Ember-1 vs Mercury 2.5 compared — price per token, context window, multimodality, openness and which to choose. Full 2026 breakdown.
Ember-1 — full profile › · Mercury 2.5 — full profile ›
Prices & specs refreshed from live data · olud.ai
Open-model prices = cheapest provider via OpenRouter; official maker rates may be higher.
| Spec | Ember-1 | Mercury 2.5 | Winner |
|---|---|---|---|
| Maker | Fireworks | Inception | – |
| Type | Proprietary | Proprietary | – |
| Context window | 1M tokens | 260K tokens | FIEmber-1 |
| Input price | $3/M | $0.04/M | INMercury 2.5 |
| Output price | $15/M | $0.15/M | INMercury 2.5 |
| Vision / multimodal | Yes | No | FIEmber-1 |
| Tool / function calling | Yes | Yes | = Tie |
| Self-hostable | No (API only) | No (API only) | – |
| License | Proprietary | Proprietary | – |
Mercury 2.5 is ~100× cheaper than Ember-1 on output tokens ($0.15 vs $15 per M tokens).
| Capability | Ember-1 | Mercury 2.5 |
|---|---|---|
| Open weights (downloadable) | ✗ | ✗ |
| Self-hostable | ✗ | ✗ |
| Runs fully offline | ✗ | ✗ |
| Vision / multimodal | ✓ | ✗ |
| Tool / function calling | ✓ | ✓ |
| 1M+ context window | ✓ | ✗ |
Independent benchmark scores measured by Artificial Analysis. Higher is better (except latency).
Benchmark data by Artificial Analysis.
| Criterion | Ember-1 | Mercury 2.5 |
|---|---|---|
| Cost-efficiency | 3.0 | 5.0 |
| Context window | 5.0 | 4.0 |
| Openness | 1.5 | 1.5 |
| Self-hosting | 1.0 | 1.0 |
| Multimodality | 5.0 | 3.5 |
Scores come from live data — output price (cost), context length, open vs closed weights (openness & self-hosting) and vision/tool support (multimodality). Raw task quality isn't scored here; it depends on your benchmark — see the verdict.
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%...
Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple tokens in parallel, achieving...
Mercury 2.5 is cheaper on output ($0.15/M vs $15/M).
Ember-1 offers the larger context window (1M tokens).
Choose Mercury 2.5 for the lower output price ($0.15/M vs $15/M). Choose Ember-1 if you need the larger 1M context window.
Browse the full open-source model leaderboard, thousands of tools and live benchmarks — all in one place.
Open the leaderboard →