---
id: "fireworks/ember-1"
also: ["fireworks/ember-1-20260923", "vercel/fireworks/ember-1"]
card_usd_per_m: "3.0 in, 15.0 out, at fireworks"
cheapest_list_usd_per_m: "3.0 in, 15.0 out, at fireworks on openrouter"
cheapest_effective_usd_per_m: "0.4533 in, 15.0 out, at fireworks on vercel"
context: 1048576
max_output: 943718
input: ["text", "image"]
output: ["text"]
released: "2026-09-24"
reasoning: ["max", "high", "low", "none"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 2
gateways: "openrouter (1), vercel (1)"
no_training: 2
trains: 0
retains_prompts: 0
---
# Fireworks: Ember-1

Ember-1 is Fireworks’ research-preview reasoning model built on Kimi K3 for coding and agentic workflows. It supports image input, function calling, and a 1M-token context window. Fireworks reports approximately 40% fewer generated tokens while maintaining comparable quality across its evaluations, helping reduce the cost of workloads with extensive reasoning.