Ember-1 vs gpt-oss-120b
Pricing, context window and real answers (September 2026)
Ember-1 (Fireworks) and gpt-oss-120b (OpenAI), compared as you can actually call them on FastMetal. Both are served from the same OpenAI-compatible endpoint and API key; switching is a change to the model string.
Specs and pricing
| Ember-1 |  gpt-oss-120b | |
|---|---|---|
| Provider | Fireworks | OpenAI |
| Input (per 1M tokens) | ¥536.1 | ¥16 |
| Output (per 1M tokens) | ¥2,680.5 | ¥79 |
| Typical cost (1,000 in + 500 out tokens × 1,000 calls) | ¥1,876 | ¥56 |
| Context window | 1,048,576 tokens | 131,072 tokens |
| Release date | 9/24/2026 | 8/5/2025 |
| Input modalities | text, image | text |
| Throughput (p50) | — | — |
| Arena · overall | Unranked | #201 · ELO 1,352 |
| Arena · Japanese | Unranked | #136 · ELO 1,328 |
| Arena · coding | Unranked | #208 · ELO 1,391 |
Prices are FastMetal's yen rates before tax. Arena ranks are as of the latest leaderboard scrape.
Which should you pick?
- On price, gpt-oss-120b: ¥79 per 1M output tokens, 97% less than Ember-1.
- For long documents, Ember-1: a 1,048,576-token context window against 131,072 for gpt-oss-120b.
- If in doubt, try both on the same key. Switching is a change to the model string, and each is billed at its own rate.
Real answers to the same prompts
Exactly what the FastMetal gateway returned, side by side. Not benchmark scores: actual output.
Count the number of 'r's in 'strawberry'
Count the number of 'r's in 'strawberry'. Explain your reasoning step by step.
Ember-1
# 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.
8.2s482 output tokens
gpt-oss-120b
**Step‑by‑step count of the letter “r” in the word “strawberry”**
1. Write out the word with each letter in order, labeling its position:
| Position | Letter |
|----------|--------|
| 1 | s |
| 2 | t |
| 3 | **r** |
| 4 | a |
| 5 | w |
| 6 | b |
| 7 | e |
| 8 | **r** |
| 9 | **r** |
|10 | y |
2. Scan the list and mark every occurrence of the letter **r**.
- Position 3 → r (first occurrence)
- Position 8 → r (second occurrence)
- Position 9 → r (third occurrence)
3. Count the marked entries: there are **3** marked positions.
**Result:** The word “strawberry” contains **3** occurrences of the letter **r**…
1.7s332 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…
Ember-1
## 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…
18.2s960 output tokens
gpt-oss-120b
### Why the `map` can’t be called
`Array.prototype.map` is a method that exists only on **arrays** (or array‑like objects).
When you see
```
TypeError: Cannot read properties of undefined (reading 'map')
at UserList (...)
```
it means that the variable you think is an array – `users` in this case – is actually **`undefined`** (or `null`).
React is trying to evaluate this line:
```jsx
{users.map(user => <li key={user.id}>{user.name}</li>)}
```
and it crashes because you can’t read `.map` from `undefined`.
---
## Common reasons `users` ends up undefined
| Reason | Typical scenario | How it shows up |
|--------|------------------|-----------------|
| **Prop not passed** | `<Use…
7.3s1610 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):…
Ember-1
# 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…
95.0s5356 output tokens
gpt-oss-120b
Below is a **step‑by‑step review** of the original `get_data` implementation followed by a **refactored version** that addresses readability, performance, and modern Python best‑practice concerns.
---
## 1. What the original function does
```python
def get_data(url, retries=3):
import requests
import time
for i in range(retries):
try:
r = requests.get(url, timeout=10)
if r.status_code == 200:
data = r.json()
result = []
for item in data:
if item["active"] == True:
result.append({"name": item["name"], "id": item["id"]})
return result…
14.4s3132 output tokens
Frequently asked questions
- Which is cheaper, Ember-1 or gpt-oss-120b?
- Per 1M output tokens, Ember-1 is ¥2,680.5 and gpt-oss-120b is ¥79 on FastMetal (yen, before tax), so gpt-oss-120b is cheaper.
- How do the context windows of Ember-1 and gpt-oss-120b compare?
- Ember-1 takes 1,048,576 tokens; gpt-oss-120b takes 131,072.
- Can I use Ember-1 and gpt-oss-120b with the same API key?
- Yes. On FastMetal's OpenAI-compatible endpoint, switch by passing "ember-1" or "gpt-oss-120b" as the model. Each is billed at its own rate from the same prepaid balance.
Try both on one API key
Create an account and add credit to call Ember-1 and gpt-oss-120b from the browser chat and the API. No monthly fee.