Ember-1
by Fireworkstext+image->text1 endpoint
Neura Intelligence Index
94.7/ 100
Rank
#11—
Confidence
lowBenchmarks
1(3% coverage)
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% fewer tokens than the base model while maintaining comparable quality across Fireworks' evaluations. It is suited for coding, knowledge work, and agentic workflows where reasoning cost and latency matter.
Capabilities
Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Top-P sampling
Stop sequences
Log probabilities
Modalities
Input
TextImage
Output
Text
Technical Specifications
Context Window
1.0M tokens
Max Output
943.7K tokens
Tokenizer
Other
Uptime (24h)
10000.0%
Parameters
2780000000000B
Country
🇺🇸US
Release Date
September 23, 20264w
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokenspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Performance Over Time
Pricing
Per 1M tokens
Input$3.00
Output$15.00
Cache read$0.30
Added
September 24, 2026
Last synced 10/23/2026