Model comparison

Claude Haiku 4.5 vs Mercury 2.5

Pricing, context window and real answers (September 2026)

Claude Haiku 4.5 (Anthropic) 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

anthropic logoClaude Haiku 4.5Mercury 2.5
ProviderAnthropicInception
Input (per 1M tokens)¥184.8¥6.77
Output (per 1M tokens)¥924¥25.38
Typical cost (1,000 in + 500 out tokens × 1,000 calls)¥647¥19
Context window200,000 tokens260,000 tokens
Release date10/15/20259/8/2026
Input modalitiesimage, texttext
Arena · overall#131 · ELO 1,413Unranked
Arena · Japanese#112 · ELO 1,357Unranked
Arena · coding#96 · ELO 1,481Unranked

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: ¥25.38 per 1M output tokens, 97% less than Claude Haiku 4.5.
  • For long documents, Mercury 2.5: a 260,000-token context window against 200,000 for Claude Haiku 4.5.
  • 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.

Claude Haiku 4.5

# Counting the 'r's in "strawberry" Let me go through each letter in the word "strawberry": 1. **s** - not an 'r' 2. **t** - not an 'r' 3. **r** - this is an 'r' ✓ (1st) 4. **a** - not an 'r' 5. **w** - not an 'r' 6. **b** - not an 'r' 7. **e** - not an 'r' 8. **r** - this is an 'r' ✓ (2nd) 9. **r** - this is an 'r' ✓ (3rd) 10. **y** - not an 'r' **Answer: There are 3 'r's in "strawberry"** The 'r's appear in positions 3, 8, and 9 of the word.
4.1s228 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…

Claude Haiku 4.5

# TypeError: Cannot read properties of undefined (reading 'map') This error occurs because `users` is `undefined` when the component renders. You're trying to call `.map()` on `undefined`, which doesn't have that method. ## Common Causes 1. **Parent component didn't pass the `users` prop** 2. **Async data hasn't loaded yet** 3. **Props passed incorrectly** ## Solutions ### 1. **Provide a Default Value** (Recommended) ```javascript function UserList({ users = [] }) { return ( <ul> {users.map(user => <li key={user.id}>{user.name}</li>)} </ul> ); } ``` ### 2. **Add a Conditional Check** ```javascript function UserList({ users }) { if (!users) { return <p>No users a…
3.9s671 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):…

Claude Haiku 4.5

# Code Review and Improvements ## Issues Found 1. **Bare `except`** - Catches all exceptions, hiding bugs 2. **Imports inside function** - Should be at module level 3. **Redundant comparison** - `== True` is unnecessary 4. **No logging** - Hard to debug failures 5. **Magic numbers** - Hardcoded timeout and sleep values 6. **Inefficient retries** - Doesn't retry on 200 with parsing errors 7. **Poor variable names** - `r`, `i` are unclear 8. **No type hints** - Reduces code clarity ## Improved Version ```python import logging import requests import time from typing import Optional from requests.exceptions import RequestException logger = logging.getLogger(__name__) def get_data( url:…
5.7s988 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

Compare on more prompts →

Frequently asked questions

Which is cheaper, Claude Haiku 4.5 or Mercury 2.5?
Per 1M output tokens, Claude Haiku 4.5 is ¥924 and Mercury 2.5 is ¥25.38 on FastMetal (yen, before tax), so Mercury 2.5 is cheaper.
How do the context windows of Claude Haiku 4.5 and Mercury 2.5 compare?
Claude Haiku 4.5 takes 200,000 tokens; Mercury 2.5 takes 260,000.
Can I use Claude Haiku 4.5 and Mercury 2.5 with the same API key?
Yes. On FastMetal's OpenAI-compatible endpoint, switch by passing "anthropic-claude-haiku-4-5" 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 Claude Haiku 4.5 and Mercury 2.5 from the browser chat and the API. No monthly fee.

More comparisons with Claude Haiku 4.5

More comparisons with Mercury 2.5