news

The problem with AI model routing

Techzine’s Erik van Klinken argues cross-provider model routing can quietly backfire: each hop to a cheaper model triggers a cold start that throws away prompt-cache and context savings, so recomputation can cost more than routing saves.

Published 2026-07-06Source: Techzine Global
Generated Tokenmaxxing editorial thumbnail for The problem with AI model routing

Why it matters

Routing is pitched as the cure for runaway token bills, yet if it wrecks caching it can inflate them. With Anthropic’s inference margins reportedly 70% and $20/100/200 plans heavily subsidized, buyers chasing per-token savings may be tuning the wrong layer.

Tokenmaxxing read

The counterintuitive lever is caching, not routing. Van Klinken expects provider-side routing — staying inside one vendor to keep the cache warm — to win, deepening lock-in. Uber reportedly spent a full year’s AI budget within four months on Claude Code tokens before it clicked.

Source takeaway

Erik van Klinken (Techzine Global): a month ago buyers still reached for the largest model 95% of the time; with Fable 5 priced at twice per token of Opus 4.8, he bets vendors’ own routers, not third-party ones, capture the efficiency trade.

Topic links

Related projects

Tools that match this angle

#1Direct
Routing

LiteLLM

BerriAI/litellm

An OpenAI-compatible gateway and SDK for calling many model providers with budgets, logging, load balancing, guardrails, and cost tracking.

52.8K9.5KSource-available
gatewaycost-trackingrouting
#2Direct
Observability

Langfuse

langfuse/langfuse

Open-source LLM engineering platform for observability, traces, metrics, evals, prompt management, datasets, and playground workflows.

30.6K3.2KSource-available
tracesevalscosts
#10Direct
Routing

Portkey Gateway

Portkey-AI/gateway

An AI gateway for routing across LLMs with guardrails, provider abstraction, and an OpenAI-compatible API surface.

12.3K1.2KMIT
gatewayguardrailsrouting
Related feed

More source-linked context

Generated Tokenmaxxing editorial thumbnail for Why Token Optimization Is a Gift to the Hyperscalers
newsU
newsmedium review

Why Token Optimization Is a Gift to the Hyperscalers

UncoverAlpha's Rihard Jarc argues the pivot from tokenmaxxing to token optimization — routing cheap work to cheaper models — won't shrink AI bills. It multiplies token volume, and the hyperscalers renting the compute collect either way.

tokenmaxxingmodel-routerai-spend
Read note
IT Pro source artwork
agentIP
agent

‘What we’re seeing right now is just rapid escalation in AI token spend’: Accenture tells staff to stop using AI for unnecessary tasks amid surging costs

Leaked internal audio, reported by IT Pro via 404 Media, shows Accenture telling staff to stop burning AI tokens on low-value work like turning PDFs into slide decks, as its agentic-AI lead flags a sharp jump in token spend.

tokenmaxxingagentstoken-consumption
Read note
Generated Tokenmaxxing editorial thumbnail for Coinbase halves its AI bill with cheaper defaults, routing, and caching
newsTD
news

Coinbase halves its AI bill with cheaper defaults, routing, and caching

Coinbase CEO Brian Armstrong says five levers — cheaper model defaults (GLM 5.2, Kimi 2.7), task routing, caching, lean context, and spend visibility — cut the company’s AI bill roughly in half despite rising token volume.

tokenmaxxingcost-governancemodel-routing
Read note