
Model comparison
DeepSeek V4.1 Flash vs GPT-6 Luna API price, context and cost.
DeepSeek V4.1 Flash (DeepSeek) and GPT-6 Luna (OpenAI) side by side: per-1M prices, cached-input rates, context, output limits and capability flags from the live RouterPlex catalog, with three worked costs. A coding-agent session costs $0.25 on DeepSeek V4.1 Flash and $0.11 on GPT-6 Luna. Both run on one prepaid key with the same OpenAI-compatible request.
Side by side
Catalog fields, one row each.
| Catalog field | DeepSeek V4.1 Flash | GPT-6 Luna |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Model ID | deepseek-v4.1-flash | gpt-6-luna |
| Input / 1M | $0.18 | $0.10 |
| Output / 1M | $0.73 | $0.50 |
| Cached input / 1M | $0.065 | $0.014 |
| Context window | 1M (1,000,000 tokens) | 922K (922,000 tokens) |
| Max output | 384K tokens | 128K tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Reasoning | Yes | Yes |
| Long-prompt tier | None | $0.20 / $0.75 from 272K |
| Price basis | Vendor list price, 0% markup | Vendor list price, 0% markup |
- DeepSeek V4.1 Flash: DeepSeek prices this model by time of day: $0.15 input / $0.60 output per 1M tokens off-peak, and double that during peak hours (01:00-04:00 and 06:00-10:00 UTC, Monday to Friday). RouterPlex bills a single flat rate in between -- the time-weighted average of the two -- so you are never billed by the clock and never pay the peak rate for off-peak work.
- GPT-6 Luna: Base rate applies at or below 272K prompt tokens. Prompts above 272K are billed at $0.20 input / $0.75 output per 1M tokens for the whole request.
What the catalog says
GPT-6 Luna is 44% cheaper on input ($0.10 against $0.18 per 1M tokens). GPT-6 Luna is 32% cheaper on output ($0.50 against $0.73 per 1M tokens). GPT-6 Luna is 78% cheaper on cached input ($0.014 against $0.065 per 1M tokens). On the coding-agent session below, GPT-6 Luna costs $0.11 against $0.25 for DeepSeek V4.1 Flash. DeepSeek V4.1 Flash has the larger context window: 1M against 922K. DeepSeek V4.1 Flash can return up to 384K tokens per response, against 128K for GPT-6 Luna. GPT-6 Luna bills prompts of 272K tokens or more at $0.20 input and $0.75 output per 1M for the whole request.
Generated from catalog prices, limits and capability flags. Price does not measure output quality.
Worked cost examples
Same workload, both bills.
Each line multiplies the catalog rate per 1M tokens by the tokens shown. Cached tokens use the route's cached-input rate, or the full input rate when it has no cache discount. Reasoning tokens bill as output, so a model that thinks at length raises the output line beyond these figures. GPT-6 Luna changes rate at 272K prompt tokens; each request below stays under that, so base rates apply.
40 requests of 50K prompt tokens, 80% of each prompt a cache hit, 2.5K output each.
0.4M input x $0.18 + 1.6M cached x $0.065 + 0.1M output x $0.73 = $0.25
0.4M input x $0.10 + 1.6M cached x $0.014 + 0.1M output x $0.50 = $0.11
10,000 conversations of 2K prompt tokens and 500 output tokens, no caching.
20M input x $0.18 + 5M output x $0.73 = $7.25
20M input x $0.10 + 5M output x $0.50 = $4.50
200 requests of 150K prompt tokens and 2K output tokens, no caching.
30M input x $0.18 + 0.4M output x $0.73 = $5.69
30M input x $0.10 + 0.4M output x $0.50 = $3.20
Switching
One key, one line.
Both models sit behind the same RouterPlex key and the same OpenAI-compatible endpoint. Keep the request shape and change the model string. Claude Code and the Anthropic SDK use the same ids on https://api.routerplex.com.
Read the quickstartimport osfrom openai import OpenAIclient = OpenAI(base_url="https://api.routerplex.com/v1",api_key=os.environ["ROUTERPLEX_API_KEY"],)reply = client.chat.completions.create(model="deepseek-v4.1-flash", # switch: "gpt-6-luna"messages=[{"role": "user", "content": "Hello!"}],)print(reply.choices[0].message.content)
# DeepSeek V4.1 Flashcurl https://api.routerplex.com/v1/chat/completions \-H "Authorization: Bearer $ROUTERPLEX_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "deepseek-v4.1-flash", "messages": [{"role": "user", "content": "Hello!"}]}'# GPT-6 Luna: same request, one field changedcurl https://api.routerplex.com/v1/chat/completions \-H "Authorization: Bearer $ROUTERPLEX_API_KEY" \-H "Content-Type: application/json" \-d '{"model": "gpt-6-luna", "messages": [{"role": "user", "content": "Hello!"}]}'
Questions
Before you pick one of the two.
01Is DeepSeek V4.1 Flash cheaper than GPT-6 Luna?+
DeepSeek V4.1 Flash costs $0.18 input and $0.73 output per 1M tokens on RouterPlex; GPT-6 Luna costs $0.10 and $0.50. On a coding-agent session (40 requests of 50K prompt tokens, 80% of each prompt a cache hit, 2.5K output each) DeepSeek V4.1 Flash comes to $0.25 and GPT-6 Luna to $0.11, so GPT-6 Luna is cheaper for that workload. A chat app month (10,000 conversations of 2K prompt tokens and 500 output tokens, no caching) costs $7.25 on DeepSeek V4.1 Flash and $4.50 on GPT-6 Luna.
02Which has the larger context window, DeepSeek V4.1 Flash or GPT-6 Luna?+
DeepSeek V4.1 Flash has the larger window: 1M for DeepSeek V4.1 Flash against 922K for GPT-6 Luna. Maximum output is 384K and 128K tokens respectively.
03Do DeepSeek V4.1 Flash and GPT-6 Luna support image input and tool calling?+
Per the RouterPlex catalog, DeepSeek V4.1 Flash: image input, tool calling, reasoning. GPT-6 Luna: image input, tool calling, reasoning. These flags come from the labs' published model metadata, not from a quality test.
04How do I switch from DeepSeek V4.1 Flash to GPT-6 Luna?+
Change one string. Both run on the same RouterPlex key and the same OpenAI-compatible endpoint (https://api.routerplex.com/v1), so the request stays identical and only model changes from "deepseek-v4.1-flash" to "gpt-6-luna". The same ids work on the Anthropic-compatible /v1/messages endpoint for Claude Code.
05When is DeepSeek V4.1 Flash worth the higher price?+
When the task needs a 1M context window or up to 384K output tokens per response, which DeepSeek V4.1 Flash offers and GPT-6 Luna does not per the catalog. Otherwise the reason to pay more is output you prefer on your own prompts; this page does not rank quality, so run both in the RouterPlex Arena before moving traffic.
Provider pricing
Try both
Both models behind one key.
Top up from $5 with no subscription, then send the same prompt to each.