How much does Ember-1 cost on Zeplik?

Input tokens cost 36.0 credits per million and output tokens 180 credits per million (1 credit = $0.10; the raw provider rates are $3.00 and $15.00 per million). New accounts start with free credits.

How long can a conversation with Ember-1 be?

Ember-1 has a 1.0M-token context window (1,048,576 tokens), which covers the conversation plus any documents you attach.

Does Ember-1 support images and tools?

Ember-1 accepts image input and supports tool calling.

Ember-1

FrontierVisionTools

Fireworks · Released September 2026

Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3).

It is Fireworks Research's Ember line, reasoning models built on open-weight bases and tuned to spend fewer tokens reaching an answer.

Facts and pricing

Provider: Fireworks
Context window: 1.0M tokens
Input price: 36.0 credits / 1M tokens ($3.00 raw)
Output price: 180 credits / 1M tokens ($15.00 raw)
Vision (image input): Yes
Tool calling: Yes
Extended reasoning: No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.20x margin. Raw prices shown per 1M tokens.

Try Ember-1 now

Or open Zeplik with Ember-1 already selected

What Ember-1 is best for

Hard problems where answer quality matters more than cost: strategy, analysis, difficult writing
Very long documents and codebases: a 1.0M-token window fits entire books or repositories in one conversation
Working with images: screenshots, charts, photos and scanned documents alongside text
Tool use and agents: reliably calls functions, so it can search, run skills and drive workflows

Example prompts

Prompts that suit a frontier model like Ember-1:

Review this business plan and give me the three hardest questions an investor would ask
Rewrite this announcement so it lands with both engineers and executives
I am choosing between two job offers, help me think through the tradeoffs
Draft a technical design doc for a rate limiter, including failure modes

Frequently asked questions

What is Ember-1?: Ember-1 is an AI model by Fireworks. Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3).
How much does Ember-1 cost on Zeplik?: Input tokens cost 36.0 credits per million and output tokens 180 credits per million (1 credit = $0.10; the raw provider rates are $3.00 and $15.00 per million). New accounts start with free credits.
How long can a conversation with Ember-1 be?: Ember-1 has a 1.0M-token context window (1,048,576 tokens), which covers the conversation plus any documents you attach.
Does Ember-1 support images and tools?: Ember-1 accepts image input and supports tool calling.

Related models

Claude Haiku 5.5Fast and light

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use.

1M ctx6.0 cr/M outOctober 2026

Nano Banana 2.1Fast and light

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro.

66K ctx90.0 cr/M outOctober 2026

Mistral Large 4Open weight

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.

524K ctx25.1 cr/M outOctober 2026

Ling 3.1 FlashFast and light

Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.

262K ctx0 cr/M outOctober 2026

Apodex 1.1 Mini (free)Fast and light

Apodex 1.1 Mini is a reasoning-first model from Apodex, built for complex, long-horizon research and forecasting tasks.

262K ctx0 cr/M outOctober 2026

Pareto 26.10 PreviewGeneral purpose

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

1.0M ctx38.4 cr/M outOctober 2026