Google: Gemini 4 Carbon vs GPT-OSS 120B
google/gemini-4-carbon · openai/gpt-oss-120b
As of November 20, 2026, GPT-OSS 120B is the cheaper API on MartLLM: $0.0001 per million input tokens and $0.0003 per million output, versus $0.1996 / $0.9980 for Google: Gemini 4 Carbon, about 99% less when output is 3 tokens for every input token. These are the best prices on the market right now. Both work with one OpenAI-compatible key and MartLLM adds no fee. Choose GPT-OSS 120B to cut cost; choose Google: Gemini 4 Carbon when context size wins. Google: Gemini 4 Carbon carries the larger context window (1,048,576 vs 128,000 tokens), which can matter for long-document work.
Google: Gemini 4 Carbon vs GPT-OSS 120B, side by side
| Spec | ||
|---|---|---|
| Price · input / 1M | $0.1996 | $0.0001 |
| Price · output / 1M | $0.9980 | $0.0003 |
| Context length | 1,048,576 | 128,000 |
| Max output tokens | 524,288 | 16,384 |
| Input modalities | text, image, video, audio, file | text |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | Yes | — |
| Reasoning | Yes | — |
| % off list | 90% off | 99.9% off |
| First token, median (7 days) | 13.5 s (6,826 requests) | 0.5 s (131 requests) |
Best prices on MartLLM right now. No MartLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated November 20, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?
Google: Gemini 4 Carbon vs GPT-OSS 120B — FAQ
Is Google: Gemini 4 Carbon or GPT-OSS 120B cheaper?
GPT-OSS 120B is cheaper on a blended token mix, by about 99%. A request costs what its provider charged, MartLLM adds no fee, and every request is listed with its cost in Activity.
What's the price difference between Google: Gemini 4 Carbon and GPT-OSS 120B?
Google: Gemini 4 Carbon: $0.1996 in / $0.9980 out per 1M tokens. GPT-OSS 120B: $0.0001 in / $0.0003 out per 1M tokens. That's roughly a 99% blended difference. Prices are live; MartLLM adds no fee.
Can I use both Google: Gemini 4 Carbon and GPT-OSS 120B with one API?
Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.martllm.com/v1 and your MartLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.martllm.com/v1/messages.