portal we could find. And our gateway and control plane are source-available under BUSL-1.1, converting to Apache-2.0 four years after each release. Every line that touches your prompt is public, but it is not OSI open source; the SDKs are Apache-2.0 or MIT.

Migration, or coexistence

Not Diamond routes through a gateway by design, so the first question is whether you are replacing it or pairing it. Not Diamond describes Code as gateway-agnostic, so TrustedRouter can serve as the gateway underneath it — though neither company publishes a tested integration. If you consolidate on TrustedRouter alone: legacy API users delete the select_model call and the client-side execution branching, then point one OpenAI-compatible client at our base URL; Not Diamond Code users remove the local proxy from the harness configuration. What does not carry over is the learned selection itself. A custom router trained on your scored evals has no TrustedRouter equivalent, and our policy routes will choose differently, so re-run the same task-specific evals before moving production traffic; see /docs/evals.

Migration shape

Start with one real request.

Decide first whether you are replacing Not Diamond or pairing it with a gateway — it executes through one by design. To consolidate: legacy API users delete the select_model call and client-side execution branching and point an OpenAI-compatible client at the TrustedRouter base URL; Not Diamond Code users remove the local proxy from the harness config. A custom router trained on your evals does not carry over — our routes are policy pools, not learned predictors — so re-run the same task evals before shifting production traffic.

Keep the first test small, stream the response, and compare output, latency, provider selection, and billed usage before moving production traffic.

Agent setup Run a small eval

TrustedRouter sideOpenAI SDK
from openai import OpenAI

client = OpenAI(
    base_url="https://api.trustedrouter.com/v1",
    api_key="sk-tr-v1-...",
)

with client.chat.completions.create(
    model="trustedrouter/zdr",
    messages=[{"role": "user", "content": "Reply PONG"}],
    stream=True,
) as response:
    for chunk in response:
        print(chunk.choices[0].delta.content or "", end="")
Official evidence

Sources checked August 16, 2026

Report a change
All gateways

Questions

Can we run Not Diamond Code on top of TrustedRouter?

Architecturally yes. Not Diamond describes Code as harness- and gateway-agnostic: the local proxy picks the model, then executes through your existing gateway, and TrustedRouter exposes OpenAI-compatible chat at one base URL. Neither company publishes a tested integration for this specific pairing, so run a small eval first. You would pay both fees: $0.05 per million tokens routed to Not Diamond, and provider price + 5.5% to us for execution.

Does TrustedRouter offer learned per-prompt routing like Not Diamond?

No. Our routes (auto, free, cheap, fast, zdr, e2e, eu) are policy pools with composable preferences and provider failover; nothing in our stack trains a predictor on your evals. If squeezing quality-per-dollar out of a fixed candidate set with a router trained on your own scored examples is the goal, Not Diamond is genuinely better at that. What our routes enforce instead is execution-side guarantees: privacy floors and an attested gateway path.

Which vendor handles our prompts more carefully?

They answer different questions. In privacy-preserving mode, Not Diamond says it never receives your payload — a structurally strong design — though where retention is enabled its hosted services generally keep content about 90 days, API logs up to 18 months, and no payload-processing opt-out for hosted model services. TrustedRouter does receive prompts, because we execute the call, and proves handling instead: no durable prompt or output logs on realtime inference, inside a gateway build attested on three clouds at trust.trustedrouter.com.

Workspace access

Sign in

Choose a sign in method to access your TrustedRouter workspace.

By signing in you agree to the terms of service and privacy policy.