Ember-1

Ember-1 is Fireworks Research's post-trained version of Kimi K3, tuned to reason in shorter traces at comparable quality, which Fireworks reports as roughly 40% fewer output tokens.

start building →

compare models

                         ...... .                .....
                        .+*===*-.              .:*****-.
                        .-%@#@@=:.            .:*@@%@%-.
                        .:*@@@#@*:            :+%@@@%*.
                         .:=@@@@%-.         ..-%%@@%=:.
                         ..-%@@@@=:.        .:=%@@@%-.
                          .:+%@@@%*:.      .:*@%@@%+.
            ...            .:=@@@@@-:.    ..-%%@@%=:.             .
           :-*:.           ..-%@@@@=:.    .:=@@@@%-.           ..:+-.
          :-@@%+:.           .+@@@@@*:    .*@@@%%-:           ..+*%=-.
          :%@@@@%-.           :*%@@@%+.  .-%%%@@*:          ..:*=%%%*:.
         .-%@@#@@@*:.         .:%@@@%%:..:=@%@@%-.         ..+=%%%%%=:.
          .-*@@@#@@%+:.       ..+%%@@%*::*%%%@%+.         .-*%%%%%=+:.
            :-%@@@@@@=-..       :*@@@%%*+%@@@%*:       ..:+=%%%%=*-.
             .:+%@@@@@%*:.      .:%%%@@%%@%%%=:.      .:+=%%%%%=+..
               .-*%@@@@@=-:     ..+%@@@%%@%%=-.     ..-*%%%%%=*:.
               ...-=@@@@@%*:.    ..+%%@@@%%=-..    ..+%%%%%%*-:.
                  .:+%@@@@@%+:.    .:+*===+:..   .:-=%%%%==+:.
                   ..-*%@@@@%=-:      .....     .:*%%%%%=*:.
                      :+%%@@@@%+.              .-=%%%%%=-..
   ....................:-*%%@%%%-..            :%%%%%=*:... . . . . .. .... .
  :+=**==*=====*=********=%@@@@%+.           ..-=%%%%=**++++++++++++++++++++-.
..-%@@@@@@@@@@@@@@@@@@@@@@@@%%%=-.            .:=%%%%%%=%%=%===%============*:.
.:%@@@@@@@@@@@@@@@@@@%%@@@%%@%=+..             .-==%%%=======%============*==+.
.-*====**=====*=***=*====*=**-...               ..-+**+*++*++*+++++++++++++++-:
 ............................                       .... .......... ....... ..

input · usd / 1m tok

$3.00

output · usd / 1m tok

$15.00

context window

1.05mtokens

modalities · in → out

pricing

base api ratesusd per 1m tokens

input: $3.00
output: $15.00
cache read: $0.30

providers

Fireworks hosts Ember-1. Impossibl routes your request intelligently and handles failover automatically when a provider is down.

Fireworks

specifications

takes text and image in, gives text outfireworks/ember-1

creatorFireworks
model typeText generation
context window1,048,576 tokens
maximum outputnot published
input
takes text and image in, gives text out
outputtext
tool callingnot verified
releasedsep 23, 2026
endpoint/v1/chat/completions

unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.

try it · your prompt, this model, live

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="fireworks/ember-1",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

# responses API
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["IMPOSSIBL_API_KEY"],
    base_url="https://api.impossibl.com/v1",
)

resp = client.responses.create(
    model="fireworks/ember-1",
    input="▌",
)
print(resp.output_text)

edit the prompt, then run

benchmarks

benchmark results are not available for this model yet.

compare Ember-1 with other models

frontier labs and open weights, best-ranked firstusd / 1m tok · in / out

anthropic/claude-opus-5-5$4.00 / $20.00compare →
openai/gpt-6-astra$10.00 / $50.00compare →
meta/muse-wonder$4.00 / $20.00compare →
xiaomi/mimo-v2.6-pro$0.435 / $0.87compare →

impossibl models --all →

frequently asked questions

What is Ember-1?

Ember-1 is Fireworks Research's post-trained version of Kimi K3, tuned to reason in shorter traces at comparable quality, which Fireworks reports as roughly 40% fewer output tokens. It keeps Kimi K3's long context, image input and tool use, and can reason before answering or answer directly.

How much does Ember-1 cost?

Ember-1 costs $3.00 per million input tokens and $15.00 per million output tokens through the Impossibl API. Cache reads cost $0.30 per million tokens. All rates are in USD.

view the pricing table ↑

What is the context length of Ember-1?

Ember-1 has a 1,048,576-token context window through the Impossibl API.

What inputs and outputs does Ember-1 support?

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

How do I use Ember-1 through an API?

Ember-1 is available through the Impossibl API. Use fireworks/ember-1 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

follow the api quickstart →

When was Ember-1 released?

Fireworks released Ember-1 on September 23, 2026.

Creator release announcement ↗

this page describes Ember-1 as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.

view the source catalog ↗model as markdown ↗report a correction →