Gemini 3.7 Flash vs gpt-oss-120b
Pricing, context window and real answers (August 2026)
Gemini 3.7 Flash (Google) 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
| Provider | OpenAI | |
|---|---|---|
| Input (per 1M tokens) | ¥134.03 | ¥16 |
| Output (per 1M tokens) | ¥670.13 | ¥79 |
| Typical cost (1,000 in + 500 out tokens × 1,000 calls) | ¥469 | ¥56 |
| Context window | 1,048,576 tokens | 131,072 tokens |
| Release date | 8/13/2026 | 8/5/2025 |
| Input modalities | text, image, video, file, audio | text |
| Arena · overall | Unranked | #186 · ELO 1,352 |
| Arena · Japanese | Unranked | #123 · ELO 1,320 |
| Arena · coding | Unranked | #190 · ELO 1,390 |
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, 88% less than Gemini 3.7 Flash.
- For long documents, Gemini 3.7 Flash: 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.
Gemini 3.7 Flash
gpt-oss-120b
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 3.7 Flash
gpt-oss-120b
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 3.7 Flash
gpt-oss-120b
Frequently asked questions
- Which is cheaper, Gemini 3.7 Flash or gpt-oss-120b?
- Per 1M output tokens, Gemini 3.7 Flash is ¥670.13 and gpt-oss-120b is ¥79 on FastMetal (yen, before tax), so gpt-oss-120b is cheaper.
- How do the context windows of Gemini 3.7 Flash and gpt-oss-120b compare?
- Gemini 3.7 Flash takes 1,048,576 tokens; gpt-oss-120b takes 131,072.
- Can I use Gemini 3.7 Flash and gpt-oss-120b with the same API key?
- Yes. On FastMetal's OpenAI-compatible endpoint, switch by passing "gemini-3.7-flash" 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 Gemini 3.7 Flash and gpt-oss-120b from the browser chat and the API. No monthly fee.