Llama 3.3 70B Instruct vs Mercury 2.5
Pricing, context window and real answers (September 2026)
Llama 3.3 70B Instruct (Meta) and Mercury 2.5 (Inception), 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
 Llama 3.3 70B Instruct | Mercury 2.5 | |
|---|---|---|
| Provider | Meta | Inception |
| Input (per 1M tokens) | ¥17.87 | ¥7.15 |
| Output (per 1M tokens) | ¥57.18 | ¥26.81 |
| Typical cost (1,000 in + 500 out tokens × 1,000 calls) | ¥46 | ¥21 |
| Context window | 131,072 tokens | 260,000 tokens |
| Release date | 12/6/2024 | 9/8/2026 |
| Input modalities | text | text |
| Throughput (p50) | — | — |
| Arena · overall | #250 · ELO 1,318 | Unranked |
| Arena · Japanese | #210 · ELO 1,212 | Unranked |
| Arena · coding | #263 · ELO 1,346 | Unranked |
Prices are FastMetal's yen rates before tax. Arena ranks are as of the latest leaderboard scrape.
Which should you pick?
- On price, Mercury 2.5: ¥26.81 per 1M output tokens, 53% less than Llama 3.3 70B Instruct.
- For long documents, Mercury 2.5: a 260,000-token context window against 131,072 for Llama 3.3 70B Instruct.
- 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.
Llama 3.3 70B Instruct
To count the number of 'r's in 'strawberry', I'll break down the word into its individual letters and then examine each one to identify the 'r's. Here are the steps:
1. **Write down the word 'strawberry' with its individual letters separated**: s-t-r-a-w-b-e-r-r-y
2. **Examine each letter to find the 'r's**: Going through the word letter by letter, I identify the 'r's.
- The first 'r' appears after 't', so that's one 'r'.
- Continuing through the word, I find another 'r' after 'e', which gives me a second 'r'.
- Then, immediately after this second 'r', I find a third 'r'.
3. **Count the total number of 'r's identified**: From the step above, I've identified a total of 3 'r's in th…
12.6s217 output tokens
Mercury 2.5
To determine the number of 'r's in the word "strawberry", we can examine each letter in sequence:
1. **s** - Not 'r'
2. **t** - Not 'r'
3. **r** - First 'r' found
4. **a** - Not 'r'
5. **w** - Not 'r'
6. **b** - Not 'r'
7. **e** - Not 'r'
8. **r** - Second 'r' found
9. **r** - Third 'r' found
10. **y** - Not 'r'
Counting these occurrences, there are **3** 'r's in "strawberry".
1.8s968 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…
Llama 3.3 70B Instruct
# Step-by-step analysis of the problem:
1. **The error is occurring because the `map()` function is being called on `undefined`**: This means that the `users` prop is not being passed to the `UserList` component, or its value is `undefined`.
2. **The `map()` function is a method of arrays**: It is used to iterate over the elements of an array and apply a transformation to each element. If `users` is not an array (i.e., it's `undefined`), this method will not be available, hence the error.
3. **To fix this error, you need to ensure that `users` is always an array**: You can achieve this by adding a conditional statement to check if `users` is an array before calling `map()` on it.
# Fixed so…
28.4s560 output tokens
Mercury 2.5
This error occurs because the `users` prop is `undefined` when the component renders. Since the code calls `.map()` on `users`, JavaScript throws a TypeError when `users` is not an array.
Here is how to fix it:
1. **Set a Default Value**
Update the function signature to default `users` to an empty array if it is not provided:
```javascript
function UserList({ users = [] }) {
// ...
}
```
2. **Add a Conditional Check**
If `users` might be null or undefined during data loading, guard the map operation:
```javascript
{users && users.map(user => <li key={user.id}>{user.name}</li>)}
```
3. **Verify Parent Props**
Ensure the parent component pas…
2.4s1028 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):…
Llama 3.3 70B Instruct
### Review and Suggestions
The provided Python function `get_data` appears to be designed to fetch data from a given URL, filter active items, and return the filtered results. Here's a review of the function focusing on readability, performance, and best practices, along with suggestions for improvement.
#### Issues and Improvements:
1. **Import Statements**: Import statements should be placed at the top of the file, not inside the function. This adheres to PEP 8, the official Python style guide.
2. **Exception Handling**: The `except` block is too broad. It's better to catch specific exceptions that you anticipate might occur. For example, `requests.get` might raise `requests.RequestExc…
40.3s815 output tokens
Mercury 2.5
Here is a review of the function with suggestions for improvement.
### Key Observations
1. **Imports:** Libraries should be imported at the module level, not inside functions.
2. **Exception Handling:** Bare `except:` clauses catch system exits and interrupts. Use specific exceptions like `requests.exceptions.RequestException`.
3. **Logic & Pythonicity:**
* Avoid `== True`; rely on truthiness or `item.get("active")`.
* List comprehensions are more concise and efficient than manual appending.
4. **Retry Strategy:** Implement exponential backoff instead of fixed sleeps, and avoid sleeping after the final failed attempt.
5. **Documentation:** Add type hints and a docstring fo…
4.6s1999 output tokens
Frequently asked questions
- Which is cheaper, Llama 3.3 70B Instruct or Mercury 2.5?
- Per 1M output tokens, Llama 3.3 70B Instruct is ¥57.18 and Mercury 2.5 is ¥26.81 on FastMetal (yen, before tax), so Mercury 2.5 is cheaper.
- How do the context windows of Llama 3.3 70B Instruct and Mercury 2.5 compare?
- Llama 3.3 70B Instruct takes 131,072 tokens; Mercury 2.5 takes 260,000.
- Can I use Llama 3.3 70B Instruct and Mercury 2.5 with the same API key?
- Yes. On FastMetal's OpenAI-compatible endpoint, switch by passing "llama-3.3-70b-instruct" or "mercury-2.5" 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 Llama 3.3 70B Instruct and Mercury 2.5 from the browser chat and the API. No monthly fee.