Is GPT-5.6 Luna or DeepSeek V4 Flash cheaper?

DeepSeek V4 Flash is cheaper for a typical request of 1,000 input and 500 output tokens: $0.00028 versus $0.0008 for GPT-5.6 Luna, about 65% less.

What are the per-token prices of GPT-5.6 Luna and DeepSeek V4 Flash?

GPT-5.6 Luna costs $0.20 input and $1.20 output per million tokens. DeepSeek V4 Flash costs $0.14 input and $0.28 output per million tokens.

Which has the larger context window, GPT-5.6 Luna or DeepSeek V4 Flash?

GPT-5.6 Luna has the larger context window: 1.05M tokens versus 1M for DeepSeek V4 Flash.

OpenAI vs DeepSeek

GPT-5.6 Luna vs DeepSeek V4 Flash: pricing comparison

DeepSeek V4 Flash costs 2.9× less than GPT-5.6 Luna for a typical 1,000-input, 500-output request. Here is how the two compare on price, context and discounts.

Prices last updated: September 25, 2026

	GPT-5.6 Luna	DeepSeek V4 Flash
Provider	OpenAI	DeepSeek
Input per 1M tokens	$0.20	$0.14
Output per 1M tokens	$1.20	$0.28
Context window	1.05M	1M
Batch discount	50% off	Not offered
Typical request (1,000 in / 500 out)	$0.0008	$0.00028
Monthly at 1,000 requests/day	$24.00	$8.40

GPT-5.6 Luna: Inputs above 272K tokens are billed at a higher long-context rate ($0.40 / $1.80).

DeepSeek V4 Flash: Open-weight model; price shown is DeepSeek's first-party API (cache-miss input).

Compare with your own numbers

Input tokens

Output tokens

Requests / day

GPT-5.6 Luna per request: $0.0008
Per month: $24.00

DeepSeek V4 Flash per request: $0.00028
Per month: $8.40

Cost by task

Cost per 1,000 requests at standard prices.
Task	Tokens (in / out)	GPT-5.6 Luna	DeepSeek V4 Flash
Short chat reply	500 / 300	$0.46	$0.154
RAG answer	6,000 / 600	$1.92	$1.01
Summarize a long document	12,000 / 1,000	$3.60	$1.96
Output-heavy generation	1,000 / 4,000	$5.00	$1.26

Output tokens usually dominate the bill — see input vs output token cost.

Frequently asked questions

Is GPT-5.6 Luna or DeepSeek V4 Flash cheaper?: DeepSeek V4 Flash is cheaper for a typical request of 1,000 input and 500 output tokens: $0.00028 versus $0.0008 for GPT-5.6 Luna, about 65% less.
What are the per-token prices of GPT-5.6 Luna and DeepSeek V4 Flash?: GPT-5.6 Luna costs $0.20 input and $1.20 output per million tokens. DeepSeek V4 Flash costs $0.14 input and $0.28 output per million tokens.
Which has the larger context window, GPT-5.6 Luna or DeepSeek V4 Flash?: GPT-5.6 Luna has the larger context window: 1.05M tokens versus 1M for DeepSeek V4 Flash.

More comparisons

All comparisons →