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%...
Model details →Fireworks: Ember-1 vs Google: Gemini 2.5 Pro
Google: Gemini 2.5 Pro wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...
Model details →Side-by-side comparison
| Capability | Fireworks: Ember-1 | Google: Gemini 2.5 Pro | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 1.0M | 1.0M | Tie |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $3.00 | $1.25 | 🏆 Google: Gemini 2.5 Pro |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $15.00 | $10.00 | 🏆 Google: Gemini 2.5 Pro |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | Yes | Yes | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is Fireworks: Ember-1 better than Google: Gemini 2.5 Pro?
Google: Gemini 2.5 Pro wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Fireworks: Ember-1 and Google: Gemini 2.5 Pro?
Input: $3.00 vs $1.25 per 1M tokens. Output: $15.00 vs $10.00 per 1M tokens.
What context windows do Fireworks: Ember-1 and Google: Gemini 2.5 Pro support?
Fireworks: Ember-1 supports up to 1.0M tokens. Google: Gemini 2.5 Pro supports up to 1.0M tokens.
Do both Fireworks: Ember-1 and Google: Gemini 2.5 Pro support tool calling?
Fireworks: Ember-1: yes. Google: Gemini 2.5 Pro: yes.