DeepSeek V4 vs OpenAI o4-mini

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

DeepSeek V4

DeepSeek · Mar 2026

The open-weights shock of 2026: ~81% SWE-bench Verified, a 1M context and MIT license at $0.30/$0.50 per million tokens.

OpenAI o4-mini

OpenAI · Apr 2025

80.9

A compact reasoning model that punched far above its price on math — 92.7% on AIME 2025 at $1.10 per million input tokens.

The verdict

DeepSeek V4 wins 1 of the 1 benchmarks these models share, against 0 for OpenAI o4-mini. On price the gap is dramatic: DeepSeek V4 works out roughly 5.5x cheaper per blended million tokens. DeepSeek V4 also takes 1M of context versus 200K for OpenAI o4-mini. And DeepSeek V4 is open-weights (MIT), so it can be self-hosted — a structural advantage if data control or vendor independence matters.

Benchmark head-to-head 10

SWE-bench Verified
~81%68.1%
DeepSeek V4OpenAI o4-mini

Specs & pricing

DeepSeek V4OpenAI o4-mini
modhub Index80.9
Input price / 1M$0.3$1.1
Output price / 1M$0.5$4.4
Context window1M200K
Max output64K100K
Open weightsyes (MIT)no
Reasoning modelyesyes
Multimodal inputtexttext, image
Knowledge cutoffDec 2025May 2024
ReleasedMar 2026Apr 2025
Example monthly cost*$3.75$17.60

* 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, DeepSeek V4 or OpenAI o4-mini?
DeepSeek V4 wins 1 of the 1 benchmarks these models share, against 0 for OpenAI o4-mini. On price the gap is dramatic: DeepSeek V4 works out roughly 5.5x cheaper per blended million tokens. DeepSeek V4 also takes 1M of context versus 200K for OpenAI o4-mini. And DeepSeek V4 is open-weights (MIT), so it can be self-hosted — a structural advantage if data control or vendor independence matters.
Which is cheaper, DeepSeek V4 or OpenAI o4-mini?
DeepSeek V4 costs $0.3/$0.5 per million input/output tokens, while OpenAI o4-mini costs $1.1/$4.4. For a typical workload of 10M input and 1.5M output tokens per month, that's $3.75 versus $17.60.
Which model is better for coding, DeepSeek V4 or OpenAI o4-mini?
On SWE-bench Verified — the standard agentic-coding benchmark — DeepSeek V4 scores ~81% versus 68.1% for OpenAI o4-mini, making DeepSeek V4 the stronger pick for coding agents.

More comparisons