llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model Directory

Scoring & Data

Scoring & Data
1367 models808 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll Benchmarks
llmboard.aiCopyright 2026 llmboard.ai

Fireworks AI model product

Ember 1

Ember 1 is a Fireworks Research model built on Moonshot Kimi K3 that uses shorter reasoning traces while matching K3-max quality on Fireworks' evaluations.

Updated Oct 23, 2026. Default version: Ember-1

LLMBoard Score71.1Ember-1
Coverage20%4 benchmark families
Context window1MTokens
Official input price$3Fireworks AI API

On this page

  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Runtime
  • Specification
  • Versions
  • Similar models
  • About
  • FAQ

Ember 1 Capability Profile

This profile uses the model's current scored version. Arena ratings and prices are shown separately.

Ember-1 LLMBoard score breakdown

Ember 1 Benchmark Results

Benchmark scores for Ember-1.

4 rows
Columns

Show columns

Sort by
Benchmark
Score
Rank
Participants
Percentile
Evidence
Evaluated
BenchmarkSWE-Bench VerifiedScore92.20%Rank03Participants120Percentile98.32%EvidenceCEvaluatedOct 22, 2026
BenchmarkTau2 AirlineScore66.00%Rank08Participants26Percentile72.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkDeepSWE 1.1Score75.20%Rank09Participants51Percentile84.00%EvidenceCEvaluatedOct 22, 2026
BenchmarkTerminal-Bench 2.1Score82.00%Rank22Participants48Percentile55.32%EvidenceCEvaluatedOct 22, 2026

Ember 1 Arena Results

Preference and agent-evaluation results for the default version.

No Arena results

The default version does not have a matching Arena result yet.

Ember 1 Pricing

Official vendor API pricing appears first, followed by individual provider offers.

Official API
$3 input, $15 output per 1M
Official provider
Fireworks AI
Lowest third-party
From $3 input, $15 output per 1M via Kilo Gateway
Tracked offerings
6
6 rows
Columns

Show columns

Sort by
Provider
Provider model ID
Region
Input / 1M
Output / 1M
Context
Updated
ProviderKilo GatewayProvider model IDfireworks/ember-1RegionglobalInput / 1M$3Output / 1M$15Context1MUpdatedOct 23, 2026
ProviderOpenRouterProvider model IDfireworks/ember-1RegionglobalInput / 1M$3Output / 1M$15Context1MUpdatedOct 23, 2026
ProviderFireworks AIProvider model IDaccounts/fireworks/models/ember-1RegionglobalInput / 1M$3Output / 1M$15Context1MUpdatedOct 23, 2026
ProviderVercel AI GatewayProvider model IDfireworks/ember-1RegionglobalInput / 1M$3Output / 1M$15Context1MUpdatedOct 23, 2026
ProviderNanoGPTProvider model IDfireworks/ember-1RegionglobalInput / 1M$3Output / 1M$15Context1MUpdatedOct 23, 2026
ProviderCloudflare AI GatewayProvider model IDfireworks/ember-1RegionglobalInput / 1M$3Output / 1M$15Context1MUpdatedOct 23, 2026

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Ember 1 Runtime Performance

Provider-specific output speed and catalog latency for Ember-1. Runtime does not affect the capability score.

No runtime data

No provider-specific speed or latency record is linked to the default version yet.

Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.

Ember 1 Specifications

Technical details for the model's default version.

Version
Ember-1
Released
Sep 23, 2026
Knowledge cutoff
Unknown
Parameters
2.8T
Context window
1M
Max output
N/A
Inputs
text
Outputs
text
Open weights
No
License
Proprietary

Ember 1 Versions

Available versions of this model. The score column identifies the version used in the overall ranking.

1 row
Columns

Show columns

Sort by
Version
Released
LLMBoard
Parameters
Context
Max output
Open weights
License
VersionEmber-1ReleasedSep 23, 2026LLMBoard71.07Parameters2.8TContext1MMax outputN/AOpen weightsNoLicenseProprietary

Models similar to Ember 1

Recommendations prioritize the same model type and family, then the closest LLMBoard score.

#61-0.04
OP

GPT-5.2-Pro

OpenAI

71.03 LLMBoard

Details
#62-0.10
AC

Qwen3.7 Plus

Alibaba Cloud / Qwen Team

70.97 LLMBoard

Details
#59+0.13
ME

Muse Spark

Meta

71.20 LLMBoard

Details
#63-0.32
OP

GPT-6-Luna

OpenAI

70.75 LLMBoard

Details
#64-0.36
AN

Claude Sonnet 4.6

Anthropic

70.71 LLMBoard

Details
#65-0.39
TE

Hy3

Tencent

70.68 LLMBoard

Details

What is Ember 1?

Key information about Ember 1 and its available data.

78T parameters, a 1040k context window, and function calling. It is available as a Research Preview on Fireworks Serverless under accounts/fireworks/models/ember-1.

Data as of 2026-10-22.

FAQ

Common questions about Ember 1.

When was Ember 1 released?

Ember 1's default version was released on Sep 23, 2026.

How much does Ember 1 cost?

Ember 1's official API price is $3 per million input tokens and $15 per million output tokens via Fireworks AI. The lowest tracked third-party offer starts at $3 input and $15 output via Kilo Gateway.

Who created Ember 1?

Ember 1 was created by Fireworks AI.

What is the context window for Ember 1?

The default version has a 1M token context window.

Is Ember 1 open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Ember 1?

6 provider offerings are linked to the default version.

Browse runtime rankings