Ember-1
Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40% fewer tokens than the base model while maintaining comparable quality across Fireworks' evaluations. It is suited for coding, knowledge work, and agentic workflows where reasoning cost and latency matter.
fireworks/ember-1
- Contexto
- 1M tokens
- Máx. completion
- 943,718
- Tools
- Sí
- JSON
- Sí
- Lanzamiento
- 2026-09-24
Llámalo desde Geek Hub
El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "fireworks/ember-1",
"messages": [{"role": "user", "content": "Hola"}]
}'Preguntas frecuentes
- ¿Qué es Ember-1?
- Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40% fewer tokens than the base model while maintaining comparable quality across Fireworks' evaluations. It is suited for coding, knowledge work, and agentic workflows where reasoning cost and latency matter. Ember-1 corre en el API de Geek Hub (compatible con OpenAI). Id: fireworks/ember-1.
- ¿Ember-1 es gratis?
- No. El input cuesta $3.2702 / 1M tokens y el output $16.3509 / 1M tokens en Geek Hub (markup incluido).
- ¿Cuál es el contexto de Ember-1?
- Ember-1 tiene una ventana de 1M tokens. Soporta hasta 943,718 tokens de completion.
- ¿Ember-1 soporta tool calling y structured outputs?
- Ember-1 acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
- ¿Cuándo se lanzó Ember-1?
- Ember-1 se lanzó el 24 de septiembre de 2026.