Gemini 3.1 Pro Preview vs Inkling
Pricing, context window and real answers (September 2026)
Gemini 3.1 Pro Preview (Google) 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
| Inkling | ||
|---|---|---|
| Provider | Thinking Machines | |
| Input (per 1M tokens) | ¥357.4 | ¥178.7 |
| Output (per 1M tokens) | ¥2,144.4 | ¥723.74 |
| Typical cost (1,000 in + 500 out tokens × 1,000 calls) | ¥1,430 | ¥541 |
| Context window | 1,048,576 tokens | 524,288 tokens |
| Release date | 2/19/2026 | 7/17/2026 |
| Input modalities | audio, file, image, text, video | text, image, audio |
| Throughput (p50) | — | — |
| Arena · overall | #15 · ELO 1,487 | #85 · ELO 1,440 |
| Arena · Japanese | #9 · ELO 1,494 | #63 · ELO 1,415 |
| Arena · coding | #28 · ELO 1,520 | #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, 66% less than Gemini 3.1 Pro Preview.
- On the Overall arena board, Gemini 3.1 Pro Preview ranks higher (#15; Inkling is #85).
- On the Japanese arena board, Gemini 3.1 Pro Preview ranks higher (#9; Inkling is #63).
- On the Coding arena board, Gemini 3.1 Pro Preview ranks higher (#28; Inkling is #78).
- For long documents, Gemini 3.1 Pro Preview: a 1,048,576-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.
Gemini 3.1 Pro Preview
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…
Gemini 3.1 Pro Preview
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):…
Gemini 3.1 Pro Preview
Inkling
Frequently asked questions
- Which is cheaper, Gemini 3.1 Pro Preview or Inkling?
- Per 1M output tokens, Gemini 3.1 Pro Preview is ¥2,144.4 and Inkling is ¥723.74 on FastMetal (yen, before tax), so Inkling is cheaper.
- How do the context windows of Gemini 3.1 Pro Preview and Inkling compare?
- Gemini 3.1 Pro Preview takes 1,048,576 tokens; Inkling takes 524,288.
- Which ranks higher, Gemini 3.1 Pro Preview or Inkling?
- Gemini 3.1 Pro Preview ranks higher on the public arena (Gemini 3.1 Pro Preview #9, Inkling #63). Ranks move as the leaderboard updates.
- Can I use Gemini 3.1 Pro Preview and Inkling with the same API key?
- Yes. On FastMetal's OpenAI-compatible endpoint, switch by passing "gemini-3.1-pro-preview" 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 Gemini 3.1 Pro Preview and Inkling from the browser chat and the API. No monthly fee.