fireworks
Fireworks: Ember-1
fireworks/ember-1
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Ember-1 (fireworks/ember-1) is a text-and-image-to-text reasoning model from Fireworks Research, listed in the OpenRouter catalog. The catalog describes it as built on Moonshot AI's Kimi K3 and tuned for shorter reasoning traces to improve token efficiency. Reasoning is enabled by default at maximum effort, with configurable levels, and the listing advertises a roughly one-million-token context window plus tool use and structured outputs. Only catalog data was available; no independent model card or benchmark results were included.[1]
Strengths
- The catalog reports a roughly one-million-token context window and text-and-image input, which could suit long or multimodal prompts.[1]
- Listed API parameters include tool calling, structured outputs and response formats, suggesting readiness for agent-style integrations.[1]
- Reasoning effort is configurable across max, high, low and none and is not mandatory, so effort can reportedly be tuned per request.[1]
Limitations
- Evidence is catalog-only: no independent model card was available in this source pack, so all capabilities are listing-reported, not verified.[1]
- No measured performance or benchmark data was supplied; validate quality, latency and cost on your own workloads.[1]
- Fields such as knowledge cutoff and a Hugging Face repository are missing; license terms and details of the underlying Kimi K3 base are unknown.[1]
Where to use it
- Candidate for long-context question answering or document analysis, given the listed context window; test on representative material.[1]
- Possible fit for agent or pipeline workloads that call tools or need structured outputs, per the listed parameters.[1]
- Worth evaluating where shorter reasoning traces matter for cost or latency, since the catalog claims token efficiency that remains unverified.[1]
Sources
- [1] OpenRouter catalog · Fireworks: Ember-1Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...
Specifications
- Model ID
- fireworks/ember-1
- Canonical ID
- fireworks/ember-1-20260923
- Creator
- fireworks
- Added to OpenRouter
- 24.09.2026
- Context length
- 1,048,576
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $3 / out $15
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · default max · efforts: max, high, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default max · efforts: max, high, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Fireworks | 1,048,576 | $3 | $15 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.