Ember-1
by Fireworksfireworks/ember-1
LLMCompare cannot run Ember-1 yet.No route to this model is configured on this site yet. Its prices and parameters are listed below for reference.
See the models that can be run nowEmber-1 at a glance
- Context length
- 1,048,576 tokens
- Maximum output
- 943,718 tokens
- Accepts
- Text, Image
- Returns
- Text
- Features
- ReasoningJSON outputTool callingPrompt cachingImage input
- Reasoning effort levels
maxhighlownoneReasoning can be turned off.- Released
- 24 Sep 2026
- Knowledge cutoff
- Not published
Model facts synced from the OpenRouter model list on 21 Oct 2026.
Ember-1 pricing by route
A route is the service LLMCompare calls to reach the model. Ember-1 has 1 route. Prices are in US dollars.
| Route | On LLMCompare | Inputper 1M tokens | Outputper 1M tokens | Cache readper 1M tokens | Price verified on | Source |
|---|---|---|---|---|---|---|
| OpenRouterDefault | Not configured | $3.00 | $15.00 | $0.30 | openrouter.ai/fireworks/ember-1 |
The cost shown in an LLMCompare report is calculated from these prices as they were at the time of the run.
Cost calculator
Estimate what a batch of calls to Ember-1 costs. The starting numbers are examples. Change them to match your task.
Part of the input tokens above, billed at the cache read price.
Billed in addition to the output tokens.
- Cost per call
- $0.0105
- 13 credits
- Cost of 100 calls
- $1.05
- 1,300 credits
Calculated from the OpenRouter prices verified on 21 Oct 2026. Credits are the cost plus a 20% service fee, at $0.001 per credit, rounded up for each call, with a minimum of 1 per call. A real run is charged for the usage the provider reports.
Parameters you can set
These are the parameters LLMCompare can set when it calls the model through OpenRouter.
| Parameter | Type | Range or options | Default |
|---|---|---|---|
temperature | Number | 0 to 2in steps of 0.1 | Provider default |
top_p | Number | 0 to 1in steps of 0.05 | Provider default |
max_tokens | Integer | 1 to 943,718 | Provider default |
reasoning_effort | One of | maxhighlownone | max |
response_format | One of | textjson_object | Provider default |
About 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%...
Description as published for this model. LLMCompare has not edited it.
Models to compare with Ember-1
Text models from the same provider and models at the nearest price. The order is not a ranking.
| Add to comparison | Model | Context | Max output | Input priceper 1M tokens | Output priceper 1M tokens | Features | Released | On LLMCompare |
|---|---|---|---|---|---|---|---|---|
Claude Sonnet 4.6Anthropicanthropic/claude-sonnet-4.6 | 1M | 128k | $3.00 | $15.00 | ReasoningJSONToolsCacheVision | No route yet | ||
Sonar Pro SearchPerplexityperplexity/sonar-pro-search | 200k | 8k | $3.00 | $15.00 | JSONVision | No route yet | ||
Claude Sonnet 4.5Anthropicanthropic/claude-sonnet-4.5 | 1M | 64k | $3.00 | $15.00 | JSONToolsCacheVision | No route yet | ||
Sonar ProPerplexityperplexity/sonar-pro | 200k | 8k | $3.00 | $15.00 | Vision | No route yet | ||
GPT-5.4OpenAIopenai/gpt-5.4 | 1.05M | 128k | $2.50 | $15.00 | ReasoningJSONToolsCacheVision | No route yet | ||
GPT-4o (2024-05-13)OpenAIopenai/gpt-4o-2024-05-13 | 128k | 4.1k | $5.00 | $15.00 | JSONToolsVision | No route yet |
Questions about Ember-1
- How much does Ember-1 cost?
- On the OpenRouter route, Ember-1 costs $3.00 per 1 million input tokens and $15.00 per 1 million output tokens, in US dollars. Input tokens that Ember-1 reads from the prompt cache cost $0.30 per 1 million tokens. LLMCompare verified this price on 21 Oct 2026.
- What is the context length of Ember-1?
- Ember-1 has a context length of 1,048,576 tokens and returns up to 943,718 output tokens in one call.
- What inputs does Ember-1 accept?
- Ember-1 accepts these inputs: Text, Image. Ember-1 returns: Text.
- Which reasoning effort levels does Ember-1 support?
- Ember-1 supports these reasoning effort levels: max, high, low, none. Reasoning can be turned off for Ember-1.
- Can I test Ember-1 on my own data?
- Not yet. LLMCompare lists the prices and parameters of Ember-1, but no route to Ember-1 is configured on LLMCompare, so it cannot be selected for an evaluation.