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%...
Context
1.05M
1,048,576 tokens
Max output
944K
943,718 tokens
Input
$3.00
per 1M tokens
Output
$15.00
per 1M tokens
Providers
6
6 listings
Intelligence
—
Not yet scored
Pricing
USD per 1M tokens · listed by Kilo Gateway
| Token type | Standard |
|---|---|
| Input | $3.00 |
| Output | $15.00 |
| Cache read | $0.30 |
Lowest input price across providers: $3.00.
Capabilities
ReasoningYes
Effort: none, low, high, max
Tool callYes
Structured outputYes
TemperatureYes
AttachmentsYes
Interleaved reasoningYes
Field: reasoning_content
Open weightsNo
ModeratedNo
Input
TextImage
Output
Text
Benchmarks
Published scores and Design Arena Elo
No published benchmark scores for this model yet.
Rankings
Position on each OneAtlas leaderboard
Providers · 6
6 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| fireworks/ember-1 | 1.04M | — | 131K | $3.00 | $15.00 | — | $0.30 | — | — | — | Yes | Yes | Unknown | Yes | Sep 22, 2026 | |
| fireworks_ai/accounts/fireworks/models/ember-1 | 1.05M | — | 131K | $3.00 | $15.00 | — | $0.30 | — | — | — | Yes | Yes | Yes | Yes | Sep 22, 2026 | |
| accounts/fireworks/models/ember-1 | 1.05M | — | 131K | $3.00 | $15.00 | — | $0.30 | — | — | — | Yes | Yes | Yes | Yes | Sep 22, 2026 | |
| fireworks/ember-1 | 1.05M | — | 944K | $3.00 | $15.00 | — | $0.30 | — | — | — | Yes | Yes | Yes | Yes | Sep 22, 2026 | |
| fireworks/ember-1 | 1.05M | 1.05M | 131K | $3.00 | $15.00 | — | $0.30 | — | — | — | Yes | Yes | Yes | Yes | Sep 22, 2026 | |
| fireworks/ember-1 | 1.05M | — | 1.05M | $3.00 | $15.00 | — | $0.30 | — | — | — | Yes | Yes | Unknown | Yes | Sep 22, 2026 |