Ember-1 released
Fireworks · Model release
Source confirmed
Data as of September 28, 2026 · How the score is built
CurrentProprietaryReasoning
Released Sep 23, 20261.04M contextFireworks Ember-1 model page
Ember-1
Decision readingEmber-1 is tracked, but not publicly ranked yet. The profile exposes 5 sourced benchmark rows and leaves unsupported fields blank until a published record exists.
Released Sep 23, 2026 — see all recent releases
Ember-1 will be repriced, updated or retired. Get each notice with its source and date. Follow model changes
Share or export
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
Unranked
field median 50.3Not eligible for a public rank
Price
$3input / $15 output
input median $1cached $0.30 · blended $9
Speed
Not measured
field median 95 tok/sTime to first token not measured
Context
1.04Mtokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Published rows are visible, but no category has enough eligible evidence for a comparative rank.
Validate before choosing
5 published rows leave some tracked benchmark slots empty. Independent runtime speed has not been measured.
Source-linked · 5 displayable benchmark rows
Follow model changesCategory score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticWeight 22%2 benchmarksVerified | Score pending | 2 benchmarks | Verified | |||
| CodingRank Not rankedWeight 20%3 benchmarksVerified | 77.9 | 3 benchmarks | Verified | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| KnowledgeWeight 12%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
5 of 486 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic2/2 verified
- Coding3/3 verified
- ReasoningNot measured
- MultimodalNot measured
- KnowledgeNot measured
- MultilingualNot measured
- Inst. FollowingNot measured
- MathNot measured
Verified sourceProvisionalNot measured
Benchmark ledger
Coding opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Coding3 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| DeepSWE | Score75.2% | Versus best verified row Best verified: Muse Spark 1.3 · 75.4% | Gap0.2 behind | WeightDisplay only | Provider exact |
| Terminal-Bench 2.1 | Score82.0% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap10.8 behind | WeightDisplay only | Provider exact |
| SWE-bench VerifiedSoftware Engineering Benchmark Verified | Score92.2% | Versus best verified row Best verified: Claude Opus 5 · 96% | Gap3.8 behind | WeightDisplay only | Provider exact |
Agentic2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 | Score82.0% | Versus best verified row Best verified: SWE-2 · 92.8% | Gap10.8 behind | WeightDisplay only | Provider exact |
| τ²-bench Airlineτ²-Bench Airline Domain | Score66.0% | Versus best verified row Best verified: Ember-1 · 66.0% | GapBest verified | WeightDisplay only | Provider exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 5 rowsLineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Radar
Full release historyEmber-1 release history
Radar confirmed these at the source. Use Ember-1 in your work? Explore Radar to follow supported changes and choose your alerts.
Radar
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- accounts/fireworks/models/ember-1Fireworks Ember-1 model page
- Context window
- 1.04MFireworks Ember-1 model page
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- Not sourced yet
- Output modalities
- Not sourced yet
- Parameters
- Not disclosed by the provider
- Availability
- Fireworks offers Ember-1 as a Research Preview through its serverless API under `accounts/fireworks/models/ember-1`. The launch post describes an initial two-week research-access window. Fireworks has not published Ember-1 weights.
- Cloud regions
- Not tracked yet
- Lifecycle
- Current
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Published at $0.30 per million cached input tokensFireworks Ember-1 model page
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track Ember-1, but the public leaderboard excludes this profile until enough non-generated benchmark coverage is available. Only published rows appear above.
Ember-1 is a proprietary model with a 1.04M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Fireworks offers Ember-1 as a Research Preview through its serverless API under `accounts/fireworks/models/ember-1`. The launch post describes an initial two-week research-access window. Fireworks has not published Ember-1 weights.
Official exact-value snapshot from Fireworks Research's September 23, 2026 Ember-1 launch table. BenchLM maps Terminal-Bench 2.1 (mirrored in coding and agentic), SWE-bench Verified, DeepSWE 1.1, and tau2-Bench Airline to their existing lanes. SWE-Interact has no compatible catalog key, so its 20.0% provider result remains in the cited launch post. Fireworks ran these evaluations without publishing enough harness detail to treat them as comparable model-only scores; every mapped row is provider-reported and excluded from weighted ranking. The reported 35–50% reasoning-token savings against Kimi K3 are workload-dependent efficiency claims, not benchmark scores.
5 of 486 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Last updated September 28, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does Ember-1 perform overall in AI benchmarks?
Ember-1 has 5 source-displayable benchmark rows, but it does not qualify for a public overall rank. The available rows remain visible by category without being converted into a site-wide score. Missing evidence stays blank instead of being estimated from an earlier model.
Is Ember-1 good for coding and programming?
Ember-1 has source-displayable benchmark coverage for coding and programming, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is Ember-1 good for agentic tool use and computer tasks?
Ember-1 has source-displayable benchmark coverage for agentic tool use and computer tasks, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Does Ember-1 have full benchmark coverage on BenchLM?
No. Ember-1 currently has 5 source-displayable rows across 486 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of Ember-1?
Ember-1 has a documented context window of 1.04M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.