Benchable
Text input
Image input
Text output
Author's Description
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%...
Key Specifications
Cost
$$$$$
Context
1M
Released
Sep 23, 2026
Supported Parameters
This model supports the following parameters:
Top P
Structured Outputs
Logprobs
Response Format
Stop
Frequency Penalty
Tools
Logit Bias
Temperature
Tool Choice
Reasoning
Include Reasoning
Presence Penalty
Top Logprobs
Max Tokens
Features
This model supports the following features:
Tools
Structured Outputs
Response Format
Reasoning
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $3 |
| Completion | $15 |
| Input Cache Read | $0.3 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
Fireworks
|
Fireworks | fireworks/ember-1-20260923 | 1M | $3 / 1M tokens | $15 / 1M tokens |
Benchmark Results
| Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
|---|