By inception · Updated 2026-11-01 · long-context / RAGcheap high-volumestep-by-step reasoning
Inception: Mercury 3 is best suited for long-context / RAG, cheap high-volume, step-by-step reasoning. Access it through one Appmo API key alongside 444 other models — Appmo's optimizer can route to it automatically when it is the best value for a request.
Not enough posts yet to judge community sentiment. 2 Hacker News stories (258 points) · 8 new GitHub repos mentioning it. How we measure this.
curl https://appmo.com/v1/chat/completions \
-H "Authorization: Bearer $APPMO_KEY" \
-d '{"model":"inception/mercury-3","messages":[{"role":"user","content":"Hello"}]}'How much does Inception: Mercury 3 cost?
Inception: Mercury 3 costs $0.1 per 1M input tokens and $0.35 per 1M output tokens ($0.163 blended), as of 2026-11-01. Prices are expected to fall as competition increases.
What is Inception: Mercury 3 best for?
Inception: Mercury 3 is best suited for long-context / RAG, cheap high-volume, step-by-step reasoning.
How do I use Inception: Mercury 3?
Send requests to Appmo's OpenAI-compatible endpoint with model id "inception/mercury-3" and one API key — no separate provider account needed.
Is Inception: Mercury 3 open source?
We have no record of public weights for Inception: Mercury 3; treat it as a closed model available only through its provider's API.
Can Inception: Mercury 3 create images?
No, Inception: Mercury 3 works with text.