Fugu Max vs Inkling
Pricing, context window and real answers (September 2026)
Fugu Max (Sakana AI) and Inkling (Thinking Machines), 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
| Fugu Max | Inkling | |
|---|---|---|
| Provider | Sakana AI | Thinking Machines |
| Input (per 1M tokens) | ¥357.4 | ¥178.7 |
| Output (per 1M tokens) | ¥1,072.2 | ¥723.74 |
| Typical cost (1,000 in + 500 out tokens × 1,000 calls) | ¥894 | ¥541 |
| Context window | 1,000,000 tokens | 524,288 tokens |
| Release date | 9/11/2026 | 7/17/2026 |
| Input modalities | text, image, file | text, image, audio |
| Throughput (p50) | — | — |
| Arena · overall | Unranked | #85 · ELO 1,440 |
| Arena · Japanese | Unranked | #63 · ELO 1,415 |
| Arena · coding | Unranked | #78 · ELO 1,492 |
Prices are FastMetal's yen rates before tax. Arena ranks are as of the latest leaderboard scrape.
Which should you pick?
- On price, Inkling: ¥723.74 per 1M output tokens, 32% less than Fugu Max.
- For long documents, Fugu Max: a 1,000,000-token context window against 524,288 for Inkling.
- 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.
Fugu Max
Inkling
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…
Fugu Max
Inkling
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):…
Fugu Max
Inkling
Frequently asked questions
- Which is cheaper, Fugu Max or Inkling?
- Per 1M output tokens, Fugu Max is ¥1,072.2 and Inkling is ¥723.74 on FastMetal (yen, before tax), so Inkling is cheaper.
- How do the context windows of Fugu Max and Inkling compare?
- Fugu Max takes 1,000,000 tokens; Inkling takes 524,288.
- Can I use Fugu Max and Inkling with the same API key?
- Yes. On FastMetal's OpenAI-compatible endpoint, switch by passing "fugu-max" or "inkling" 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 Fugu Max and Inkling from the browser chat and the API. No monthly fee.