BuildLearnCommunity ModelsCheapestCoding Long-contextBest value API key
🎯 Don't want to pick? Send model: "appmo/auto" and Appmo routes each request to the cheapest model that's good enough — cutting your bill up to 40%. See how →
Models › unbiased › Pareto

Pareto — pricing & benchmarks

By unbiased · Updated 2026-07-24 · vision / documents

Pareto costs $2.5 per 1M input tokens and $7.5 per 1M output tokens, with a 262K context window. It is best suited for vision / documents, and is available through one OpenAI-compatible Appmo API key.
$2.5Input / 1M
$7.5Output / 1M
262KContext
—Intelligence
—Coding
—GPQA %
—Speed tok/s

What Pareto is used for

Pareto is best suited for vision / documents. Access it through one Appmo API key alongside 440 other models — Appmo's optimizer can route to it automatically when it is the best value for a request.

Use it via the Appmo API (OpenAI-compatible)

curl https://appmo.com/v1/chat/completions \
  -H "Authorization: Bearer $APPMO_KEY" \
  -d '{"model":"unbiased/pareto","messages":[{"role":"user","content":"Hello"}]}'

FAQ

How much does Pareto cost?
Pareto costs $2.5 per 1M input tokens and $7.5 per 1M output tokens ($3.75 blended), as of 2026-07-24. Prices are expected to fall as competition increases.

What is Pareto best for?
Pareto is best suited for vision / documents.

How do I use Pareto?
Send requests to Appmo's OpenAI-compatible endpoint with model id "unbiased/pareto" and one API key — no separate provider account needed.