RXed AI News

AI news with a spine.
@RXed_EU

Workload costs

Nobody knows what two million tokens a day means. So pick the job and how often you run it — the bill comes out per model, as a range, with every assumption visible below. Ranges, not single numbers: the inputs are ranges too, and a decimal here would be a guess in a suit.

Class:
ModelClass$/day$/month Reasoning Coding Agentic

Straight per-token arithmetic on list prices: no caching, no batching discount, no volume deal. Thinking tokens bill as output, so treat reasoning models as a floor. Weight class is kept because class also tells you something about quality. Capability & cost data: Artificial Analysis

Every number above rests on these. They are rules of thumb, published so you can disagree with them:

Task archetypeTokens inTokens outBasis
Classify & routeRead one short item and pick a label or destination — inbox triage, ticket routing, lead scoring.800–1,800120–300one email or ticket including a short quoted thread; output is a label plus a one-line reason
Extract fields from a documentPull structured data out of an invoice, receipt, order or contract page.600–1,600150–400one OCR'd page; output is a JSON record of 8-20 fields
Draft a replyWrite a customer-ready answer grounded in the incoming message and a short context block.1,200–3,000250–600incoming message plus tone/policy context; output is a full email
Answer from a knowledge baseRetrieval-augmented answer over your own documents — SOP lookup, policy question, product detail.2,500–6,000250–700question plus 3-6 retrieved chunks; output is a cited answer
Summarise something longCondense a meeting transcript, report or thread into a briefing.6,000–20,000400–1,200a 30-60 minute transcript or a 10-25 page document
Write a piece of contentProduce a post, newsletter section or product description from a brief and source material.2,000–8,000800–2,500brief plus reference material; output is publishable copy
Multi-step agent runA goal the model pursues over several tool calls — each step re-reads the growing context.15,000–60,0001,500–6,0006-15 tool-calling steps with accumulated context; the dominant cost is re-reading, not writing
Scheduled checkA small recurring evaluation — did anything change, does this look wrong, is this worth alerting.400–1,20080–250one status payload or diff; output is a verdict plus a short reason

Blueprints that run no model at all (The billable-hours tracker, The lead pipeline that doesn't leak, The client file portal you own, The service-due reminder engine, The downtime alarm, The contract signing station, The 3-2-1 backup strategy, The privacy-first analytics box…) cost hosting, not tokens — they are not in the picker, because a token bill for them would be fiction.