Ember-1
Ember-1 is a specialized reasoning model developed by Fireworks Research based on Kimi K3. It is designed to optimize efficiency by producing concise reasoning traces while supporting both text and image inputs.
Ember-1 specs and pricing
- Provider: Fireworks
- Released: September 24, 2026
- Context window: 1M tokens
- Max output: 944K tokens
- Input: text, images
- Output: text
- Price: $3.00 input / $15 output per 1M tokens
- Reasoning: yes
- Tool calling: yes
What Ember-1 is good at
- Complex tasks requiring multi-step reasoning
- Analyzing documents alongside visual data
- Applications that benefit from integrated tool calling
To-dos to try with Ember-1
- Analyze this technical diagram and explain the underlying logic step-by-step.
- Use the provided tool to search for current market data and summarize the findings.
- Evaluate these two project proposals and identify potential logical inconsistencies.
FAQ
- What is the primary focus of the Ember-1 model? Ember-1 is a specialized reasoning model engineered to produce efficient, shorter reasoning traces.
- Can this model process visual information? Yes, Ember-1 supports both text and image inputs.
- How much does Ember-1 cost? Ember-1 costs $3.00 per million input tokens and $15 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 10.5 credits ($1 = 100 credits).
- What is the context window of Ember-1? Ember-1 can read up to 1M tokens at once and write up to 944K tokens in one reply.
- Can I use Ember-1 without coding? Yes. In todo.is you pick Ember-1 as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.