DeepSeek V4.1 Flash 1017 vs gpt-oss-20b

Price, context window & benchmark comparison

DeepSeek V4.1 Flash 1017

DeepSeek

$0.098 / $0.29

Input / Output · per 1M tokens

gpt-oss-20b

OpenAI

$0.03 / $0.13

Input / Output · per 1M tokens

Compare different models

Verdict: gpt-oss-20b is 2.7× cheaper than DeepSeek V4.1 Flash 1017 on a typical 3:1 input/output mix. DeepSeek V4.1 Flash 1017 has the larger context window (1M vs 131K).

	DeepSeek V4.1 Flash 1017	gpt-oss-20b
Input price / 1M	$0.098	$0.03
Output price / 1M	$0.29	$0.13
Blended price (3:1)	$0.15	$0.055
Cached input / 1M	$0.0029	$0.03
Context window	1M	131K
Max output	393K	118K
Intelligence index	28.6	—
Coding index	—	20.7
Providers	47	—
Best provider uptime (30m)	100.0%	—
Vision input	Yes	No
Reasoning	Yes	Yes
Tool calling	Yes	Yes
Released	2026-10-17	2025-08-05
Retirement	—	—

Cost calculator

Input tokens / requestOutput tokens / requestRequests / day

FAQ

Which is cheaper, DeepSeek V4.1 Flash 1017 or gpt-oss-20b?

gpt-oss-20b is 2.7× cheaper than DeepSeek V4.1 Flash 1017 on a typical 3:1 input/output mix.

DeepSeek V4.1 Flash 1017 vs gpt-oss-20b: which has a bigger context window?

DeepSeek V4.1 Flash 1017: 1,048,576 tokens. gpt-oss-20b: 131,072 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: DeepSeek V4.1 Flash 1017 ≈ $343.00, gpt-oss-20b ≈ $125.00.

More comparisons