GPT-6 Luna vs DeepSeek V4.1 Flash: API price, context and cost per task
Two of the cheapest capable models: OpenAI's GPT-6 Luna and DeepSeek V4.1 Flash, the first DeepSeek model built on its Causal Encoder-Decoder architecture.
On output, GPT-6 Luna is 1.1x cheaper ($0.5 vs $0.567 per million tokens). On input, DeepSeek V4.1 Flash is 2x cheaper ($0.051 vs $0.1 per million tokens). GPT-6 Luna reads more per request: 1,050,000 tokens against 1,048,576.
Data updated 2026-11-11 - source: public OpenRouter model list, refreshed daily. Prices in USD, excluding VAT.
Specs and prices side by side
| GPT-6 Luna | DeepSeek V4.1 Flash | |
|---|---|---|
| Vendor | OpenAI | DeepSeek |
| Input, per 1M tokens | $0.1 | $0.051 |
| Output, per 1M tokens | $0.5 | $0.567 |
| Cached input, per 1M | $0.01 | $0.018 |
| Batch (input / output) | $0.05 / $0.25 | $0.112 / $0.336 |
| Context window | 1,050,000 | 1,048,576 |
| Max output | 128,000 | 943,718 |
| Input types | text, images, files | text, images |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| On OpenRouter since | 22 Sep 2026 | 10 Sep 2026 |
Highlighted: the cheaper price or the larger limit. "Not published" means the figure is not in the public model listing yet.
What a month of work costs
Four typical workloads at today's list prices. Reasoning models also bill their thinking as output tokens, so treat output-heavy numbers as a floor.
| Workload | GPT-6 Luna | DeepSeek V4.1 Flash | Difference |
|---|---|---|---|
| Support chatbot10,000 conversations a month, about 1,500 input and 400 output tokens each | $3.50 | $3.03 | DeepSeek V4.1 Flash 1.2x cheaper |
| Coding agent300 tasks a month, about 80,000 input tokens (code context re-read across steps) and 8,000 output tokens each | $3.60 | $2.58 | DeepSeek V4.1 Flash 1.4x cheaper |
| Coding agent with caching70% of input served from the prompt cache | $2.09 | $2.03 | |
| Long-document analysis1,000 documents a month, about 50,000 tokens in and a 1,500-token summary out | $5.75 | $3.40 | DeepSeek V4.1 Flash 1.7x cheaper |
| Content drafting600 articles a month, about 3,000 tokens of brief in and 2,500 tokens of draft out | $0.93 | $0.942 | GPT-6 Luna 1x cheaper |
Price stability over the last 30 days
- GPT-6 Luna: no change in the last 30 days.
- DeepSeek V4.1 Flash: 14 price changes since 12 Oct 2026. Input ranged $0.0137 - $0.3, output $0.0112 - $1.2 per million tokens. Volatile: the listed price follows whichever provider OpenRouter currently routes to, so budget with the upper end of the range.
DeepSeek V4.1 Flash: price log
| Date | Input | Output |
|---|---|---|
| 2026-11-07 | $0.051 | $0.567 |
| 2026-10-29 | $0.045 | $0.5 |
| 2026-10-27 | $0.14 | $0.42 |
| 2026-10-24 | $0.02 | $1 |
| 2026-10-23 | $0.165 | $0.66 |
| 2026-10-22 | $0.3 | $1.2 |
| 2026-10-21 | $0.049 | $0.525 |
| 2026-10-20 | $0.0352 | $0.0112 |
What the vendors and benchmarks say
GPT-6 Luna
"GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol."model card on OpenRouter
DeepSeek V4.1 Flash
"DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture."model card on OpenRouter
Which one to pick
DeepSeek V4.1 Flash usually wins on input price, but its OpenRouter rate has jumped up and down repeatedly over the past month, while Luna's list price has stayed put. For predictable costs and file input, Luna; for the lowest input cost on huge contexts, V4.1 Flash - check today's rate first.
Related reading
How we calculate
Prices are the public per-token list rates from OpenRouter's model list, which match the vendors' own API prices for first-party models and show the current routed price for open-weight models served by several hosts. Monthly costs multiply those rates by the token volumes in each workload; caching assumes the stated share of input is billed at the cached-input rate. Benchmarks and claims are quoted from the named sources, mostly the vendors themselves - treat them as a guide and test on your own tasks. See also the AI cost calculator and all tracked model prices.
Frequently asked questions
Which is cheaper, GPT-6 Luna or DeepSeek V4.1 Flash?
As of 11 Nov 2026, GPT-6 Luna costs $0.1 per million input tokens and $0.5 per million output tokens; DeepSeek V4.1 Flash costs $0.051 and $0.567. GPT-6 Luna is cheaper in 1 of the 4 monthly workloads we price on this page. The real bill also depends on how many reasoning tokens each model writes.
Which has the larger context window?
GPT-6 Luna reads up to 1,050,000 tokens and can write up to 128,000; DeepSeek V4.1 Flash reads up to 1,048,576 and writes up to 943,718.
How much does a support chatbot cost on each model?
For 10,000 conversations a month (about 15 million input and 4 million output tokens) you would pay about $3.50 on GPT-6 Luna and $3.03 on DeepSeek V4.1 Flash at list prices, before any caching or batch discounts.
Do they offer prompt caching or batch discounts?
GPT-6 Luna lists cached input at $0.01 per million and a batch rate of $0.05 / $0.25. DeepSeek V4.1 Flash lists cached input at $0.018 per million and a batch rate of $0.112 / $0.336. Caching matters most for agents and chatbots that resend the same context on every turn.
// follow
New tests and price changes, straight to your feed reader
Free RSS, no account and no email needed.
Follow Quantslant →