GPT-4.1 vs gpt-oss-120b

Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.

GPT-4.1

OpenAI · Apr 2025

A non-reasoning workhorse with a 1M-token context window, still popular for predictable-latency production APIs.

gpt-oss-120b

OpenAI · Aug 2025

OpenAI's open-weights MoE reasoning model under Apache 2.0 — near o4-mini quality, runnable on a single 80GB GPU.

The verdict

gpt-oss-120b wins 1 of the 1 benchmarks these models share, against 0 for GPT-4.1. On price the gap is dramatic: gpt-oss-120b works out roughly 18x cheaper per blended million tokens. GPT-4.1 also takes 1M of context versus 131K for gpt-oss-120b. And gpt-oss-120b is open-weights (Apache 2.0), so it can be self-hosted — a structural advantage if data control or vendor independence matters.

Benchmark head-to-head 01

GPQA Diamond
66.3%80.1%
GPT-4.1gpt-oss-120b

Specs & pricing

GPT-4.1gpt-oss-120b
modhub Index
Input price / 1M$2$0.1
Output price / 1M$8$0.5
Context window1M131K
Max output33K131K
Open weightsnoyes (Apache 2.0)
Reasoning modelnoyes
Multimodal inputtext, imagetext
Knowledge cutoffJun 2024Jun 2024
ReleasedApr 2025Aug 2025
Example monthly cost*$32.00$1.75

* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.

Frequently asked questions

Which is better, GPT-4.1 or gpt-oss-120b?
gpt-oss-120b wins 1 of the 1 benchmarks these models share, against 0 for GPT-4.1. On price the gap is dramatic: gpt-oss-120b works out roughly 18x cheaper per blended million tokens. GPT-4.1 also takes 1M of context versus 131K for gpt-oss-120b. And gpt-oss-120b is open-weights (Apache 2.0), so it can be self-hosted — a structural advantage if data control or vendor independence matters.
Which is cheaper, GPT-4.1 or gpt-oss-120b?
GPT-4.1 costs $2/$8 per million input/output tokens, while gpt-oss-120b costs $0.1/$0.5. For a typical workload of 10M input and 1.5M output tokens per month, that's $32.00 versus $1.75.
Which model is better for coding, GPT-4.1 or gpt-oss-120b?
We don't yet track SWE-bench Verified results for both models; check their individual pages for coding-related scores.

More comparisons