BroadRouter

DeepSeek V4.1 Flash API pricing: per token, cached and plans

By the BroadNet Inference team · 5 min read · Published · Updated

On BroadNet Inference, DeepSeek V4.1 Flash costs $0.175 per 1M input tokens, $0.0055 per 1M cached input tokens and $0.52 per 1M output tokens, reasoning included. Or pay a flat price per session: $60 a month, $15 a week or $1 an hour, with no token meter, one request at a time.

DeepSeek V4.1 Flash is the model on BroadNet’s unlimited plans and one of four chat models sold per token. That gives you four ways to pay for the same model: per token, or a monthly, weekly or hourly plan. This page lists all of them, works through real requests, and shows where each option wins. Prices come from BroadNet’s pricing file, synced 2026-11-14. For the same model’s price at every host we track, see the DeepSeek V4.1 Flash price page. For how it sits against the rest of the market, see the LLM API price index.

How much does DeepSeek V4.1 Flash cost per token?

Token type Price per 1M tokens
Input $0.175
Cached input $0.0055
Output, including reasoning $0.52

Model ID: broadnet/deepseek-v4.1-flash. Context: 1,048,576 tokens per request, prompt and answer together. Input: text and images, with images billed as input tokens. A pay-as-you-go key allows 30 requests a minute and 4 in flight.

What do the flat plans cost?

Plan Price per session Period Paid by
Full Moon $60 Month, renews Card
Orbit $15 Week Account balance
Meteor $1 One hour from purchase Account balance

Each session gives unlimited DeepSeek V4.1 Flash tokens, one request at a time. There is no token meter, no monthly cap, no 5-hour window and no weekly limit. With a founders code, Full Moon is $45 a month for the first three months. Running Orbit every week for a month works out to $64.29, so Full Moon is the cheaper way to cover a whole month. How sessions work.

What does one request cost?

Three typical shapes, sized to land on round token totals:

Workload Tokens Cost
100 chat requests of 10,000 input and 1,000 output tokens 1M input, 0.1M output $0.175 plus a tenth of $0.52
10 agent turns re-sending a 100,000-token cached repository 1M cached input $0.0055
1,000 answers of 1,000 tokens, reasoning included 1M output $0.52

The cache line is the one that matters for agents. Cached input costs $0.0055 per 1M on this model, against $0.175 for new input, so a stable prompt prefix is usually the biggest single saving. How to raise your cache rate, or model your own hit rate in the prompt caching calculator.

What does a month cost per token?

BroadNet’s worked scenarios, priced on the per-token rates above:

Workload Input a month Cache hits Output a month Per token Cheaper option
Side project 100M 50% 10M $14.23 pay as you go
Daily assistant 300M 50% 30M $42.67 pay as you go
Full-time coding agent 1,000M 80% 50M $65.40 Full Moon
Always-on agent 3,000M 80% 150M $196.20 Full Moon

At 80% cache hits and 20 input tokens per output token, one Full Moon session breaks even at about 917 million input and 46 million output tokens a month. The full break-even math, or plug in your own volumes with the flat-rate vs per-token calculator.

How much can one plan session process?

A session runs one request at a time. At a typical speed of about 100 tokens per second, a session generating non-stop for 30 days would produce about 259 million output tokens. Real agents read, run tools and wait, so the practical figure is lower. To go faster, run more sessions in parallel; parallel agents on a flat rate explains how many you need.

How does this compare with other providers?

Published prices for the same model, per 1M tokens, fetched 14 November 2026 from each provider’s pricing page. DeepSeek’s own API now takes the model name deepseek-flash (version DeepSeek-V4.1-Flash-1017). DeepInfra shows its rates as discounts from a list price of USD 0.20 / 0.006 / 0.60 and does not say when the discounts end:

Provider Input Cached input Output
BroadNet Inference $0.175 $0.0055 $0.52
DeepSeek API, peak hours USD 0.30 USD 0.006 USD 1.20
DeepSeek API, off-peak USD 0.15 USD 0.003 USD 0.60
Together AI USD 0.30 USD 0.006 USD 1.20
Fireworks AI, standard USD 0.30 USD 0.006 USD 1.20
Fireworks AI, spot USD 0.21 USD 0.0042 USD 0.84
DeepInfra, DeepSeek-V4.1-Flash, 30% off list USD 0.14 USD 0.0042 USD 0.42
DeepInfra, DeepSeek-V4.1-Flash-1017, 51% off list USD 0.098 USD 0.0029 USD 0.294

BroadNet’s rates are below Together’s, Fireworks’ and DeepSeek’s peak rates, but not the lowest. DeepInfra’s discounted listings are cheaper than BroadNet on input, cached input and output at any hour. DeepSeek’s own API halves its prices outside its peak windows (01:00 to 04:00 and 06:00 to 10:00 UTC on weekdays), which makes its off-peak input and cached input cheaper than BroadNet’s, while its output stays higher. Fireworks’ spot tier is also cheaper on cached input. Routers list more offers; the provider pricing comparison covers them with sources.

What else affects the bill?

  • Reasoning. DeepSeek V4.1 Flash thinks before answering. Set reasoning_effort to low for simple steps, and keep max_tokens at 1,000 or more. Why replies come back empty.
  • Retries. A retried request is a new inference and is billed again on per-token keys.
  • Images. Billed as input tokens on per-token keys, included on plans.
  • Long context. Every turn resends the context. Caching keeps that cheap; when a 1M context is worth it.

Which DeepSeek V4.1 Flash pricing option should you choose?

  1. Start on pay-as-you-go and log a week of prompt_tokens, cached_tokens and completion_tokens.
  2. Multiply by about 4.3 and put the totals in the LLM API cost calculator or the BroadNet pricing page.
  3. If a plan wins, test your agent on a $1 Meteor hour. The Aider setup guide gets a terminal agent running in minutes.
  4. If you need tools and structured output listed by BroadNet, also compare GLM 5.3 vs DeepSeek V4.1 Flash. For other ways to reach DeepSeek models, see DeepSeek API alternatives.

Where BroadNet Inference fits

BroadNet is the option if you want DeepSeek V4.1 Flash both per token and unlimited on one account, with a 1M context and zero data retention. It is not the cheapest per-token price: DeepInfra’s discounted listings are lower on every rate, and DeepSeek’s off-peak input and cached rates are lower. For light or bursty traffic billed per token, those may cost less. BroadNet’s edge is the flat plan once an agent runs most of the day, plus no content retained. Choose a plan.

Questions

How much does DeepSeek V4.1 Flash cost per million tokens?

On BroadNet Inference, $0.175 per 1M input tokens, $0.0055 per 1M cached input tokens and $0.52 per 1M output tokens.

Is there an unlimited DeepSeek API plan?

Yes. BroadNet's Full Moon plan is $60 a month per session with no token meter, no monthly cap and no weekly limit. One session runs one request at a time.

Are reasoning tokens extra?

On per-token keys, reasoning is reported in completion tokens and billed at the output price. On a plan, there is no token meter, so reasoning costs nothing extra.

Can I use DeepSeek V4.1 Flash on the free credit?

No. DeepSeek V4.1 Flash is available after a top-up. The $5 starting credit covers Gemma 4 VL 26B, the two transcription models and hourly keys.

When are DeepSeek API off-peak hours?

DeepSeek's pricing page (fetched 14 November 2026) lists peak hours as 01:00 to 04:00 and 06:00 to 10:00 UTC, Monday to Friday, excluding Chinese public holidays. All other hours, including weekends, are billed at half the peak rate.

How does BroadNet's price compare with DeepSeek's own API?

BroadNet is not the cheapest per token. DeepSeek's off-peak input and cached input are cheaper than BroadNet's (its output is dearer), and DeepInfra lists a discounted DeepSeek-V4.1-Flash-1017 below BroadNet on all three rates. BroadNet's edge is the flat plan at high volume, zero data retention and one key for chat and speech to text.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity