Inference
EN
Fireworks

Ember-1

Ember-1 is a reasoning model from Fireworks in the Fireworks Ember family. It has 8 scored results in 3 categories. It has no index.

  • Closed weights
  • Reasoning
  • Input: text · image
  • Released 2026-09
UnrankedEnough results for an index.
IndexAll categories, out of 100.UnrankedMedian 51.0
CoverageIndex weight that has results.50%
SpeedOutput tokens per second.62/sMedian 67/s
First tokenSeconds to the first output token.0.4 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$3.00Median $0.60
Output / 1MUS dollars per 1M output tokens.$15.00Median $2.55
ContextMaximum tokens in one request.1.05MMedian 262K
EloLMArena rating and rank.—Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
fireworks/ember-1
Max outputMaximum output tokens per request.
944K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.30
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
2 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
Fireworks AIHost$3.00$15.001.05M
OpenRouterRouter$3.00$15.001.05M

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.3 counted69.7—
CodingCode writing and repair.4 counted66.9—
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.None counted——
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.1 counted68.2—

Results

8 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
Software Engineering Benchmark VerifiedCoding92.2%4 / 114
DeepSWEAgentic75.2%7 / 59
Vibe Code Bench v1.1Coding83.9% ±3.220 / 123
Terminal-Bench 2.1 · BenchLMAgentic82.0%29 / 86
ProofBench v1.1Math61.0% ±4.924 / 54
Code MigrationCoding32.5% ±4.638 / 77
Terminal-Bench 4.0Agentic20.7% ±3.633 / 61
IOICoding46.3% ±9.230 / 45
Legal Research BenchLegal44.7% ±3.524 / 90
Tax Agent BenchFinance31.1% ±3.329 / 82
Public Benefits Bench v1.1Public benefits66.2% ±1.219 / 50
EMBFinance63.4% ±2.929 / 75
SAGEEducation86.4% ±1.913 / 29
Finance Agent (v2)Finance51.9% ±2.138 / 79
CyberBench v1.1Other69.5% ±5.624 / 48
Terminal-Bench-ScienceScience5.7% ±2.822 / 44
BioMysteryBenchScience67.0% ±3.020 / 30
MysteryMechanismScience22.5% ±2.821 / 30
τ²-Bench Airline DomainAgentic66.0%—

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseVals AINo licence statedmodels.devMIT

History

5 releases
Output / 1M$15.00 → $15.00
23 Oct 202612 Nov 2026

Questions

How much does Ember-1 cost?
$3.00 per 1M input tokens, $15.00 per 1M output tokens.
How fast is Ember-1?
62 output tokens per second, 0.4 s to the first token.
What is the context window of Ember-1?
1.05M tokens.
Is Ember-1 open source?
No. Its weights are not published.
When was Ember-1 released?
September 2026.