How much does the Ember-1 API cost?

On FastMetal, Ember-1 is billed per token in yen: ¥536.1 per 1M input tokens and ¥2,680.5 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.

Can I call Ember-1 with the OpenAI SDK?

Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "ember-1" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.

What is the context window of Ember-1?

1,048,576 tokens, shared between the prompt and the response.

What do I need to try Ember-1?

Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Back to Models

ember-1

Ember-1

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%...

9/24/2026

1,048,576 tokens

Input: ¥536.1/M

Output: ¥2,680.5/M

Try in Chat Get API Key

Specifications

Modalities

Input

text

image

Output

text

Supported Parameters

frequency_penalty

include_reasoning

logit_bias

logprobs

max_tokens

presence_penalty

reasoning

reasoning_effort

repetition_penalty

response_format

stop

structured_outputs

temperature

tool_choice

tools

top_k

top_logprobs

top_p

Max Output Tokens

943,718

Reasoning Configuration

Default: Thinking on (effort: max)
Selectable effort levels: max
high
low
Turning thinking off: Possible (reasoning.enabled: false)

How to control thinking, and what it costs

Data policy

Prompt retention: Unknown — we could not confirm
Training: Not used for training

"Unknown" does not mean "safe". It means we could not confirm it.

Whether a provider trains on prompts is a declared value from our terms with them. Retention is determined from the upstream listing for every host this model can reach. Neither is guessed.

Code Examples

curl https://api.fastmetal.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "ember-1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

How Ember-1 actually answers

Real responses to our standard prompts, recorded on FastMetal.

Count the number of 'r's in 'strawberry'

Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.

# Counting the 'r's in "strawberry" **Step 1: Write out the word letter by letter** s - t - r - a - w - b - e - r - r - y **Step 2: Examine each letter one at a time** | Position | Letter | Is it 'r'? | |----------|--------|------------| | 1 | s | No | | 2 | t | No | | 3 | r | ✅ Yes (1) | | 4 | a | No | | 5 | w | No | | 6 | b | No | | 7 | e | No | | 8 | r | ✅ Yes (2) | | 9 | r | ✅ Yes (3) | | 10 | y | No | **Step 3: Verify by splitting the word into parts** - "straw" → contains **1** r - "berry" → contains **2** r's - Total: 1 + 2 = **3** ## Answer The word "strawberry" contains **3** r's.

8.2s response482 output tokens

Debug This Error

I'm getting the following error in my Node.js application: TypeError: Cannot read properties of undefined (reading 'map') at UserList (/app/components/UserList.js:12:25) at renderWithHooks (/app/node_modules/rea…

## The Cause The error means `users` is `undefined` when the component renders, so calling `.map()` on it fails. The component itself is fine — the problem is that the `users` prop isn't being provided (or isn't ready yet). The most common reasons this happens: 1. **Async data hasn't loaded yet** — the parent fetches users from an API, and the component renders before the fetch completes: ```jsx const [users, setUsers] = useState(); // undefined initially! ``` 2. **The prop isn't passed or is misspelled** in the parent: ```jsx <UserList user={users} /> // typo: should be "users" ``` 3. **Wrong data shape** — e.g., passing the whole response object instead of `response…

18.2s response960 output tokens

Code Review

Please review the following Python function and suggest improvements for readability, performance, and best practices: def get_data(url, retries=3): import requests import time for i in range(retries):…

# Code Review ## Bugs and correctness issues - **Bare `except:`** catches *everything* — including `KeyboardInterrupt` and, critically, `KeyError` from `item["active"]`. A malformed item in the response would be misinterpreted as a network failure, wasting all your retries on a data problem that retrying can't fix. - **Retrying all non-200 statuses** — a 404 or 401 will never succeed on retry. Only transient errors (connection failures, timeouts, 429, 5xx) are worth retrying. - **Wasted sleep on the final attempt** — the loop sleeps 2 seconds even after the last failure, before returning `[]`. - **Ambiguous return value** — `[]` means both "request failed" and "no active items." Callers ca…

95.0s response5356 output tokens

Compare these answers side by side with other models →

Frequently asked questions

How much does the Ember-1 API cost?: On FastMetal, Ember-1 is billed per token in yen: ¥536.1 per 1M input tokens and ¥2,680.5 per 1M output tokens, before tax. Usage is drawn from a prepaid balance; there is no subscription or monthly fee.
Can I call Ember-1 with the OpenAI SDK?: Yes. Point base_url at https://api.fastmetal.ai/v1 and pass "ember-1" as the model; existing OpenAI-style code works unchanged, including streaming, tool calls and structured output.
What is the context window of Ember-1?: 1,048,576 tokens, shared between the prompt and the response.
What do I need to try Ember-1?: Create an account and add credit; the model is then available both in the browser chat and over the API. There is no contract or minimum spend.

Try Ember-1 right now

Ember-1 is available on FastMetal through one API key. Start in the browser, or call it from the OpenAI SDK.

Create a free account

Compare with other models

See all comparisons →