Atlas / Models / Fireworks / Fireworks: Ember-1

Fireworks: Ember-1✓ Catalog verified

fireworks/ember-1

Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...

Input price
$3.00 /1M
Output price
$15.00 /1M
Context
1.0M
Modalities
textimage
Released
Sep 24, 2026
Tool calling
✓ Yes
Atlas signal
93/100
01

Overview

Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...

Access: available through the official Fireworks API. Context window: 1.0M.

Pricing and metadata from the ModelsAtlas catalog.Last refreshed Sep 25, 2026
02

Specifications

API identifierfireworks/ember-1
ProviderFireworks
Model typeMultimodal LLM
Context window1.0M catalog
Input modalitiestext · image
Output modalitiestext
ReleasedSep 24, 2026
ModeratedNo
Architecture modalitytext+image->text
Supported parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokenspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Source: provider documentation + catalog feedMethodology →
03

Pricing

Live pricing components for fireworks/ember-1 as published in the catalog.

$3.00
Input /1M
$15.00
Output /1M
—
Per request
—
Per image
Pricing componentRaw unit priceNormalizedUnit
Prompt tokens$0.000003$3.00 / 1MPer input token
Completion tokens$0.000015$15.00 / 1MPer output token
Request feeN/AN/APer request
Image feeN/AN/APer image unit
Web search feeN/AN/APer search request
Source: catalog pricing feedCompare all pricing →Cheapest models →
04

Cost calculator

Estimate monthly spend from your own token volumes.

Scale / Volume

Estimated Total Cost

$4.5Calculated from current list pricing in the ModelsAtlas catalog.
05

Capabilities

CapabilityStatusWhat it means
Visual Understanding✓ SupportedImage and document analysis support
Audio ProcessingNot advertisedSpeech and voice aligned flows
Tool Calling✓ SupportedSupports tools / function calling
Self-HostingNot advertisedDeploy outside managed APIs
Derived from catalog capability tags and supported parameters
06

Capability signals

Directional signals derived from model metadata and capability tags — not official benchmark submissions.

Fireworks: Ember-1
MMLU Signal (Reasoning)
97signal
Coding Signal (HumanEval proxy)
92signal
Math Signal (GSM8K proxy)
87signal
Science Signal (GPQA proxy)
95signal
Estimated from metadata — not an official benchmark runAll benchmarks →Methodology →
07

Quick start

Call Fireworks: Ember-1 through an OpenAI-compatible client.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="fireworks/ember-1",
    messages=[{"role": "user", "content": "Explain quantum physics."}]
)

print(response.choices[0].message.content)
08

Alternatives

Closest models by context window from a different provider.

09

Sources & attribution

Pricing and metadata are maintained in the ModelsAtlas catalog.

Capability bars use metadata tags — directional estimates onlyHow we source and verify data →
10

Frequently asked questions

How much does Fireworks: Ember-1 cost?

$3.00 per 1M input tokens and $15.00 per 1M output tokens on the official Fireworks API.

What is the context window of Fireworks: Ember-1?

Fireworks: Ember-1 supports up to 1.0M tokens of context.

Does Fireworks: Ember-1 support tool / function calling?

Yes, Fireworks: Ember-1 supports tool / function calling — you can register tools and the model will emit structured tool calls.

How do I access Fireworks: Ember-1?

Use the official Fireworks API with the model id `fireworks/ember-1`. See the Quick start section above for code examples.