Skip to content
Alpha
  • Models
  • Rankings
  • Ori
Talk to sales

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Customers
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
Favicon for fireworks

Fireworks: Ember-1

fireworks/ember-1

Compare

Ember-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3Opens in new tab. 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.

Modalities
In / out price
$3 / $15per 1M
Context
1.0M
Released
Sep 24, 2026
Compare
ProvidersPricingPerformanceUptimeBenchmarksAppsActivityFAQExplore

Providers

This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.

Pricing

The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).

Uptime

Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.

Benchmarks

Scores on standardized evaluations and this model’s own outputs on shared benchmark prompts. Higher percentages are better — and each rank shows where this model lands among the models evaluated on that source.

Benchmark score summary for Fireworks: Ember-1 (Vals AI)
SourceBenchmarkScore
Vals AIEmber-1 BioMysteryBench67.0%
Vals AIEmber-1 Code Migration32.5%
Vals AIEmber-1 CyberBench v1.169.5%
Vals AIEmber-1 EMB63.4%
Vals AIEmber-1 Finance Agent (v2)51.9%
Vals AIEmber-1 Harvey's Legal Agent Benchmark v19.2%
Vals AIEmber-1 IOI46.3%
Vals AIEmber-1 Legal Research Bench44.7%
Vals AIEmber-1 MysteryMechanism22.5%
Vals AIEmber-1 ProofBench v1.161.0%
Vals AIEmber-1 Public Benefits Bench v1.166.2%
Vals AIEmber-1 SAGE86.4%
Vals AIEmber-1 Vals Science Index31.8%
Vals AIEmber-1 Tax Agent Bench31.1%
Vals AIEmber-1 Terminal-Bench 4.020.7%
Vals AIEmber-1 Terminal-Bench-Science5.7%
Vals AIEmber-1 Vals Index50.9%
Vals AIEmber-1 Vibe Code Bench v1.183.9%

Apps

Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.

Activity

Token volume and request traffic to this model over time.

API

Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.

Not currently available through EU in-region routing. In-region routing docs

Explore more models

AI Models with Vision: Multimodal LLMs for Image UnderstandingCollectionAI Model RankingsRanking
Throughput
62tok/s

P50, best across providers

Latency
0.48s

P50, best provider

1.
Favicon for https://nousresearch.com
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
3.48Btokens
2.
Favicon for https://openrouter.ai/images/apps/cline.png
Cline
Cline is an open-source AI coding agent that lives inside your IDE, autonomously exploring your codebase, editing files, running terminal commands, and using browser automation.
1.01Btokens
3.
Favicon for https://omp.sh/
omp
new
377Mtokens
4.
Favicon for https://novelcrafter.com/
novelcrafter
Your personal novel writing toolbox. Plan, write and tinker with your story.
200Mtokens
5.
Favicon for https://goose-docs.ai/
goose
new
177Mtokens
Rest of OpenRouter
118M
Top 5 Apps
13.9M

Frequently asked questions

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.

Ember-1 costs $3.00/M input tokens and $15.00/M output tokens, with separate rates for Cache Read at $0.30/M tokens.

Ember-1 has a 1,048,576 token context window.

Yes. Ember-1 accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.

Ember-1 accepts text and images as input and returns text.

Ember-1 was released on September 24, 2026.

More models from Fireworks AI

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% 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.

Text1.0M context$3 / $15
FireLLaVA 13B

A blazing fast vision-language model, FireLLaVA quickly understands both text and images. It achieves impressive chat skills in tests, and was designed to mimic multimodal GPT-4.

The first commercially permissive open source LLaVA model, trained entirely on open source LLM generated instruction following data.

Text4K context