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 › fireworks › Fireworks: Ember-1

Fireworks: Ember-1 — pricing & benchmarks

By fireworks · Updated 2026-07-24 · long-context / RAGvision / documentsstep-by-step reasoning

Fireworks: Ember-1 costs $3 per 1M input tokens and $15 per 1M output tokens, with a 1M context window. It is best suited for long-context / RAG, vision / documents, step-by-step reasoning, and is available through one OpenAI-compatible Appmo API key.
$3Input / 1M
$15Output / 1M
1MContext
—Intelligence
—Coding
—GPQA %
—Speed tok/s

What Fireworks: Ember-1 is used for

Fireworks: Ember-1 is best suited for long-context / RAG, vision / documents, step-by-step reasoning. Access it through one Appmo API key alongside 451 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":"fireworks/ember-1","messages":[{"role":"user","content":"Hello"}]}'

FAQ

How much does Fireworks: Ember-1 cost?
Fireworks: Ember-1 costs $3 per 1M input tokens and $15 per 1M output tokens ($6 blended), as of 2026-07-24. Prices are expected to fall as competition increases.

What is Fireworks: Ember-1 best for?
Fireworks: Ember-1 is best suited for long-context / RAG, vision / documents, step-by-step reasoning.

How do I use Fireworks: Ember-1?
Send requests to Appmo's OpenAI-compatible endpoint with model id "fireworks/ember-1" and one API key — no separate provider account needed.