Fireworks: Ember-1 API
Moonshot AI
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%...
About Fireworks: Ember-1
Fireworks: Ember-1 is a language model developed by Moonshot AI. It's particularly well-suited for analyzing images, screenshots, and visual content, tackling complex, multi-step reasoning problems, orchestrating tool-using agents that call APIs and external services, producing structured outputs for reliable data extraction, and handling large contexts of up to 1.0M tokens. Its 1.0M-token context window means you can pass in entire documents, codebases, or conversation histories without losing context.
As of Sep 30, 2026, Fireworks: Ember-1 costs $0.975 per 1M input tokens and $4.88 per 1M output tokens on Qubax, versus $3.00 / $15.00 on OpenRouter (68% less on input). A typical 1,000 chat requests (2K tokens in, 500 out) come to about $4.39. Pay with USDC, USDT, BTC, ETH or 200+ other coins — no credit card required.
Pricing
| Token Type | Qubax | OpenRouter | You Save |
|---|---|---|---|
| Input (per 1M tokens) | $0.975 | $3.00 | 68% |
| Output (per 1M tokens) | $4.88 | $15.00 | 68% |
| Cache read (per 1M tokens) | $0.390 | — | — |
Prices per 1 million tokens. Pay with 200+ cryptocurrencies. Cache read is the discounted rate providers offer for repeated prompt prefixes.
Estimated Monthly Cost
Specifications
Use Cases
Capabilities
Quick Start
from openai import OpenAI
client = OpenAI(
base_url="https://api.qubax.ai/v1",
api_key="qbx_live_YOUR_API_KEY",
)
response = client.chat.completions.create(
model="ember-1",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.qubax.ai/v1",
apiKey: "qbx_live_YOUR_API_KEY",
});
const response = await client.chat.completions.create({
model: "ember-1",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);curl https://api.qubax.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer qbx_live_YOUR_API_KEY" \
-d '{
"model": "ember-1",
"messages": [{"role": "user", "content": "Hello!"}]
}'Get your API key from the dashboard.
Why use Fireworks: Ember-1 on Qubax?
68% Cheaper
Up to 68% off OpenRouter prices
Pay with Crypto
200+ coins (BTC, ETH, SOL, USDT, USDC & more). No credit card needed.
OpenAI Compatible
Drop-in replacement. Works with Cline, Cursor, any tool.
More from Moonshot AI
Compare Fireworks: Ember-1 with alternatives
| Model | Provider | Input / 1M | Output / 1M | vs Fireworks: Ember-1 |
|---|---|---|---|---|
| Fireworks: Ember-1 | Moonshot AI | $0.975 | $4.88 | — |
| Hermes 3 Llama 3.1 405b (Web) | Meta | $0.958 | $2.61 | Cheaper |
| GPT-5.4 Image 2 | OpenAI | $0.832 | $1.56 | Cheaper |
| Sakana: Fugu Max | Other | $0.650 | $1.95 | Cheaper |
| GPT-5.2 Codex | OpenAI | $0.569 | $4.55 | Cheaper |
Frequently Asked Questions
How much does the Fireworks: Ember-1 API cost?
On Qubax, Fireworks: Ember-1 costs $0.975 per 1M input tokens and $4.88 per 1M output tokens. This is 68% cheaper than OpenRouter's price of $3.00 per 1M input tokens.
Is the Fireworks: Ember-1 API compatible with OpenAI?
Yes. Qubax provides an OpenAI-compatible API. You can use Fireworks: Ember-1 as a drop-in replacement by changing your base URL to https://api.qubax.ai/v1 and using your Qubax API key. It works with Cline, Cursor, OpenCode, Hermes Agent, and any tool that supports OpenAI APIs.
Why is Fireworks: Ember-1 cheaper on Qubax than OpenRouter?
Qubax sources AI inference from an open compute marketplace on the Base blockchain where GPU providers compete on price. We pass the savings to you — 68% cheaper than OpenRouter's price for Fireworks: Ember-1.
How do I pay for Fireworks: Ember-1 API usage?
Qubax uses prepaid crypto credits. Deposit USDC on the Base chain and your balance is automatically deducted as you use the API. No credit card required. Top up from $3.
What is the context window of Fireworks: Ember-1?
Fireworks: Ember-1 supports a context window of 1.0M tokens, allowing you to process large documents, codebases, or long conversations in a single request.
What can I build with Fireworks: Ember-1?
Fireworks: Ember-1 is versatile enough for a wide range of applications. You can use it to analyze images and visual content, tackle complex multi-step reasoning tasks, build autonomous agents that call external tools and APIs, generate structured JSON output for data pipelines, process long documents and entire codebases, and more. Because it's served through Qubax's OpenAI-compatible API, integration into existing apps, agents, or workflows takes just a few lines of code.
How fast is Fireworks: Ember-1 on Qubax?
Fireworks: Ember-1 on Qubax supports streaming responses, so tokens begin arriving in real time as they're generated. Latency depends on the provider and prompt complexity. Qubax routes requests through an intelligent routing layer, which selects the fastest available compute provider for each request — so you get competitive latency at a lower price.
Fireworks: Ember-1 vs Hermes 3 Llama 3.1 405b (Web): which should I choose?
Fireworks: Ember-1 by Moonshot AI and Hermes 3 Llama 3.1 405b (Web) by Meta are both strong models in a similar price tier. Fireworks: Ember-1 excels at complex reasoning and supports vision/image inputs. Hermes 3 Llama 3.1 405b (Web) comes from a different lab and may have different strengths depending on your workload. On Qubax, Fireworks: Ember-1 starts at $0.975/1M input tokens while Hermes 3 Llama 3.1 405b (Web) comes in at $0.958/1M, so Hermes 3 Llama 3.1 405b (Web) may be worth considering if you need to minimize per-token cost. Both are available on Qubax with crypto payments and OpenAI-compatible APIs, so you can try each and switch freely.
Can I use Fireworks: Ember-1 for commercial projects?
Yes. Fireworks: Ember-1 on Qubax can be used for commercial purposes. You own the outputs you generate. Qubax provides the API infrastructure — you bring your use case.
Browse 400+ other AI models
GPT, Claude, Gemini, Llama, DeepSeek & more — all up to 99% off.
See all models →