Inferse
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your platform
Vendor dashboard

Ember-1

Fireworks· released 24 Sept 2026

fireworks/ember-1
Input / 1M tokens
$3
Output / 1M tokens
$15
Context window1M tokens

Longest answer: 944K tokens

reads textreads imagetool callingvisionreasoning
See it on openrouter.ai

About

Ember-1 is a reasoning model from Fireworks Research, built on Kimi K3. It accepts text and images, supports tools, and returns text. Vision and reasoning are enabled, with a context window of 1,048,576 tokens and a maximum output of 943,718 tokens. The model ID is `fireworks/ember-1`. Fireworks lists its release date as 2026-09-24. Input costs $3 per 1M tokens and output costs $15 per 1M tokens. The model is designed to use shorter reasoning traces; the available description says it uses roughly 40%... but does not complete what that figure refers to. For builders assessing fit, the listed input types, tools, reasoning, context and output limits provide the clearest specifics: text and image input, text output, and a context window just over one million tokens.

Who it is for

Teams building text or image workflows that need reasoning and tool support may consider Ember-1. Its large context and output limits suit workflows that need room for long inputs or responses.

What is good

  • Accepts text and image inputs
  • Tool support and reasoning enabled
  • 1,048,576-token context window
  • 943,718-token maximum output

What to know first

  • Input costs $3 per 1M tokens
  • Output costs $15 per 1M tokens

Verdict

Ember-1 combines image input, tools and reasoning with large context and output limits. Its listed token prices are $3 per 1M input tokens and $15 per 1M output tokens.

Details

Lab
Fireworksopenrouter.ai · 3 Oct 2026
Context
1,049Kopenrouter.ai · 3 Oct 2026
Input price
$3 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$15 / 1Mopenrouter.ai · 3 Oct 2026
Max output
943,718 tokensopenrouter.ai · 3 Oct 2026
Inputs
text, imageopenrouter.ai · 3 Oct 2026
Open weights
Noopenrouter.ai · 3 Oct 2026

More longest-context models

See the list
Auto Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterAuto Router (Beta) ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterGrok 4.20 ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIGrok 4.20 Multi-Agent ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIPareto Code Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterLlama 4 Scout ctx1,311Kin$0.1 / 1Mout$0.3 / 1M Meta

Listed on Inferse

Sources