LLMCost
~unbiased

Pareto Latest API Pricing

Pareto Latest costs $0.800 per 1M input tokens and $3.20 per 1M output tokens (cache reads: $0.030). Context window: 1.0M. Prices verified 2026-10-21 · source

🔔 Price alerts coming soon
Price history
2026-10-14 → 2026-10-21 · 59 daily snapshots
inputoutputinput -68% over windowoutput -57.3%

Rebuilt daily from our snapshot archive — the chart appears once a model has 5+ snapshots of history.

Pricing behavior
2 price changes in the last 59 daily snapshots
Last move (2026-10-18): input -68%

From our own daily snapshot archive — independent of provider announcements.

Input / 1M tokens
$0.800
Output / 1M tokens
$3.20
Context window
1.0M
Max output
131K

Token economics

Token typePricevs base input
Standard input$0.800—
Cache read$0.030−96%
Output$3.20—

Prompt caching stores repeated context server-side: reads cost far less, but writes carry a one-time premium.

What would Pareto Latest cost you per month?

WorkloadRequests/moAvg tokens (in/out)Est. monthly cost
Light chatbot10,000800 / 400$19.20
Coding agent5,0008,000 / 2,000$64.00
RAG pipeline30,0004,000 / 500$144.00
Doc summarizer2,00020,000 / 1,000$38.40

Estimates use list prices without prompt caching. Caching can cut input cost by up to 90% on repeated context.

About Pareto Latest

This model always redirects to the latest model in the Pareto family.

Compare Pareto Latest with

Popular head-to-heads — see all on the comparisons index.

Frequently asked questions

How much does Pareto Latest cost?

Pareto Latest costs $0.800 per 1M input tokens and $3.20 per 1M output tokens; cached input tokens cost $0.030 per 1M. Verified 2026-10-21 — provider source.

What is the context window?

1.0M tokens, with up to 131K output tokens per response. That's roughly 1311 pages of text in a single request.

Does it support prompt caching?

Yes — cached input is $0.030/1M, about 96% cheaper than standard input. Agents and RAG workloads with repeated context benefit most.

What's a cheaper alternative?

ScaleDown: Summarize saves about 98% on a typical workload with comparable quality.

Official resources