fireworks · Frontier
Ember 1
Fireworks Research reasoning model built on Kimi K3. It accepts text and images, supports tool calling and structured output, and has a 1M-token context window.
- Reasoning
- Tools
- Vision
- Structured output
- Input
- Text, Images
- Output
- Text
- Reasoning effort
- none · low · high · max
- Discovery tier
- Frontier
Pricing
USD per 1M tokens- Input
- $3.00
- Output
- $15.00
- Cache read
- $0.30
Reference prices as published by the model provider. API example
Specifications
- Context window
- 1M
- Max output
- —
- Average output (7 days)
- 3.3K tokens
- Longer than 97% of 473 models
Side by side
Ember 1 compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Ember 1fireworksThis model | AionLabs: Aion 3.5aionlabsRemove | |
|---|---|---|
| Provider | fireworks | aionlabs |
| Discovery tier | Frontier | Frontier |
| Added | Sep 24, 2026 | Sep 23, 2026 |
| Limits | ||
| Context window | 1.05MBest | 262.14K |
| Max output | — | 32.77K |
| Average output | 3.3K tokens | 1.4K tokens |
| Pricing, USD per 1M tokens | ||
| Input | $3.00 | $3.00 |
| Output | $15.00 | $6.00Best |
| Cache read | $0.30Best | $0.75 |
| Performance | ||
| Throughput | — | 65.5 tok/s |
| Time to first token | — | 4.2 s |
| Request success (24h) | — | 100.0% |
| Capabilities | ||
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Vision | Yes | No |
| Structured output | Yes | No |
| Reasoning effort | none, low, high, max | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Ember 1
- AionLabs: Aion 3.5
| Leaderboard | Ember 1 | AionLabs: Aion 3.5 |
|---|---|---|
| Roleplay | Not in top 20 | #19 · 18.5% |
| Creative writing | Not in top 20 | #15 · 20.1% |
Ranks among Noumen catalog models on Use cases leaderboards. Only top-20 placements are listed.
- Ember 1
- AionLabs: Aion 3.5
| Leaderboard | Ember 1 | AionLabs: Aion 3.5 |
|---|---|---|
| Creative Writing v3 | Not in top 20 | #13 · 1931 |
| Longform Writing | Not in top 20 | #9 · 82.1 |
Ranks among Noumen catalog models on EQ-Bench leaderboards. Only top-20 placements are listed.EQ-Bench
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Prompt cache hits
- 82.4%
- About $0.77 per 1M input tokens with caching
- Request success (24h)
- 100.0%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "fireworks/ember-1",
"reasoning_effort": "none",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="fireworks/ember-1",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)