TokenRoute
Get started
Back to models

Fireworks: Ember-1

fireworks/ember-1

Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...

Try in Playground

Pricing

Input$2.10 /M
Output$10.50 /M
Cache read$0.2100 /M

Specs

Context length1M tokens
Max output943.7K tokens
Inputtext, image
Outputtext

Quickstart

Point the OpenAI SDK at https://tokenroute.app/api/v1 and use a TokenRoute API key.

bash
curl https://tokenroute.app/api/v1/chat/completions \
  -H "Authorization: Bearer $TOKENROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "fireworks/ember-1",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Supported parameters

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